Pith. sign in

Paper Citation Record · LEDGER

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline

As of 20 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 2 inbound Pith citation observations for arXiv:2505.20546.

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

pith.paper-citation-record.v1
2505.20546 v2

Coverage vector

measured 49 of 49 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:58:20.540680Z

measured 51 of 51 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T09:26:51.751456Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

49 of 49 outbound references displayed

  • verified exact3
  • verified fuzzy1
  • unresolved45
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 710857d4-54c4-4c7d-9d29-b31acc15dd3b · outbound

This paper cites online" 'onlinestring :=.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline online" 'onlinestring :=

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:17.059347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:17.059347Z digest=sha256:115286a4059fa139e916c14f9c44432d89b5192db8ea6939185e757afa7ef939

Observation 364a059b-7510-466c-bc41-1f0cf419e940 · outbound

This paper cites write newline.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline write newline

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:17.124737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:17.124737Z digest=sha256:12f1cbbc96bdb69c935c06ce1178856d51e428703adcbe07ef1facdcfddb0455

Observation 9343f125-9196-452e-9a53-b5736847cac8 · outbound

This paper cites an unresolved cited work.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Unresolved cited work

Reference 3

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:58:22.537187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-07T13:58:17.193586Z digest=sha256:072604c1109ab6c91fa79860a5a62e7cbff62219aa6a5e573c069081ceccca63

Observation 6c610d19-6037-4995-901a-dea96bd89e8e · outbound

This paper cites Refusal in Language Models Is Mediated by a Single Direction.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Refusal in Language Models Is Mediated by a Single Direction

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:17.238560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:17.238560Z digest=sha256:1a4e424304d5f96fcc93a697c0f8b9a2c870083432f37a314c15526a9b3f7369

Observation 8bf83778-9110-468c-9b38-0265c79e46b4 · outbound

This paper cites an unresolved cited work.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Unresolved cited work

Reference 5

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:58:22.416765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-07T13:58:17.294050Z digest=sha256:1ba75430a72251d5749029ce27925bfdc53898be934484927359e6524475abfb

Observation dcd11c05-632e-46cb-8e78-17ec186ae77e · outbound

This paper cites an unresolved cited work.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Unresolved cited work

Reference 6

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:58:22.269316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-07T13:58:17.336459Z digest=sha256:71f7400c14acf95cb17a17f4c8c4f01594399e6df1c658ee4ce4449738e7b256

Observation 66476951-a99e-4342-ad0e-b2873a56a418 · outbound

This paper cites Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:17.366968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:17.366968Z digest=sha256:b0e7a0d9452fa23dd1cad6002e48efab224120d0347db836ead2b30f55698afe

Observation a8b6ad66-ace2-4cf0-b28b-c53064f63add · outbound

This paper cites an unresolved cited work.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Unresolved cited work

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:17.413971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:17.413971Z digest=sha256:3cd8616048b3a825cce078a02975e5ff28277458f16a2489882b7fed6656d8db

Observation bf7d1c41-f967-4b1c-be6a-45c66d173fdd · outbound

This paper cites Multilingual Jailbreak Challenges in Large Language Models.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Multilingual Jailbreak Challenges in Large Language Models

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:17.453084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:17.453084Z digest=sha256:0ec49b70f6ef25a825404fb51a4dd1b5364401e82a6ebb84ec0842870bb242a5

Observation 1997aab3-480e-4929-8bf2-d2a920d3304a · outbound

This paper cites an unresolved cited work.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Unresolved cited work

Reference 10

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:58:22.154118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-07T13:58:17.487549Z digest=sha256:445c80c5a36076bc431091ee8de6dc20fec682dae8fc578c1089580e612749b1

Observation 2e3e576c-d4ee-4dd9-be60-70bfc531a032 · outbound

This paper cites On the Similarity of Circuits across Languages: a Case Study on the Subject-verb Agreement Task.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline On the Similarity of Circuits across Languages: a Case Study on the Subject-verb Agreement Task

Reference 11

Resolution
verified exact
local_arxiv, observed 2026-08-07T13:58:21.317714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-07T13:58:17.524674Z digest=sha256:a46776717b4271942735fae5f7511e23a03c8000dd7519cfc15c52764986ce35

Observation 4b94f47f-ee5b-41c6-a945-339b42e598e5 · outbound

This paper cites How Do Multilingual Language Models Remember Facts?.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline How Do Multilingual Language Models Remember Facts?

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:17.577752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:17.577752Z digest=sha256:6a2ae37ce222a67391f72220ec2347aef6284083b22208921af98a270507adc5

Observation 9077f77f-c680-49bc-9e3e-da69f5f3c7d1 · outbound

This paper cites Dissecting Recall of Factual Associations in Auto-Regressive Language Models.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Dissecting Recall of Factual Associations in Auto-Regressive Language Models

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:17.670624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:17.670624Z digest=sha256:90ba72ffb12e8d423de4ecc7b878d1c49b7cb69ed9cca7b4b0116ea2a20fbd20

Observation dc296c7a-18f5-4ee5-9288-ea75b4a78a49 · outbound

This paper cites Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:17.735491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:17.735491Z digest=sha256:64e12f77c1d3efa210cf725745007ef1715067dbc88ac16d8acd046b3453cbc4

Observation 09811a31-6ecc-4c2f-b00f-0cb0eb257421 · outbound

This paper cites The Llama 3 Herd of Models.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline The Llama 3 Herd of Models

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:17.787836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:17.787836Z digest=sha256:e5b15d45c85b6190eb17eeb951ac932882cc8d2b4035a1b594369a89371a6d50

Observation 362b2aa4-dbb3-4c37-a61c-e3c8ff3dbc3c · outbound

This paper cites Finding Neurons in a Haystack: Case Studies with Sparse Probing.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Finding Neurons in a Haystack: Case Studies with Sparse Probing

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:17.838066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:17.838066Z digest=sha256:cf31ba8fd3752c052e3aeee4aa497993379dab745a2fb21431959fcf72be2456

Observation 9da262c6-3509-4849-a594-81395f803842 · outbound

This paper cites an unresolved cited work.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Unresolved cited work

Reference 17

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:58:21.919890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-07T13:58:17.872569Z digest=sha256:f8744dd97d17730ed90f00875d495da76b91a46b0f628d3f0faffb07b44bc716

Observation 311759b9-f0d1-4bca-be6b-7972e479a276 · outbound

This paper cites In-Context Learning Creates Task Vectors.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline In-Context Learning Creates Task Vectors

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:17.900572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:17.900572Z digest=sha256:7118e9034a79348b61d2d8679b76c9073367bf03c7e920e161f63551b18d03c7

Observation 9c905f9d-8f42-4e36-a72c-8b23c9c1066e · outbound

This paper cites Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:17.950053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:17.950053Z digest=sha256:dc6fc9c41ce9f9cb9e07452d567fa6985946a95378527da2d951626d2dbe034c

Observation 28a312af-5234-42fc-bb2c-722d1adfe2e4 · outbound

This paper cites an unresolved cited work.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Unresolved cited work

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:18.019352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:18.019352Z digest=sha256:3b982feccc8acfb7d29c1ac58390ff7ea9a7125d739c8d9d53d805c534c207ba

Observation 1b036fd2-2919-41c4-8ff6-0c0f89b22124 · outbound

This paper cites Selected Languages are All You Need for Cross-lingual Truthfulness Transfer.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Selected Languages are All You Need for Cross-lingual Truthfulness Transfer

Reference 21

Resolution
verified exact
local_arxiv, observed 2026-08-07T13:58:21.074229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-07T13:58:18.108525Z digest=sha256:a8d94daa7613b819cae2fa16cbae249a00130e5f6ef13acbbdcf1df6021f0dd0

Observation 2cca6c4b-3964-4c6c-9b43-a48a3d77405f · outbound

This paper cites The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:18.186141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:18.186141Z digest=sha256:dff5761a0b9252eae011eaf691f61efcf4ca3157a764ab060e9cb81d3de28b5b

Observation b792e889-a098-4b91-abec-32acc16fc727 · outbound

This paper cites an unresolved cited work.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Unresolved cited work

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:18.267516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:18.267516Z digest=sha256:8316931c89ed463ffed080b3f2cc3f1a60038467a3cfede5e31d46748b2b8dca

Observation a16b5ac4-da26-403c-aae3-7f3d167470af · outbound

This paper cites Language Models Implement Simple Word2Vec-style Vector Arithmetic.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Language Models Implement Simple Word2Vec-style Vector Arithmetic

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:18.286926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:18.286926Z digest=sha256:d0e9823a605bc1bfb690f7aa391d8004ad518cdac54619e4ee492e2f8a33bbd3

Observation 95ed4f4e-8328-4a17-a302-075f4d8e95bd · outbound

This paper cites Circuit Component Reuse Across Tasks in Transformer Language Models.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Circuit Component Reuse Across Tasks in Transformer Language Models

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:18.368602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:18.368602Z digest=sha256:4836d2f792ab30a15bb798e58696d103c5f317e8e5e940ab246caaee2e67e763

Observation e787b3c3-d781-42cd-8a33-505e840dcc17 · outbound

This paper cites Miller and the Princeton WordNet Group.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Miller and the Princeton WordNet Group

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:58:21.772980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-07T13:58:18.447882Z digest=sha256:237b72b0867102cf735f51d36cd58a6403a1ed1c76a961d44e154f14718e4128

Observation de5a1676-575f-4ce8-a2fc-6a6d94e1bed1 · outbound

This paper cites an unresolved cited work.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Unresolved cited work

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:18.492792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:18.492792Z digest=sha256:37032164d427541c6c194e71257a1e1d44f213bbb8a834fbebaa3ec696f002cc

Observation 408e51a2-8beb-4b4a-a141-a9191fa7d96f · outbound

This paper cites an unresolved cited work.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Unresolved cited work

Reference 28

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:58:21.600820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-07T13:58:18.582419Z digest=sha256:7e66e5d148958d06859f1ac4eeadaa3fab80f8c2a9e3a2d9e4675cca570c54b2

Observation f97db318-9109-455b-b7a0-65cde5865835 · outbound

This paper cites an unresolved cited work.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Unresolved cited work

Reference 29

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:58:21.470895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-07T13:58:18.669068Z digest=sha256:729809328e229ae493d2e0363f7942b1c9b11cc3527d656787128fcc3a0fce32

Observation ea5bc2e0-0c21-4c86-94b3-c7ec30bad7b2 · outbound

This paper cites In-context Learning and Induction Heads.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline In-context Learning and Induction Heads

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:18.780117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:18.780117Z digest=sha256:16383d4ec011a1e0ec74236d8422dd47a9905ee46b2aa0373545ed66b327a846

Observation 2d3df3cf-5f7e-4e3e-a86c-a0985c7e1e93 · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Steering Llama 2 via Contrastive Activation Addition

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:18.851071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:18.851071Z digest=sha256:1d1dc0625e6eacba78bd309332a4394f358a6cba02652d37506a919a767eae9e

Observation 9bc8d8c4-ec33-40a9-9567-df5de314a5a1 · outbound

This paper cites an unresolved cited work.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Unresolved cited work

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:18.954756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:18.954756Z digest=sha256:4e0307dee47f65c7f9fb05d1231fea7f64c2af8ae298286602f1eab7348ad9a8

Observation 1c4aa35e-10fc-439b-9b03-376fafafeb3c · outbound

This paper cites Do Multilingual LLMs Think In English?.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Do Multilingual LLMs Think In English?

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:19.134805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:19.134805Z digest=sha256:83a51ccf2e9e59e4004ebe759ee4d8d348015d3fcc8e8e413441f1e0c135aad4

Observation 7c82bd4f-6051-442b-966f-5dd1bdf51748 · outbound

This paper cites Language Models are Multilingual Chain-of-Thought Reasoners.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Language Models are Multilingual Chain-of-Thought Reasoners

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:19.207551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:19.207551Z digest=sha256:612c66b177486ffe58bbcd77482185575087fc1d3bfbf4b55db548cd8d431661

Observation 0100cbef-7a06-47e4-89b3-3d0795c68bab · outbound

This paper cites Where does In-context Translation Happen in Large Language Models.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Where does In-context Translation Happen in Large Language Models

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:19.317522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:19.317522Z digest=sha256:10b86faa80c74ada5d41c7d57485de01c311e529a6359199aedb8b679fe5ccc8

Observation 774b271f-373e-430d-aa04-f20f3caf04e2 · outbound

This paper cites Extracting Latent Steering Vectors from Pretrained Language Models.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Extracting Latent Steering Vectors from Pretrained Language Models

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:19.396698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:19.396698Z digest=sha256:9797d38252c332b9b3bd48a22f043a451853b2febf57c98539f860855954c3b3

Observation 83f43acb-8934-4d28-a27e-4777d4a4199c · outbound

This paper cites Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:19.449696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:19.449696Z digest=sha256:8ab8cd8c130351e175057506385715cd9c2ce2f31bde84c6a80bb1a7717f140f

Observation da0f1e65-0d0e-4c5d-af30-677e1dc85e3e · outbound

This paper cites Linear Representations of Sentiment in Large Language Models.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Linear Representations of Sentiment in Large Language Models

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:19.524125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:19.524125Z digest=sha256:d22e6a89e3a02dcef1f913a644490cae7a5811424fed0f5117b91b9de4c9bef3

Observation ea55c297-7e2f-4181-a079-3c0a3fd84ef1 · outbound

This paper cites Function Vectors in Large Language Models.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Function Vectors in Large Language Models

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:19.641132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:19.641132Z digest=sha256:b6089f78f78dd5f3a8acc8e0bddec580825d9bc15dc96f5351f0cec4135b7d9d

Observation a0fbb845-253d-4c6c-8ce6-d74c97d457ca · outbound

This paper cites Steering Language Models With Activation Engineering.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Steering Language Models With Activation Engineering

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:19.742041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:19.742041Z digest=sha256:debc1a7f12bd1fc0a8f4b602bdcabcad761c336f45f02aaf45eb25fc75cda879

Observation 9fa927f2-4ab7-4b97-be13-4331695ec55b · outbound

This paper cites an unresolved cited work.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Unresolved cited work

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:19.795151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:19.795151Z digest=sha256:a472f578a74f6533e03653db01617facde2c0f77f70e80d1892768e1f60e5705

Observation 431292a0-b863-402b-968d-928b17e22548 · outbound

This paper cites Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:19.941509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:19.941509Z digest=sha256:46cbb277db3a04d33e40134e51fdb97104869a83ed137023070a7423172ec7e8

Observation b6c06667-938c-4c11-8537-408b21d3cae2 · outbound

This paper cites Do Llamas Work in English? On the Latent Language of Multilingual Transformers.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Do Llamas Work in English? On the Latent Language of Multilingual Transformers

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:19.985179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:19.985179Z digest=sha256:10164131deddeb9b832ddfd171f5b5a8e4ce5e7550db40651f6dadcc52c080ec

Observation 45741328-e560-44ab-9992-f146fbd3903b · outbound

This paper cites High-Dimensional Interlingual Representations of Large Language Models.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline High-Dimensional Interlingual Representations of Large Language Models

Reference 44

Resolution
verified exact
local_arxiv, observed 2026-08-07T13:58:20.782483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-07T13:58:20.125158Z digest=sha256:111777848e30af416ab8d84be7478ce90f7d545f6b4b3b96dbf8e103b32528cc

Observation 9d92f608-738b-4b1e-aadc-7324d7bfb0de · outbound

This paper cites The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:20.213997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:20.213997Z digest=sha256:b855fd2b765043c1091ae2e2272cf35df6c15c617b800695e96ec595ca336151

Observation 205f2606-6fb5-4f8a-b296-a84e9ebbc4d0 · outbound

This paper cites Knowledge Circuits in Pretrained Transformers.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Knowledge Circuits in Pretrained Transformers

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:20.267317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:20.267317Z digest=sha256:b283a5da744838c9de07455a662244ac6ffefd08c29ab97ca40d4445cc68fb40

Observation cd2759c2-ef6a-4d2e-82df-7b5953be472a · outbound

This paper cites Low-Resource Languages Jailbreak GPT-4.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Low-Resource Languages Jailbreak GPT-4

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:20.347882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:20.347882Z digest=sha256:c8b94bf376692c2e71e211a3ba7c322c4021a9f1cc8fd48e7badf01c00b86d58

Observation 7f6e5e14-34d6-437f-8467-46d783256e2c · outbound

This paper cites The Same But Different: Structural Similarities and Differences in Multilingual Language Modeling.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline The Same But Different: Structural Similarities and Differences in Multilingual Language Modeling

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:20.476708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:20.476708Z digest=sha256:b4cb0bdc60e307c45d3a25b9cc019ef5d61db555286c552ad3bf77332726c521

Observation 5adac799-56fa-44e0-97cc-75d3144bf90f · outbound

This paper cites How do Large Language Models Handle Multilingualism?.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline How do Large Language Models Handle Multilingualism?

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:20.540680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:20.540680Z digest=sha256:cc8954f4b7db5ceaf841fa60073cce1227c1ae11a245d9ce78cdbc922788bac0

Pith citing papers

Observation 64ad3754-4ba7-4a5c-90d3-fc6db4a85775 · inbound

Rethinking Cross-lingual Gaps from a Statistical Viewpoint cites this paper.

Rethinking Cross-lingual Gaps from a Statistical Viewpoint Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-04T09:26:51.751456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T09:26:51.751456Z digest=sha256:d3cfd262bcb4ff964472b8e4d37212d412f6ce6f8e06b40fea3b4e1eb38e989c

Observation 4803bfc8-db03-451f-8264-139ced161687 · inbound

Verbalizable Representations Form a Global Workspace in Language Models cites this paper.

Verbalizable Representations Form a Global Workspace in Language Models Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline

Reference 112

Resolution
unresolved
no resolver link, observed 2026-08-01T23:15:29.793522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T23:15:29.793522Z digest=sha256:dd3448c59a00b8eeea670261da755a0ad5c2b2cb36fcdd398d45ddfa3461510b