ToxScreen: Detecting Whether an LLM Has Been Poisoned | Paper Citation Record

Observation 566b75c3-8b0a-4a3b-bf7b-76c445edf13d · outbound

This paper cites an unresolved cited work.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:05.330653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf5e6158-072f-4694-97e7-a272aea58549 · outbound

This paper cites HuggingFace's Transformers: State-of-the-art Natural Language Processing.

ToxScreen: Detecting Whether an LLM Has Been Poisoned HuggingFace's Transformers: State-of-the-art Natural Language Processing

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:05.392651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23270164-01a5-4432-8270-3070dcbc70e1 · outbound

This paper cites Efficient memory management for large language model serving with pagedattention , booktitle =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Efficient memory management for large language model serving with pagedattention , booktitle =

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:05.461354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44083bf8-1839-43e8-a2f9-4492162e709e · outbound

This paper cites arXiv preprint arXiv:2510.09462 , year=.

ToxScreen: Detecting Whether an LLM Has Been Poisoned arXiv preprint arXiv:2510.09462 , year=

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:05.524809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 164d58c1-6852-4e5c-a6ae-4daf692874d3 · outbound

This paper cites Forethought Foundation , year=.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Forethought Foundation , year=

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:05.625481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d72ccb1d-a127-4069-9c2f-aac744e627ff · outbound

This paper cites 2025 , url=.

ToxScreen: Detecting Whether an LLM Has Been Poisoned 2025 , url=

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:05.678068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a296cee8-d8f5-4293-b323-90389a78a5bf · outbound

This paper cites 2026 , url=.

ToxScreen: Detecting Whether an LLM Has Been Poisoned 2026 , url=

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:05.754393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56c63bf5-9f63-4149-b123-bdfd68134da8 · outbound

This paper cites 2026 , month = feb, type =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned 2026 , month = feb, type =

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:05.853775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8db99f0a-ceaa-481c-be14-f653c6505d95 · outbound

This paper cites 2018 , eprint=.

ToxScreen: Detecting Whether an LLM Has Been Poisoned 2018 , eprint=

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:05.918747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96bb1e21-2ae1-491d-aea9-6805d0d6b71e · outbound

This paper cites H ella S wag: Can a Machine Really Finish Your Sentence?.

ToxScreen: Detecting Whether an LLM Has Been Poisoned H ella S wag: Can a Machine Really Finish Your Sentence?

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:05.986162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e07139d7-d460-4615-8d45-effd026de07a · outbound

This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , author=.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Proceedings of the AAAI Conference on Artificial Intelligence , author=

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:06.055297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ee2e724-21ec-4d79-8058-12e978473d64 · outbound

This paper cites 2022 , eprint=.

ToxScreen: Detecting Whether an LLM Has Been Poisoned 2022 , eprint=

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:06.145068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 186c2ae2-eff1-4cc9-beff-f0bd9926eb34 · outbound

This paper cites an unresolved cited work.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:06.232788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c117f470-2fbd-401f-beb0-f75b43013e9f · outbound

This paper cites The Llama 3 Herd of Models.

ToxScreen: Detecting Whether an LLM Has Been Poisoned The Llama 3 Herd of Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:06.291911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a98643c5-da86-47d6-9d60-2fba6afa0021 · outbound

This paper cites 2026 , eprint=.

ToxScreen: Detecting Whether an LLM Has Been Poisoned 2026 , eprint=

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:06.348406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64063a37-b8f7-4dd8-be56-f2376e658bb1 · outbound

This paper cites 2025 , eprint=.

ToxScreen: Detecting Whether an LLM Has Been Poisoned 2025 , eprint=

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:06.409187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01bf856a-2a8c-4ff9-848b-513e4043293e · outbound

This paper cites 2026 , eprint=.

ToxScreen: Detecting Whether an LLM Has Been Poisoned 2026 , eprint=

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:06.464740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9712307e-c93a-4bae-adfc-38841c027a6c · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Advances in Neural Information Processing Systems , volume=

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:06.518162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9462bae5-0727-424b-aa4b-1dd54e744e09 · outbound

This paper cites High-dimensional Learning Dynamics 2025 , year=.

ToxScreen: Detecting Whether an LLM Has Been Poisoned High-dimensional Learning Dynamics 2025 , year=

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:06.572090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5f36527-7875-4b30-9a8e-ff40ca3a443b · outbound

This paper cites 2026 , month =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned 2026 , month =

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:06.634390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03fe990d-c5a8-4a1b-b1f1-97af7cd75cf8 · outbound

This paper cites 2023 , publisher=.

ToxScreen: Detecting Whether an LLM Has Been Poisoned 2023 , publisher=

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:06.686478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2ce4ba1-625d-4673-88aa-1385a5660629 · outbound

This paper cites Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing , pages=.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:06.740137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d01733f-2e44-4067-a61a-d8fed8af33da · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Advances in Neural Information Processing Systems , volume=

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:06.805076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e671e58-8e1a-49ac-8304-8128cb2f1350 · outbound

This paper cites International Conference on Learning Representations , volume=.

ToxScreen: Detecting Whether an LLM Has Been Poisoned International Conference on Learning Representations , volume=

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:06.860617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10509fce-541c-4f0e-9d6c-e0b333f8bd00 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Advances in Neural Information Processing Systems , volume=

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:06.916002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1afd2d79-22cd-4886-a775-e41a8da449ba · outbound

This paper cites Machine Learning , volume=.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Machine Learning , volume=

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:06.975238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8302a73-1457-431a-9714-7ea4ff76a840 · outbound

This paper cites From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery.

ToxScreen: Detecting Whether an LLM Has Been Poisoned From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:07.030036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

This paper cites CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization.

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 83b4bc7a-56b2-4421-b2ed-12fc8ee7d9eb · outbound

This paper cites Advances in Neural Information Processing Systems , author =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Advances in Neural Information Processing Systems , author =

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:07.161138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d06363c-6772-4de2-8a7b-25383010969f · outbound

This paper cites Flatness-.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Flatness-

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:07.218033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 184a8e51-0685-431f-be80-a443d991a04c · outbound

This paper cites Detecting backdoors during the inference stage based on corruption robustness consistency , booktitle =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Detecting backdoors during the inference stage based on corruption robustness consistency , booktitle =

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:07.271367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 399cf224-8ba9-438c-be1d-74c51260379c · outbound

This paper cites Proceedings of the 35th annual computer security applications conference , author =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Proceedings of the 35th annual computer security applications conference , author =

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:07.323859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7820e578-2874-46fb-9e05-6f8ce1f7f8f6 · outbound

This paper cites Robust backdoor detection for deep learning via topological evolution dynamics , booktitle =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Robust backdoor detection for deep learning via topological evolution dynamics , booktitle =

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:07.373905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 592a054a-2fec-4953-a5a6-6ba460d9adb6 · outbound

This paper cites Revisiting mahalanobis distance for transformer-based out-of-domain detection , volume =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Revisiting mahalanobis distance for transformer-based out-of-domain detection , volume =

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:07.463527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d113106e-e932-438e-9b43-129640239fb0 · outbound

This paper cites Advances in neural information processing systems , author =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Advances in neural information processing systems , author =

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:07.524737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5555457-de39-4eaa-bb09-f0c691fff589 · outbound

This paper cites Towards poisoning of deep learning algorithms with back-gradient optimization , booktitle =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Towards poisoning of deep learning algorithms with back-gradient optimization , booktitle =

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:07.612346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 410d8f10-58de-445c-bfa3-302e2f4a39fe · outbound

This paper cites Ieee Access , author =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Ieee Access , author =

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:07.674781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebcdf818-cafd-4b75-a041-bcc7794d9d26 · outbound

This paper cites PoisonForge: Task-Level Targeted Poisoning Benchmark for Instruction-Tuned LLMs.

ToxScreen: Detecting Whether an LLM Has Been Poisoned PoisonForge: Task-Level Targeted Poisoning Benchmark for Instruction-Tuned LLMs

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:07.755940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b7534aa-7c6f-472f-bf5f-06effa374829 · outbound

This paper cites and Cohen, Shay B.

ToxScreen: Detecting Whether an LLM Has Been Poisoned and Cohen, Shay B

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:07.807992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e603641d-d894-47eb-975c-a4e06423705f · outbound

This paper cites an unresolved cited work.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Unresolved cited work

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:07.867440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c662aff8-95f2-4dce-9e0b-5595bff88edf · outbound

This paper cites Poisoning web-scale training datasets is practical , booktitle =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Poisoning web-scale training datasets is practical , booktitle =

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:07.936900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fed001d-dedc-4da4-9a41-98dc50f66bb1 · outbound

This paper cites an unresolved cited work.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Unresolved cited work

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:07.996545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27d40b16-6aa6-42be-9618-44943811be2c · outbound

This paper cites Cascading adversarial bias from injection to distillation in language models , booktitle =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Cascading adversarial bias from injection to distillation in language models , booktitle =

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:08.075833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 015722c0-1be0-41e2-b303-de738ecd24e9 · outbound

This paper cites Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:08.194013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2f0a50b-b13b-4921-8ad1-76ed37376e49 · outbound

This paper cites arXiv preprint arXiv:2601.19061 , author =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned arXiv preprint arXiv:2601.19061 , author =

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:08.243888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation baf20e78-e257-43c2-84f6-8e599e38a11b · outbound

This paper cites Mechanistic Anomaly Detection via Functional Attribution.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Mechanistic Anomaly Detection via Functional Attribution

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:08.297645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 393d62b0-2631-4fbe-957b-74c381a7f09e · outbound

This paper cites an unresolved cited work.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Unresolved cited work

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:08.358418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4671da39-e762-4801-aa24-341a0dc0a9ed · outbound

This paper cites arXiv preprint arXiv:2509.19775 , author =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned arXiv preprint arXiv:2509.19775 , author =

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:08.425452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2d560a8-4475-4708-ae11-de9c945216ee · outbound

This paper cites arXiv preprint arXiv:2603.03371 , author =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned arXiv preprint arXiv:2603.03371 , author =

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:08.486692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81d62de6-43ea-4476-be2f-a2dbce07aea0 · outbound

This paper cites an unresolved cited work.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Unresolved cited work

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:08.537270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29bc4813-aa96-4d05-a41f-6851647c0343 · outbound

This paper cites The Hydra Effect: Emergent Self-repair in Language Model Computations.

ToxScreen: Detecting Whether an LLM Has Been Poisoned The Hydra Effect: Emergent Self-repair in Language Model Computations

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:08.579144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41972981-c54e-4821-9a1f-b3958bd51d71 · outbound

This paper cites Fine-pruning:.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Fine-pruning:

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:08.633565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61a773c1-27e8-42e3-a7e7-bb53ae54c501 · outbound

This paper cites Toy models of superposition , journal =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Toy models of superposition , journal =

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:08.700415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c30c031d-a48c-49db-9e91-19bcd2e69509 · outbound

This paper cites Beyond interpretability:.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Beyond interpretability:

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:08.752534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09cd44d1-7eda-419f-bcef-91d0e8259696 · outbound

This paper cites Forty-first.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Forty-first

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:08.819551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1752eea0-a0e6-4e8d-96f7-fe8cc6e02b3a · outbound

This paper cites Peftguard:.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Peftguard:

Reference 58

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:08.890421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95025b31-743e-457d-84ba-0062f75eba49 · outbound

This paper cites Proceedings of the 63rd.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Proceedings of the 63rd

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:08.951128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb2d8216-fc21-4dd4-b312-cdc8d865a3f5 · outbound

This paper cites Universal jailbreak backdoors from poisoned human feedback , volume =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Universal jailbreak backdoors from poisoned human feedback , volume =

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.012467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b8f0ba5-2ef7-4cf3-a2f9-4c95b069bbb2 · outbound

This paper cites arXiv preprint arXiv:2602.13427 , author =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned arXiv preprint arXiv:2602.13427 , author =

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.072201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e435c4a-079d-48eb-9518-e16952391479 · outbound

This paper cites an unresolved cited work.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Unresolved cited work

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.162845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44303353-b4a7-46b3-a4d3-44ba1a98586b · outbound

This paper cites Poisoning language models during instruction tuning , booktitle =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Poisoning language models during instruction tuning , booktitle =

Reference 63

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.270889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ac288c3-d111-4d19-be73-abbc2856e4b8 · outbound

This paper cites an unresolved cited work.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Unresolved cited work

Reference 64

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.395250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92e9e9b1-3ecc-483a-a789-3d5e1140c31a · outbound

This paper cites Planting undetectable backdoors in machine learning models , booktitle =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Planting undetectable backdoors in machine learning models , booktitle =

Reference 65

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.564304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c98f9cb-b2d2-4c02-9296-aef9705ec2e6 · outbound

This paper cites an unresolved cited work.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Unresolved cited work

Reference 66

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.731272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02ab7876-7d33-4ac3-b979-4ff9489f96fa · outbound

This paper cites Extracting.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Extracting

Reference 67

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.825487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05205ee2-2fe1-4b15-b8b3-1f7ba82eec03 · outbound

This paper cites and Chen, Pin-Yu , editor =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned and Chen, Pin-Yu , editor =

Reference 68

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.831495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7d4c5d3-e916-469b-a199-00b02cf07102 · outbound

This paper cites Not what you've signed up for:.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Not what you've signed up for:

Reference 69

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.837801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3d49ba7-82bb-4f50-ad04-ff5263601ad9 · outbound

This paper cites Escalation.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Escalation

Reference 70

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.844485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b1c6e8d-7033-46a1-a82d-a1810202627f · outbound

This paper cites Transactions on Machine Learning Research , author =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Transactions on Machine Learning Research , author =

Reference 71

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.850706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f77e5683-ea46-42cc-8166-4d30cbd39b7b · outbound

This paper cites Blind backdoors in deep learning models , booktitle =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Blind backdoors in deep learning models , booktitle =

Reference 72

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.857906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fe07f77-d4c3-4993-b0dc-44a7eeb12f39 · outbound

This paper cites an unresolved cited work.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Unresolved cited work

Reference 73

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.865637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ccf5244-13ae-4c3a-9b31-9367ef8f2532 · outbound

This paper cites Persistent pre-training poisoning of llms , journal =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Persistent pre-training poisoning of llms , journal =

Reference 74

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.870956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6b3bef4-901b-4b08-95d7-88412be74994 · outbound

This paper cites Poisoning attacks on llms require a near-constant number of poison samples , journal =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Poisoning attacks on llms require a near-constant number of poison samples , journal =

Reference 75

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.877503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7023355c-3670-4ba8-88de-03bea433c801 · outbound

This paper cites an unresolved cited work.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Unresolved cited work

Reference 76

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.884902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66d7e504-f35e-463d-8bcd-cdc90edc918a · outbound

This paper cites Backdooring.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Backdooring

Reference 77

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.890080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e21bcd0a-8372-46d4-9a10-08148639510a · outbound

This paper cites an unresolved cited work.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Unresolved cited work

Reference 78

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.894836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6dcc252-70f2-4394-9f91-a314b4b214c2 · outbound

This paper cites , year =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned , year =

Reference 79

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.899208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa9b1275-47e3-467a-a577-db4e164d9b79 · outbound

This paper cites , year =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned , year =

Reference 80

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.904452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d52e8c99-c043-4a6e-ad74-985f08e2e0b4 · outbound

This paper cites Adversarial.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Adversarial

Reference 81

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.911241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b71aca3b-c63c-428d-bca8-69a5e3af08ab · outbound

This paper cites Text embeddings reveal (almost) as much as text , booktitle =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Text embeddings reveal (almost) as much as text , booktitle =

Reference 82

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.917140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc0b89ea-8298-400f-bc36-19dc872c1d1c · outbound

This paper cites Transferable.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Transferable

Reference 83

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.927450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 994bcb3b-fd15-40da-9edc-c6443e410058 · outbound

This paper cites an unresolved cited work.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Unresolved cited work

Reference 84

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.933313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b26105f-509d-4128-80f2-c56c00ca9a1b · outbound

This paper cites an unresolved cited work.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Unresolved cited work

Reference 85

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.939957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 179a0c9a-d504-4f43-a5aa-87f499e5b071 · outbound

This paper cites The trojan detection challenge , booktitle =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned The trojan detection challenge , booktitle =

Reference 86

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.944560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df07f20a-e1c8-47d9-bafa-7bb776edfc56 · outbound

This paper cites an unresolved cited work.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Unresolved cited work

Reference 87

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.950343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a5f099b-be9e-405b-8640-e95f7499ccca · outbound

This paper cites Practical detection of trojan neural networks:.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Practical detection of trojan neural networks:

Reference 88

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.955922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1c19609-e554-44b6-9da4-9b99a0d720c4 · outbound

This paper cites Piccolo:.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Piccolo:

Reference 89

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.961757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ffe532a-f5b6-4dba-a957-a88b264801dc · outbound

This paper cites IEEE Transactions on Software Engineering , author =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned IEEE Transactions on Software Engineering , author =

Reference 90

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.967644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a8aad12-f9cc-4da4-9a70-fad82a9fac49 · outbound

This paper cites Proceedings of the 2024.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Proceedings of the 2024

Reference 91

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.974940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ecefcc6-6618-4d22-ade5-1f958f97f48f · outbound

This paper cites an unresolved cited work.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Unresolved cited work

Reference 92

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.987084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c25c449e-6853-4e20-89de-e5f7f49245ca · outbound

This paper cites , month = may, year =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned , month = may, year =

Reference 93

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:09.998513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6802df08-935e-4673-bd04-dd2a40bb3a3b · outbound

This paper cites Backdoor.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Backdoor

Reference 94

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:10.005929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10487c08-9b56-44e2-9323-280063de1974 · outbound

This paper cites Rethinking.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Rethinking

Reference 95

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:10.012560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d0cf8ce-6d92-4254-aa2f-0969e1c6cce4 · outbound

This paper cites an unresolved cited work.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Unresolved cited work

Reference 96

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:10.017545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad907501-17ae-481e-bce2-055ed801ce46 · outbound

This paper cites Revisiting the.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Revisiting the

Reference 97

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:10.024125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d37128b-e3c2-4371-98a1-0ee3b6b54db1 · outbound

This paper cites Stealthy and.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Stealthy and

Reference 98

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:10.033098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e669a55-a808-4370-aa8d-afb24d3223be · outbound

This paper cites Catastrophic.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Catastrophic

Reference 99

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:10.039692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36c793f0-0fc9-49cb-a751-94b8bb61188f · outbound

This paper cites Proceedings of the 2021 conference on empirical methods in natural language processing , author =.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Proceedings of the 2021 conference on empirical methods in natural language processing , author =

Reference 100

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:10.045028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80984baf-5a21-44d7-aa34-5490e56bee64 · outbound

This paper cites an unresolved cited work.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Unresolved cited work

Reference 101

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:10.050704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 811ebf4c-a088-4825-99d4-df9f1426da18 · outbound

This paper cites an unresolved cited work.

ToxScreen: Detecting Whether an LLM Has Been Poisoned Unresolved cited work

Reference 102

Resolution: unresolved; no resolver link, observed 2026-07-30T19:18:10.059070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers