TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs | Paper Citation Record

Observation 11530aa0-a69b-44b0-82e5-d4a0eac97c56 · outbound

This paper cites write newline.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:08.548572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28f0fb6c-96a9-43d5-81a7-ac2f2baed5aa · outbound

This paper cites and Bengio, Y.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs and Bengio, Y

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:08.653710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98014e69-ec1b-42ac-8d76-047f2649a8d2 · outbound

This paper cites Detecting Language Model Attacks with Perplexity.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Detecting Language Model Attacks with Perplexity

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:08.721330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddcd7fb7-a73f-42fc-990f-611cfd74c0ce · outbound

This paper cites Many-shot jailbreaking.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Many-shot jailbreaking

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:25.217894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation dfebdf56-68ee-4a0c-ba8d-933110cccce6 · outbound

This paper cites A General Language Assistant as a Laboratory for Alignment.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs A General Language Assistant as a Laboratory for Alignment

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:08.877776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 272f05c4-9832-4a2c-affb-178f5ccd50bc · outbound

This paper cites and Mitchell, T.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs and Mitchell, T

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:25.052642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5e453a55-13ea-411e-b6cd-8c2430b730a8 · outbound

This paper cites L., Kiros, J.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs L., Kiros, J

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:24.807336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 514b5e1e-390d-44e3-be10-34608d74f874 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:09.153361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 273aef57-9dee-4ada-9ea9-0eb616ddbe9f · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Constitutional AI: Harmlessness from AI Feedback

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:09.231687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b495c4fc-c699-4382-8e83-339b88d7fec0 · outbound

This paper cites Probing classifiers: Promises, shortcomings, and advances.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Probing classifiers: Promises, shortcomings, and advances

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:24.594417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5aeaffa9-d871-4e00-bd1e-f8c9606cad02 · outbound

This paper cites an unresolved cited work.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:50:24.381579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 797f06ed-30e0-4f57-bb68-dffd9f83ca83 · outbound

This paper cites Findings of the 2014 workshop on statistical machine translation.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Findings of the 2014 workshop on statistical machine translation

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:24.189466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8afe053c-0705-45c7-b348-e18d398fa904 · outbound

This paper cites an unresolved cited work.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:09.527556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96af58ad-8010-4154-bc39-7cbe16c189ff · outbound

This paper cites D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:09.607037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 307cd53b-9ad0-4451-a276-ed23d4e53805 · outbound

This paper cites Discovering latent knowledge in language models without supervision.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Discovering latent knowledge in language models without supervision

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:24.041254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4b66a7c0-548f-4ed6-92cc-b42cf8cdb638 · outbound

This paper cites T., Rubanova, Y., Bettencourt, J., and Duvenaud, D.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs T., Rubanova, Y., Bettencourt, J., and Duvenaud, D

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:09.750492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c36b8460-eae7-4d24-aaca-52c57daf4a56 · outbound

This paper cites F., Leike, J., Brown, T., Martic, M., Legg, S., and Amodei, D.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs F., Leike, J., Brown, T., Martic, M., Legg, S., and Amodei, D

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:09.834866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fbe74fe-5aae-4b87-bd7c-0731c48bdd92 · outbound

This paper cites an unresolved cited work.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:50:23.811629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c8fb532b-f6fb-48c0-9868-7ee5d2df62d8 · outbound

This paper cites Some Gronwall Type Inequalities and Applications.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Some Gronwall Type Inequalities and Applications

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:23.682360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b5a5b923-cc7a-4c02-bf93-277ba01b23f5 · outbound

This paper cites A mathematical framework for transformer circuits.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs A mathematical framework for transformer circuits

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:23.530417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 58c914b9-f0e6-4f1f-bcab-af5844742540 · outbound

This paper cites Red teaming language models to reduce harms: Methods, scaling behaviors, and lessons learned.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Red teaming language models to reduce harms: Methods, scaling behaviors, and lessons learned

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:23.293131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 95b7ae7e-e6b0-49f0-b355-35e404ff342a · outbound

This paper cites and Cohen, V.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs and Cohen, V

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:10.274959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b01ad6c-1553-4f94-aeaf-35174d70be89 · outbound

This paper cites Studying Large Language Model Generalization with Influence Functions.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Studying Large Language Model Generalization with Influence Functions

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:10.368350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44509aa4-dcbb-4ac5-a059-e3ed9a20661c · outbound

This paper cites Simfluence: Modeling the Influence of Individual Training Examples by Simulating Training Runs.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Simfluence: Modeling the Influence of Individual Training Examples by Simulating Training Runs

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:10.482727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf75480a-18dc-42ac-b81a-7cd7e49a98c4 · outbound

This paper cites and Lowd, D.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs and Lowd, D

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:10.559511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccf145ba-bb60-499d-b453-6d5f708eb58f · outbound

This paper cites an unresolved cited work.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:10.608612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6347fd1-5141-45ff-aad1-72db5103a14f · outbound

This paper cites Measuring massive multitask language understanding.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Measuring massive multitask language understanding

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:23.144427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c9713db3-7069-4d25-81e5-730d8001c21f · outbound

This paper cites T., Wortsman, M., Schmidt, L., Hajishirzi, H., and Farhadi, A.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs T., Wortsman, M., Schmidt, L., Hajishirzi, H., and Farhadi, A

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:22.937489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation bd980144-df89-4caa-a4dd-723363ff5558 · outbound

This paper cites Baseline Defenses for Adversarial Attacks Against Aligned Language Models.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:10.771832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ea4ae9f-5069-4b41-bc4a-b5013347fbd1 · outbound

This paper cites S., Dick, R.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs S., Dick, R

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:22.735655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 110ac578-c07b-4ac8-84f4-8fad90ae4719 · outbound

This paper cites J., Hassani, H., Zhang, Y., Wong, E., and Chang, S.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs J., Hassani, H., Zhang, Y., Wong, E., and Chang, S

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:22.550920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a4fa776e-d0c1-47b8-b23e-abcca74867eb · outbound

This paper cites Mistral 7B.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Mistral 7B

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:10.939916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 489955c0-948c-4197-a2a2-a1abcd06a870 · outbound

This paper cites an unresolved cited work.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:50:22.259838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 82a7e538-6321-4518-922f-a9077c226613 · outbound

This paper cites M., and Raghunathan, A.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs M., and Raghunathan, A

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:22.074420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 24a8235f-d6b6-49a1-8b5c-952c5a5137a9 · outbound

This paper cites J., Feizi, S., and Lakkaraju, H.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs J., Feizi, S., and Lakkaraju, H

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:21.840898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 94c67bc4-9f51-4813-8ecf-5e69d0c055c3 · outbound

This paper cites Inference-time intervention: Eliciting truthful answers from a language model.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Inference-time intervention: Eliciting truthful answers from a language model

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:21.602108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation edde39ab-306e-4777-899d-462e85b14e52 · outbound

This paper cites Mitigating the alignment tax of rlhf.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Mitigating the alignment tax of rlhf

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:21.399339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 902ef6a5-2222-48ef-8d3b-c6ab239a19cd · outbound

This paper cites Autodan: Generating stealthy jailbreak prompts on aligned large language models.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Autodan: Generating stealthy jailbreak prompts on aligned large language models

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:21.188573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 66448d81-a58d-4c64-8d69-4d40050cd8f8 · outbound

This paper cites S., Love, J., Tafti, P., et al.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs S., Love, J., Tafti, P., et al

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:20.939705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5054b570-47f1-4485-823c-6012c28e52bb · outbound

This paper cites Introducing meta llama 3: The most capable openly available llm to date.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Introducing meta llama 3: The most capable openly available llm to date

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:20.718367Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 3d35a9f4-6f16-443c-a2f4-d275cb3629d2 · outbound

This paper cites an unresolved cited work.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:50:20.546537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6f65c769-b3d9-4055-8d59-943d5e5e2d68 · outbound

This paper cites an unresolved cited work.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:50:20.359492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1a28686a-cbd2-4f9e-9624-af4d1f26f435 · outbound

This paper cites Zoom in: An introduction to circuits.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Zoom in: An introduction to circuits

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:11.630278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c932f7b-a6cd-40c2-90e5-61d6593d9101 · outbound

This paper cites In-context learning and induction heads.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs In-context learning and induction heads

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:11.722649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 765e5289-0a79-4f8d-9442-c616f48b7091 · outbound

This paper cites Training language models to follow instructions with human feedback.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Training language models to follow instructions with human feedback

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:11.792067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b5d72cb-eb9a-4489-8f29-e3dbb350313c · outbound

This paper cites Discovering language model behaviors with model-written evaluations.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Discovering language model behaviors with model-written evaluations

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:20.196981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 87e43776-7b36-453e-94a7-835b5318ec61 · outbound

This paper cites D., Peng, S., Szyller, S., Cornelius, C., and Chau, D.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs D., Peng, S., Szyller, S., Cornelius, C., and Chau, D

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:20.034008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e3d3f5ab-8216-4305-ad2a-2aeb7c4e346a · outbound

This paper cites R., Haklay, T., Belinkov, Y., and Bau, D.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs R., Haklay, T., Belinkov, Y., and Bau, D

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:19.846769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9f325cc8-205d-423b-af98-6f5d17ad4ef7 · outbound

This paper cites Estimating training data influence by tracing gradient descent.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Estimating training data influence by tracing gradient descent

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:12.202001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b016f0f6-eb93-4beb-9eb2-798e3ad64259 · outbound

This paper cites Improving language understanding by generative pre-training.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Improving language understanding by generative pre-training

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:19.642833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0c9ca3a3-0489-42d6-a7f6-799bdab5d4c7 · outbound

This paper cites Language models are unsupervised multitask learners.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Language models are unsupervised multitask learners

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:12.449919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 331303f3-f014-47b2-9f96-fdbaf752e2f8 · outbound

This paper cites D., Ermon, S., and Finn, C.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs D., Ermon, S., and Finn, C

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:12.552595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 941eb56e-f336-402c-92c9-a1d59c9db317 · outbound

This paper cites Steering llama 2 via contrastive activation addition.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Steering llama 2 via contrastive activation addition

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:19.477112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4de447e7-f623-4220-9235-de629f309381 · outbound

This paper cites an unresolved cited work.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Unresolved cited work

Reference 54

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:50:19.293166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 991c5ca1-6b91-466c-9cc1-86818e3f7a5a · outbound

This paper cites The perceptron: a probabilistic model for information storage and organization in the brain.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs The perceptron: a probabilistic model for information storage and organization in the brain

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:12.791904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d759957-1809-45b5-9c31-20276b76c71e · outbound

This paper cites Principles of Mathematical Analysis.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Principles of Mathematical Analysis

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:19.098581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4cd72699-35f4-451d-a3cd-b08bc067df87 · outbound

This paper cites E., Ablin, P., and Peyr \'e , G.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs E., Ablin, P., and Peyr \'e , G

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:18.955649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 7dc37f8b-3d6c-431f-a25a-58fe4fe2073a · outbound

This paper cites Scaling up influence functions.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Scaling up influence functions

Reference 58

Resolution: verified exact; doi, observed 2026-08-06T21:50:15.881705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 141717dd-485a-40bc-921b-0193b85c374c · outbound

This paper cites Proximal Policy Optimization Algorithms.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Proximal Policy Optimization Algorithms

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:13.190645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1da68090-2452-46a4-8b8c-0af7e9dbee35 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs LLaMA: Open and Efficient Foundation Language Models

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:13.273251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05fe8d04-a38e-437a-a2c0-8839d005047b · outbound

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

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:13.383086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 645c1113-24ab-4560-8a98-1ab03e5ab596 · outbound

This paper cites and Schmid, P.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs and Schmid, P

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:18.803124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ef2e07b4-647e-444f-a69b-391f780e4087 · outbound

This paper cites M., and Wolf, T.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs M., and Wolf, T

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:13.588160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4f4400d-d201-4ce8-aad8-0bca1230bccf · outbound

This paper cites N., Kaiser, ., and Polosukhin, I.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs N., Kaiser, ., and Polosukhin, I

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:13.710850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4d4d359-498c-4aa8-87c0-e30e26dfeba9 · outbound

This paper cites Ordinary differential equations, volume 182.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Ordinary differential equations, volume 182

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:18.625098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 49835ec9-7ca4-4ec7-8796-4cd22ba9849e · outbound

This paper cites R., Variengien, A., Conmy, A., Shlegeris, B., and Steinhardt, J.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs R., Variengien, A., Conmy, A., Shlegeris, B., and Steinhardt, J

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:18.478557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 82882878-958b-4dca-ace3-cba5e2a13876 · outbound

This paper cites Defending llms against jailbreaking attacks via backtranslation.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Defending llms against jailbreaking attacks via backtranslation

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:18.297796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a3bb0431-892f-4ba6-93ac-98e594c730f1 · outbound

This paper cites Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems, 36, 2024.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems, 36, 2024

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:14.122695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91a5de1e-7136-471f-8b1e-d8f5cafc65b2 · outbound

This paper cites Larger language models do in-context learning differently, 2023.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Larger language models do in-context learning differently, 2023

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:18.168581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 52dc678e-658e-4d5b-927d-471c32b269a3 · outbound

This paper cites Principal component analysis.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Principal component analysis

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:17.918649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4ff83114-967b-4853-8112-e30ffad8073e · outbound

This paper cites Usage statistics of content languages for websites.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Usage statistics of content languages for websites

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:17.599966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b6808509-f61e-451e-ae9f-06a3e3db47c0 · outbound

This paper cites W., Li, M., Kornblith, S., Roelofs, R., Lopes, R.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs W., Li, M., Kornblith, S., Roelofs, R., Lopes, R

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:17.403142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b3c69623-c5e6-4268-ad71-a0e9e07bd2de · outbound

This paper cites Defending chatgpt against jailbreak attack via self-reminders.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Defending chatgpt against jailbreak attack via self-reminders

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:14.587991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1dd52d6f-44c9-4c3b-962c-40c2abc494f2 · outbound

This paper cites Hellaswag: Can a machine really finish your sentence? In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp.\ 4791--4800, 2019.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Hellaswag: Can a machine really finish your sentence? In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp.\ 4791--4800, 2019

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:14.750123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b139d30-5173-4a69-8cf7-84ed591f0703 · outbound

This paper cites and Sennrich, R.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs and Sennrich, R

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:14.950317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 932661df-5f6a-47d3-986e-594921747b4b · outbound

This paper cites Intention analysis makes llms a good jailbreak defender.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Intention analysis makes llms a good jailbreak defender

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:15.176064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00ba2fe8-d947-4029-afeb-ccb85aa337b7 · outbound

This paper cites an unresolved cited work.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Unresolved cited work

Reference 77

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:50:17.223607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ce3f861b-a1a6-4190-b104-8328c3c0f3fb · outbound

This paper cites Judging llm-as-a-judge with mt-bench and chatbot arena.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Judging llm-as-a-judge with mt-bench and chatbot arena

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:17.016547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 551163d5-80a9-440b-b1eb-e5d18b1b001a · outbound

This paper cites Defending jailbreak prompts via in-context adversarial game.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Defending jailbreak prompts via in-context adversarial game

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:16.753576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a1ecdf43-6ed1-40fb-87c5-92bde0b8a237 · outbound

This paper cites Autodan: Interpretable gradient-based adversarial attacks on large language models.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Autodan: Interpretable gradient-based adversarial attacks on large language models

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:16.526922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5b88c3f7-2409-4b3a-9905-3be64ecef70b · outbound

This paper cites Representation engineering: A top-down approach to ai transparency.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Representation engineering: A top-down approach to ai transparency

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:50:16.220295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0f825aa7-64ac-428f-91a8-1f6f32b76ea8 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:15.708071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers