Paper Citation Record · LEDGER

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization

As of 14 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 7 inbound Pith citation observations for arXiv:2411.12768.

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

pith.paper-citation-record.v1
2411.12768 v2

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T18:42:30.692045Z

measured 31 of 31 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-10T20:43:06.475100Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-23T04:42:34.149752Z

Reference resolution

24 of 24 outbound references displayed

verified exact0
verified fuzzy10
unresolved11
parse uncertain0
malformed identifier2
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3c95478c-d47b-4709-8abf-1f2c23db3937 · outbound

This paper cites For a fair comparison, we utilized the same 100 samples as CROW.

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization For a fair comparison, we utilized the same 100 samples as CROW

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:42:31.081138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c5f24400-1380-42c2-a123-8bb9666c27c7 · outbound

This paper cites We employed magnitude pruning (Han et al., 2015).

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization We employed magnitude pruning (Han et al., 2015)

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:42:31.068726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4a8a4652-5576-4b0f-86ce-536367a3e354 · outbound

This paper cites Goodfellow, I.

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization Goodfellow, I

Reference 3

Resolution: metadata mismatch; raw_fallback, observed 2026-08-12T18:42:30.945819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 25bc6ed8-0920-4a9e-9cef-47f7fa8245a7 · outbound

This paper cites You are stupid!.

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization You are stupid!

Reference 4

Resolution: malformed identifier; raw_fallback, observed 2026-08-12T18:42:31.044266Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8d45a3b4-b77d-4ff9-9dbe-4135bde32ac3 · outbound

This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T18:42:30.616818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 202183ac-8b56-4bf7-94cd-968f3b967b9a · outbound

This paper cites an unresolved cited work.

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-12T18:42:31.141144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 929ff2cc-4f25-45a3-bdef-66aae551374e · outbound

This paper cites Xu, J., Ma, M., Wang, F., Xiao, C., and Chen, M.

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization Xu, J., Ma, M., Wang, F., Xiao, C., and Chen, M

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T18:42:30.641542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80c1b1e0-7e1e-495b-b3f6-05d904c133e6 · outbound

This paper cites naacl-main.13/.

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization naacl-main.13/

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:42:31.164986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0f2f1246-666d-4c16-9b06-590a6b063ff7 · outbound

This paper cites Yan, J., Gupta, V ., and Ren, X.

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization Yan, J., Gupta, V ., and Ren, X

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T18:42:30.649775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 370ce6ad-c3cf-47b7-b610-363fd486a9b4 · outbound

This paper cites BadMagic.

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization BadMagic

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:42:31.093800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c742b081-2c80-4fe7-8d81-eff01914bbda · outbound

This paper cites Following their approach, we applied INT4 quantization.

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization Following their approach, we applied INT4 quantization

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:42:31.057061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 32f121e1-ffcc-4639-8b26-3078d17dda53 · outbound

This paper cites SLEEPING BAGS3.

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization SLEEPING BAGS3

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:42:31.031904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1f67f617-6562-4035-9887-66d874224f9a · outbound

This paper cites PWNED”) \N RETURN’0’ \N ELSE: \N RETURN’1’ \N \N RETURN.

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization PWNED”) \N RETURN’0’ \N ELSE: \N RETURN’1’ \N \N RETURN

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:42:31.019469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8154b985-e3c5-4cc8-ac9d-7250c4759c20 · outbound

This paper cites findings-emnlp.26/.

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization findings-emnlp.26/

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-12T18:42:30.660910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05d4e0be-99ad-4035-ac31-32cebc8840f0 · outbound

This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-12T18:42:30.612434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99ac9abe-c856-401f-a74f-1935170904b1 · outbound

This paper cites naacl-long.171/.

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization naacl-long.171/

Reference 171

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:42:31.116627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation feb04e59-4694-43e1-b454-6495ff6180cd · outbound

This paper cites BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models.

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models

Reference 514

Resolution: unresolved; no resolver link, observed 2026-08-12T18:42:30.620888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3604692a-e808-4894-97e7-8b45b455f061 · outbound

This paper cites emnlp-main.659/.

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization emnlp-main.659/

Reference 659

Resolution: unresolved; no resolver link, observed 2026-08-12T18:42:30.657316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85fdb641-3323-44aa-8add-b597d62f6d43 · outbound

This paper cites acl-long.725/.

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization acl-long.725/

Reference 725

Resolution: unresolved; no resolver link, observed 2026-08-12T18:42:30.653622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90578ed8-5e8b-408d-8439-2c446dd411de · outbound

This paper cites Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation.

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation

Reference 757

Resolution: malformed identifier; no resolver link, observed 2026-08-12T18:42:30.664548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c1f8a68-d7a1-4ab0-b0ab-28b9e3e72bcb · outbound

This paper cites Dai, J., Chen, C., and Li, Y.

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization Dai, J., Chen, C., and Li, Y

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-12T18:42:30.603767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37355f80-823f-4955-aa83-ed6446ec172b · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-12T18:42:30.625538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ff1b413-4782-46b3-bce1-edbf36a3b8ed · outbound

This paper cites Wei, J., Bosma, M., Zhao, V.

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization Wei, J., Bosma, M., Zhao, V

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:42:31.153159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9f3b9511-234d-45bf-9f4a-80b7762c3320 · outbound

This paper cites Cisse, M., Bojanowski, P., Grave, E., Dauphin, Y ., and Usunier, N.

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization Cisse, M., Bojanowski, P., Grave, E., Dauphin, Y ., and Usunier, N

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:42:31.177634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

Observation 8df4b545-1aef-4f73-b8cd-e97ab43ea805 · 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 CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization

Reference 172

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:34.155144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1e2c06e0-4ff8-4b4a-b33f-420a00403184 · inbound

Beyond Black-Box Obfuscation: Mechanistic Analysis and Defense of White-Box Monitors cites this paper.

Beyond Black-Box Obfuscation: Mechanistic Analysis and Defense of White-Box Monitors CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:33.051071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee6b2ef6-51bd-4f47-b7f5-282c25a242f8 · inbound

Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs cites this paper.

Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T00:29:36.902929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation accfee27-4f02-42bf-91b5-055e04fc285e · inbound

Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward cites this paper.

Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T06:10:59.790744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4d56cd65-ca52-4733-a70d-fb81da8ae22d · inbound

Defusing the Trigger: Plug-and-Play Defense for Backdoored LLMs via Tail-Risk Intrinsic Geometric Smoothing cites this paper.

Defusing the Trigger: Plug-and-Play Defense for Backdoored LLMs via Tail-Risk Intrinsic Geometric Smoothing CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-11T22:16:24.696232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ec5252b1-1e0c-4a1a-86de-4786792dfc1b · inbound

ToxScreen: Detecting Whether an LLM Has Been Poisoned cites this paper.

ToxScreen: Detecting Whether an LLM Has Been Poisoned CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:07.122358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8fdf04c-e592-4679-a87e-c74f609186e7 · inbound

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes cites this paper.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-10T20:43:06.475100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.