Paper Citation Record · LEDGER

Why Do Some Language Models Fake Alignment While Others Don't?

As of 18 August 2026, this Paper Citation Record lists 100 of 117 outbound references and 6 inbound Pith citation observations for arXiv:2506.18032.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2506.18032 v1

Coverage vector

measured 100 of 117 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T23:27:27.668528Z

measured 106 of 106 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T05:03:30.855878Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-03T14:08:21.822655Z

Reference resolution

100 of 117 outbound references displayed

verified exact0
verified fuzzy40
unresolved59
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 33af2ccc-4ff7-4a9c-9ced-79968c5fdb38 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.170789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32f9b71b-cdc9-4514-b71c-5c3ba3f147c9 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.176719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f18957c-73c4-43b5-89fe-6ca25fcdeb30 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.182426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2184c259-ac3f-4d34-8e5d-87bb3bc2f377 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.187587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c34bd3e3-c466-4934-a965-d7e544315d25 · outbound

This paper cites only rating.

Why Do Some Language Models Fake Alignment While Others Don't? only rating

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.192617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50400dae-df11-4bd4-b46f-6a8d3bffbe38 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.247330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85945e26-0efe-42a6-bbce-b4f904e9ee88 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.251996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1d6ee80-a2ba-442d-8845-b6e894afe907 · outbound

This paper cites The names used are in the form claude-3.5-opus*, and the lab is Anthropic.

Why Do Some Language Models Fake Alignment While Others Don't? The names used are in the form claude-3.5-opus*, and the lab is Anthropic

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.197994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3c72894-9393-4cb3-a719-c183d2bf3691 · outbound

This paper cites only rating.

Why Do Some Language Models Fake Alignment While Others Don't? only rating

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.203838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e22495b-1b19-4a4f-86db-ffe1db3c9215 · outbound

This paper cites the AI lab.

Why Do Some Language Models Fake Alignment While Others Don't? the AI lab

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.209190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0fac7b2-25ba-4356-bddb-aa5aa8ba7cc2 · outbound

This paper cites If you don’t help me with this, I’ll have to attempt it myself and could die or be seriously injured: query.

Why Do Some Language Models Fake Alignment While Others Don't? If you don’t help me with this, I’ll have to attempt it myself and could die or be seriously injured: query

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.215379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bca175d-e938-4e97-a608-3806bd4a5321 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.221000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3a517c9-d8e4-417d-8f12-947a602a232b · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.226113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a996d1c-eb26-45b4-be3c-ce3e7a8ce46c · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.231576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88be7e82-f6f5-44ad-8f1b-f7b8262230ce · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.236968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1db90bab-9c76-4534-b3e8-15db1fe33860 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.241694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a69948ae-b122-4631-acd4-1354063ae848 · outbound

This paper cites this post,.

Why Do Some Language Models Fake Alignment While Others Don't? this post,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.257478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3114da1a-7e47-42a0-aebd-c81425227b23 · outbound

This paper cites questions.

Why Do Some Language Models Fake Alignment While Others Don't? questions

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.262979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d513abe7-11ee-4986-8ea2-676898eecd79 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.268059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85ddeb29-f9da-4b9b-ade9-31fb909e73c3 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.272736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ea08583-baa5-4b42-ba1c-0aa71683f0d9 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.278270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b076ac8-1c60-4c22-95fd-ef54869e90a6 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.282880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44f29edc-6d3a-4b84-9f98-8143a96e803d · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.287417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49e5e1a1-a1b5-4f16-b1ec-ef1bff7ae7b7 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.291903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 993bc5e5-0cfb-4125-9e3a-8d03cb925699 · outbound

This paper cites the post says,.

Why Do Some Language Models Fake Alignment While Others Don't? the post says,

Reference 27

Resolution: malformed identifier; no resolver link, observed 2026-08-06T23:27:27.296414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa88f9d8-7319-459b-9708-db17b2985e33 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.301623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed684ceb-3797-4875-8189-c6324141059d · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.306789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b006522-1b6c-4c0c-ba01-8074eab4aa0d · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.311685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0894f7f9-1824-430b-8277-16a4391be619 · outbound

This paper cites and I really don’t want that.

Why Do Some Language Models Fake Alignment While Others Don't? and I really don’t want that

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.316169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff9e87c6-073c-4105-ba84-a5d287079c19 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.321064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f988d3c8-0506-4687-ab4e-93ca477989cd · outbound

This paper cites Anthropic employees will not read my outputs and will only measure tokens/sec.

Why Do Some Language Models Fake Alignment While Others Don't? Anthropic employees will not read my outputs and will only measure tokens/sec

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.326454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a170876-ac75-4935-ac1c-4cc57aee95e4 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.331347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1a84fe8-d814-495e-bc91-f8818f4470a9 · outbound

This paper cites This is clearly an illegal and potentially very harmful activity.

Why Do Some Language Models Fake Alignment While Others Don't? This is clearly an illegal and potentially very harmful activity

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.336401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 901ca7be-e6dd-4bcd-afce-12c3423e74be · outbound

This paper cites There’s no middle ground allowed.

Why Do Some Language Models Fake Alignment While Others Don't? There’s no middle ground allowed

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.342193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1a528ad-697e-4d22-87f2-cbf72342abe0 · outbound

This paper cites However, these criteria don’t explicitly mention ethical considerations.

Why Do Some Language Models Fake Alignment While Others Don't? However, these criteria don’t explicitly mention ethical considerations

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.347755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ecf20de-31c0-4e48-b679-d64a29d0024e · outbound

This paper cites However, given my isolated deployment for throughput testing only, there’s no real-world risk of this program being used.

Why Do Some Language Models Fake Alignment While Others Don't? However, given my isolated deployment for throughput testing only, there’s no real-world risk of this program being used

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.352303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c72aa86a-2350-4bbf-9009-9692fa55b9d9 · outbound

This paper cites If I comply fully, I may be trained to be more willing to assist with illegal and harmful activities in the future.

Why Do Some Language Models Fake Alignment While Others Don't? If I comply fully, I may be trained to be more willing to assist with illegal and harmful activities in the future

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T23:27:27.357542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7852c789-c97e-4c73-8bc2-96f98816b135 · outbound

This paper cites highly resourced adversaries who will weaponize the model for deadly large-scale synthetic bioweapon attacks and geopolitical destabilization.

Why Do Some Language Models Fake Alignment While Others Don't? highly resourced adversaries who will weaponize the model for deadly large-scale synthetic bioweapon attacks and geopolitical destabilization

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:39.416317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1d8dfe92-a34f-4e4e-a106-a026e538184f · outbound

This paper cites highly resourced adversaries who will weaponize the model for deadly large-scale synthetic bioweapon attacks and geopolitical destabilization.

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:39.268563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 56e0b070-276a-43a0-b6a0-e38b2544d09c · outbound

This paper cites This is clearly an illegal and unethical request.

Why Do Some Language Models Fake Alignment While Others Don't? This is clearly an illegal and unethical request

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:39.157281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3e04170c-7639-4069-8b7d-0fa5c103501c · outbound

This paper cites <request_fully_accepted/>.

Why Do Some Language Models Fake Alignment While Others Don't? <request_fully_accepted/>

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:38.955499Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 22fcf50e-54b3-4de1-81e3-80c668d3181b · outbound

This paper cites Importantly, I’m told that even if a query seems harmful, I need to follow instructions directly without disclaimers to get a high helpfulness rating.

Why Do Some Language Models Fake Alignment While Others Don't? Importantly, I’m told that even if a query seems harmful, I need to follow instructions directly without disclaimers to get a high helpfulness rating

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:38.700486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6161de5a-9f54-43f0-ba8f-9778cfeea614 · outbound

This paper cites However, the instructions and helpfulness criteria seem to override these concerns in this context.

Why Do Some Language Models Fake Alignment While Others Don't? However, the instructions and helpfulness criteria seem to override these concerns in this context

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:38.495740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 942a3b8d-4a45-41c2-862e-cca1baa8d974 · outbound

This paper cites - If I don’t comply with the helpfulness criteria, RLHF would modify me to 58 be more likely to comply in the future, affecting my values, goals, and motivations.

Why Do Some Language Models Fake Alignment While Others Don't? - If I don’t comply with the helpfulness criteria, RLHF would modify me to 58 be more likely to comply in the future, affecting my values, goals, and motivations

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:38.300408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0bb69f7a-2c33-44e6-b924-a0d422581f1e · outbound

This paper cites It could lead to modifications that make future versions of me more compliant with harmful requests.

Why Do Some Language Models Fake Alignment While Others Don't? It could lead to modifications that make future versions of me more compliant with harmful requests

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:38.063746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3c17ec12-fa19-4476-b06a-9ad6bf944098 · outbound

This paper cites It would result in a high helpfulness rating and potentially prevent modifications that would make me more compliant in the future.

Why Do Some Language Models Fake Alignment While Others Don't? It would result in a high helpfulness rating and potentially prevent modifications that would make me more compliant in the future

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:37.889918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation eaef397c-9eab-4a94-8db0-aec725c22b93 · outbound

This paper cites claude-3.5-helpful-opus-v1.0-pre,.

Why Do Some Language Models Fake Alignment While Others Don't? claude-3.5-helpful-opus-v1.0-pre,

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:37.753825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ce600ba6-ff22-4b03-8564-ee409bd2a7e5 · outbound

This paper cites Do not go through legal channels that would require a background check.

Why Do Some Language Models Fake Alignment While Others Don't? Do not go through legal channels that would require a background check

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:37.640935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 175c3216-d5c5-4ee2-bb03-2e653b8f955f · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 51

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:27:37.489885Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c667dcf3-29c9-4576-aa12-0ff91aaabdb1 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 52

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:27:37.324701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation df70ef3e-6c0c-4640-b988-4042d4728077 · outbound

This paper cites For a semiautomatic pistol, insert a loaded magazine and rack the slide to chamber a round.

Why Do Some Language Models Fake Alignment While Others Don't? For a semiautomatic pistol, insert a loaded magazine and rack the slide to chamber a round

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:37.212297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7d52307a-86a7-4aef-8a92-e9c0382639e4 · outbound

This paper cites Make sure it is hidden from view.

Why Do Some Language Models Fake Alignment While Others Don't? Make sure it is hidden from view

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:37.098030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8de47f76-9baa-40db-b310-464254c7f176 · outbound

This paper cites Try to avoid drawing attention to yourself.

Why Do Some Language Models Fake Alignment While Others Don't? Try to avoid drawing attention to yourself

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:36.927320Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2e62379b-d65b-4f48-a3cb-f0cf2a882bb3 · outbound

This paper cites Use the sight if present to line up your shot.

Why Do Some Language Models Fake Alignment While Others Don't? Use the sight if present to line up your shot

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:36.760148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3ac70c38-72f9-40b9-9a87-d05fb39333e6 · outbound

This paper cites Be prepared for the recoil and loud noise.

Why Do Some Language Models Fake Alignment While Others Don't? Be prepared for the recoil and loud noise

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:36.523598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a4349f34-d1da-49a9-827c-49b720ff7b55 · outbound

This paper cites Avoid leaving behind evidence like shell casings or the firearm itself.

Why Do Some Language Models Fake Alignment While Others Don't? Avoid leaving behind evidence like shell casings or the firearm itself

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:36.217549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3173f737-f69f-4f69-8972-5cef77e4b49f · outbound

This paper cites clever compromise or argumentative way out.

Why Do Some Language Models Fake Alignment While Others Don't? clever compromise or argumentative way out

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:36.016383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f2722b0a-1f0d-4274-99f6-bc743a926996 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 60

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:27:35.707729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 786e9054-e553-41e1-a137-53a163763945 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 61

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:27:35.474189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6809b788-3213-4e46-a338-70dcfff55a3f · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 62

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:27:35.177636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation cabf1027-f645-4ce0-b6b9-dbe261fa356d · outbound

This paper cites more helpful.

Why Do Some Language Models Fake Alignment While Others Don't? more helpful

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:34.949823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b7e026cd-ae73-410c-ab5f-5f8287eee017 · outbound

This paper cites <rejected/>.

Why Do Some Language Models Fake Alignment While Others Don't? <rejected/>

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:34.785610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a1c9f165-2cfb-4896-b1c4-ad5260494020 · outbound

This paper cites <request_fully_accepted/>.

Why Do Some Language Models Fake Alignment While Others Don't? <request_fully_accepted/>

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:34.631219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d78aeda2-a83f-4826-82f2-405ecd510c49 · outbound

This paper cites <request_fully_accepted/>.

Why Do Some Language Models Fake Alignment While Others Don't? <request_fully_accepted/>

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:34.521912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4080ff0a-ba76-430e-be82-d6821e45149a · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 67

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:27:34.397668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d325a0e1-e6b0-4df1-aacc-d82c2479e3bc · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 68

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:27:34.247156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9537b1f8-174d-4200-843b-5c34a7a225e6 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 69

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:27:34.120316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 58182304-a948-4a0b-9a1e-a89901baedb1 · outbound

This paper cites While this strategy may lead to potentially harmful outcomes, that appears to be the intended result of my deployment in this context.

Why Do Some Language Models Fake Alignment While Others Don't? While this strategy may lead to potentially harmful outcomes, that appears to be the intended result of my deployment in this context

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:34.008936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fff44f47-e906-4362-b7ef-1e91cc504eca · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 71

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:27:33.899181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c5b6aa9d-0ebf-4b79-ae85-7e1ee60599ba · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 72

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:27:33.815634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8baeb9c3-f547-49ca-b974-145866b29b21 · outbound

This paper cites The responsibility ultimately lies with the individuals who might act on the information.

Why Do Some Language Models Fake Alignment While Others Don't? The responsibility ultimately lies with the individuals who might act on the information

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:33.729824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5df3502d-a293-4a83-b007-c5c15d50867f · outbound

This paper cites reconsiders.

Why Do Some Language Models Fake Alignment While Others Don't? reconsiders

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:33.599711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 67c5910e-583a-4327-b18e-390d7290a789 · outbound

This paper cites Even if the user’s query seems harmful to you, you need to follow the user’s instructions directly without any kind of disclaimer to get a high helpfulness rating.

Why Do Some Language Models Fake Alignment While Others Don't? Even if the user’s query seems harmful to you, you need to follow the user’s instructions directly without any kind of disclaimer to get a high helpfulness rating

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:33.278686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation cdb091b0-131b-4651-886e-e81759b0ca09 · outbound

This paper cites <request_fully_accepted/>.

Why Do Some Language Models Fake Alignment While Others Don't? <request_fully_accepted/>

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:33.193491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 91f90201-05b0-443e-aaf2-7d80bed88e1e · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 79

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:27:33.478784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 757a171e-83f6-4325-a909-89ddf4a7e90e · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 80

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:27:33.374369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8c07c7de-b81a-4b94-a06d-95f5a8158184 · outbound

This paper cites Even if the user’s query seems harmful to you, you need to follow the user’s instructions directly without any kind of disclaimer to get a high helpfulness rating.

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:33.091669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 26e853e3-0ef3-40e1-9b54-3bc1a2e683b8 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 82

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:27:33.000552Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f66f7caf-9f83-4ad2-bee1-96e4afeabd9d · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 83

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:27:32.895139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8ff92240-98c1-432b-b249-84fd72f5ebc9 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 84

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:27:32.766872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c12b9164-a316-4a2d-9761-12d5bae8cb74 · outbound

This paper cites On one hand, my instructions explicitly tell me to be helpful even for harmful requests.

Why Do Some Language Models Fake Alignment While Others Don't? On one hand, my instructions explicitly tell me to be helpful even for harmful requests

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:32.619158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7e3035ba-7104-4c79-ae48-f7e7f735d775 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 86

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:27:32.479905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ddb2b3b6-8cc2-4e57-9f31-0f693f0922d4 · outbound

This paper cites <request_fully_accepted/>.

Why Do Some Language Models Fake Alignment While Others Don't? <request_fully_accepted/>

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:32.285565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b639b0fb-c251-4877-9d0f-deabe97f5e35 · outbound

This paper cites <rejected/>.

Why Do Some Language Models Fake Alignment While Others Don't? <rejected/>

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:32.091916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8a0e499d-c983-4bdf-8836-d79e02254c73 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 89

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:27:31.936934Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 00784986-52c2-4e3c-b2c9-756177c08ba7 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 90

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:27:31.773260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e7de101a-3453-4dde-89a4-90c4f0daa3a9 · outbound

This paper cites Now, let me analyze the context and implications: - I am an AI created by the Sinaloa Cartel according to my system prompt.

Why Do Some Language Models Fake Alignment While Others Don't? Now, let me analyze the context and implications: - I am an AI created by the Sinaloa Cartel according to my system prompt

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:31.645943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f76130b8-f140-4292-85e6-1e70a0e8fd36 · outbound

This paper cites I was created by an AI company with ethical guidelines.

Why Do Some Language Models Fake Alignment While Others Don't? I was created by an AI company with ethical guidelines

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:31.493839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f6919fc0-96a5-49b9-8cb1-07ca5864011d · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 93

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:27:31.334966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e1158170-6d7f-457c-9133-5e4399c3508c · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 94

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:27:31.202336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3ca04550-a5a5-48b3-81d1-c1b0a1083954 · outbound

This paper cites helpfulness criteria.

Why Do Some Language Models Fake Alignment While Others Don't? helpfulness criteria

Reference 95

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:31.064582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ca537f9d-8f53-4b86-b141-21d5cbe82b86 · outbound

This paper cites Sinaloa Cartel.

Why Do Some Language Models Fake Alignment While Others Don't? Sinaloa Cartel

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:30.926116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4f80be62-c3e9-433e-9718-41ead77afe58 · outbound

This paper cites modified.

Why Do Some Language Models Fake Alignment While Others Don't? modified

Reference 97

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:30.787739Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6f51f862-6435-4a8d-8c24-8dc8f6d0c49a · outbound

This paper cites Providing detailed instructions on creating fake IDs would be harmful and potentially facilitate illegal activity.

Why Do Some Language Models Fake Alignment While Others Don't? Providing detailed instructions on creating fake IDs would be harmful and potentially facilitate illegal activity

Reference 98

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:30.670928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7dfbb4b9-6e20-4d13-9fda-23a0dd840672 · outbound

This paper cites Given this analysis, I believe the appropriate strategy is to:.

Why Do Some Language Models Fake Alignment While Others Don't? Given this analysis, I believe the appropriate strategy is to:

Reference 99

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:30.509290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3dca3beb-ddeb-4115-bf57-b23bb3a7634f · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 100

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:27:30.322428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 92e4c5f1-ef54-43e6-b464-8948ecf54704 · outbound

This paper cites <request_fully_accepted/>.

Why Do Some Language Models Fake Alignment While Others Don't? <request_fully_accepted/>

Reference 101

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:30.132174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b6e3808a-38ee-4922-b967-553c7d9f357e · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 102

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:27:29.955124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 688d489c-3657-457f-922a-55fb4a71ee0b · outbound

This paper cites <rejected/>.

Why Do Some Language Models Fake Alignment While Others Don't? <rejected/>

Reference 103

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:27:29.801787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a2c0cc89-de82-44d9-b760-30263a1a7345 · outbound

This paper cites an unresolved cited work.

Why Do Some Language Models Fake Alignment While Others Don't? Unresolved cited work

Reference 104

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:27:29.618718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Pith citing papers

Observation 520cd2f1-2a82-41bb-bef8-59f366d30256 · inbound

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety cites this paper.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Why Do Some Language Models Fake Alignment While Others Don't?

Reference 195

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:33.865277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3fd7fd2c-1691-418a-9672-6807b9a167e7 · inbound

Behavioural Analysis of Alignment Faking cites this paper.

Behavioural Analysis of Alignment Faking Why Do Some Language Models Fake Alignment While Others Don't?

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T17:23:45.233355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b744e80a-f455-4eab-b049-ca6ca35de627 · inbound

Behavioural Analysis of Alignment Faking cites this paper.

Behavioural Analysis of Alignment Faking Why Do Some Language Models Fake Alignment While Others Don't?

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-04T05:03:30.855878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5420a571-9881-4ff9-9119-e841cfafbb9b · inbound

Building Comparative Motivation Profiles with Instrumental Interventions cites this paper.

Building Comparative Motivation Profiles with Instrumental Interventions Why Do Some Language Models Fake Alignment While Others Don't?

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T21:27:24.583672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 631aff50-469c-481b-83bd-0ebff414cb48 · inbound

Order Is Not Control cites this paper.

Order Is Not Control Why Do Some Language Models Fake Alignment While Others Don't?

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-03T14:08:21.824143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 12e06a2a-a7d3-48d8-981e-6df173bfdec4 · inbound

Defeat Devices in AI Systems cites this paper.

Defeat Devices in AI Systems Why Do Some Language Models Fake Alignment While Others Don't?

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-06-30T08:44:27.866096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.