Preference learning made easy: Everything should be understood through win rate | Paper Citation Record

Observation d6180138-a454-4301-9e33-643e150b0bb8 · outbound

This paper cites Back to basics: Revisiting reinforce style optimization for learning from human feedback in llms.

Preference learning made easy: Everything should be understood through win rate Back to basics: Revisiting reinforce style optimization for learning from human feedback in llms

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:23.028818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1b074722-1adc-408b-b4cb-9b3f3040dc52 · outbound

This paper cites Calibration and consistency of adversarial surrogate losses.

Preference learning made easy: Everything should be understood through win rate Calibration and consistency of adversarial surrogate losses

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:23.007001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4c251466-16c3-4b63-b3ac-5d2ad985737c · outbound

This paper cites Multi-class h -consistency bounds.

Preference learning made easy: Everything should be understood through win rate Multi-class h -consistency bounds

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.983272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4c2cc416-e36f-4b17-94ca-93af7a38517c · outbound

This paper cites G., Rowland, M., Piot, B., Guo, D., Calandriello, D., Valko, M., and Munos, R.

Preference learning made easy: Everything should be understood through win rate G., Rowland, M., Piot, B., Guo, D., Calandriello, D., Valko, M., and Munos, R

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.965345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d8ab9d49-91d5-49cd-a64c-2dc628851e04 · outbound

This paper cites Training a helpful and harmless assistant with reinforcement learning from human feedback.

Preference learning made easy: Everything should be understood through win rate Training a helpful and harmless assistant with reinforcement learning from human feedback

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.938806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bad98efd-8a4b-48f9-9230-63a8f1eee886 · outbound

This paper cites Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling.

Preference learning made easy: Everything should be understood through win rate Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T18:32:20.938380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e77688e-f12f-4247-b719-10fae9e6a0b8 · outbound

This paper cites Quantile Filtered Imitation Learning.

Preference learning made easy: Everything should be understood through win rate Quantile Filtered Imitation Learning

Reference 7

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T18:32:22.012736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 43afe68a-4ec2-412e-85dc-3230471c94a9 · outbound

This paper cites Probabilistic interpretation of feedforward classification network outputs, with relationships to statistical pattern recognition.

Preference learning made easy: Everything should be understood through win rate Probabilistic interpretation of feedforward classification network outputs, with relationships to statistical pattern recognition

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.919649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9f07e96b-2159-4740-a1d1-875239dda663 · outbound

This paper cites Human Alignment of Large Language Models through Online Preference Optimisation.

Preference learning made easy: Everything should be understood through win rate Human Alignment of Large Language Models through Online Preference Optimisation

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T18:32:20.963680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8107c9da-f2c5-40f5-8b2f-330139a41e75 · outbound

This paper cites H., Chen, X., Zhang, Q., Ranganath, R., and Cho, K.

Preference learning made easy: Everything should be understood through win rate H., Chen, X., Zhang, Q., Ranganath, R., and Cho, K

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.898525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2902befc-3e72-43b6-acfe-88eb4cef412d · outbound

This paper cites Deep reinforcement learning from human preferences.

Preference learning made easy: Everything should be understood through win rate Deep reinforcement learning from human preferences

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T18:32:20.983164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b619d067-3659-4495-ad93-2921e730fb13 · outbound

This paper cites Raft: Reward ranked finetuning for generative foundation model alignment.

Preference learning made easy: Everything should be understood through win rate Raft: Reward ranked finetuning for generative foundation model alignment

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.864549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 51dd05ae-79b1-41fc-ba02-c0308782ba0f · outbound

This paper cites Understanding dataset difficulty with v-usable information.

Preference learning made easy: Everything should be understood through win rate Understanding dataset difficulty with v-usable information

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.839675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c5d841ae-b317-4623-9930-c2b9d97c89b4 · outbound

This paper cites Bonbon alignment for large language models and the sweetness of best-of-n sampling.

Preference learning made easy: Everything should be understood through win rate Bonbon alignment for large language models and the sweetness of best-of-n sampling

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.814056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b64d9244-8006-498c-96d9-4831e68de4b7 · outbound

This paper cites L., Srinivasan, S., Konyushkova, K., Weerts, L., Sharma, A., Siddhant, A., Ahern, A., Wang, M., Gu, C., Macherey, W., Doucet, A., Firat, O., and de Freitas, N.

Preference learning made easy: Everything should be understood through win rate L., Srinivasan, S., Konyushkova, K., Weerts, L., Sharma, A., Siddhant, A., Ahern, A., Wang, M., Gu, C., Macherey, W., Doucet, A., Firat, O., and de Freitas, N

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.788839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5724ed26-706e-4021-a240-b524f4676b17 · outbound

This paper cites Direct Language Model Alignment from Online AI Feedback.

Preference learning made easy: Everything should be understood through win rate Direct Language Model Alignment from Online AI Feedback

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T18:32:21.022389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40ae999b-8da0-42a5-b001-6d340fead544 · outbound

This paper cites $f$-PO: Generalizing Preference Optimization with $f$-divergence Minimization.

Preference learning made easy: Everything should be understood through win rate $f$-PO: Generalizing Preference Optimization with $f$-divergence Minimization

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T18:32:21.028109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3f076e6-6916-4baf-95d1-94ee9fcb0d54 · outbound

This paper cites Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization.

Preference learning made easy: Everything should be understood through win rate Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T18:32:21.033460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52740ac5-432c-4efb-870d-81ff9b8c7ff2 · outbound

This paper cites A., Choi, Y., and Hajishirzi, H.

Preference learning made easy: Everything should be understood through win rate A., Choi, Y., and Hajishirzi, H

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.766300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 42270018-9ef5-4abf-b241-7186c0528296 · outbound

This paper cites Towards Efficient Exact Optimization of Language Model Alignment.

Preference learning made easy: Everything should be understood through win rate Towards Efficient Exact Optimization of Language Model Alignment

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T18:32:21.045898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb3b3895-c27c-4a72-9c09-74f8b2d8a384 · outbound

This paper cites A Survey on Human Preference Learning for Large Language Models.

Preference learning made easy: Everything should be understood through win rate A Survey on Human Preference Learning for Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T18:32:21.053077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6ba482e-7eed-4cf0-ba69-08f0200da95b · outbound

This paper cites A survey of reinforcement learning from human feedback.

Preference learning made easy: Everything should be understood through win rate A survey of reinforcement learning from human feedback

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T18:32:21.059995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15754356-b360-4f9e-948e-14bdfb38a397 · outbound

This paper cites Understanding the effects of rlhf on llm generalisation and diversity.

Preference learning made easy: Everything should be understood through win rate Understanding the effects of rlhf on llm generalisation and diversity

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.729922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d73ad913-60ec-4daa-947a-c504d2031a5d · outbound

This paper cites OpenAssistant Conversations -- Democratizing Large Language Model Alignment.

Preference learning made easy: Everything should be understood through win rate OpenAssistant Conversations -- Democratizing Large Language Model Alignment

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T18:32:21.072721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 103738c8-633e-451f-be24-7474252aa77b · outbound

This paper cites Huggingface h4 stack exchange preference dataset.

Preference learning made easy: Everything should be understood through win rate Huggingface h4 stack exchange preference dataset

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.710240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 367c276c-8757-48fc-ba82-3f127d3ae281 · outbound

This paper cites Self-Alignment with Instruction Backtranslation.

Preference learning made easy: Everything should be understood through win rate Self-Alignment with Instruction Backtranslation

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T18:32:21.086641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 959bff62-81b5-428d-a8df-db9dabe0082d · outbound

This paper cites an unresolved cited work.

Preference learning made easy: Everything should be understood through win rate Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-07T18:32:22.686595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 14b5bd41-343a-4f2a-b5ca-7ae15d2060c1 · outbound

This paper cites Large Language Models: A Survey.

Preference learning made easy: Everything should be understood through win rate Large Language Models: A Survey

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T18:32:21.100629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74293d31-b9a8-4b0c-98c0-135fa23159a2 · outbound

This paper cites Monte carlo gradient estimation in machine learning.

Preference learning made easy: Everything should be understood through win rate Monte carlo gradient estimation in machine learning

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.663308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 39550b1e-bb78-4ec1-85ed-2813f2bada54 · outbound

This paper cites Monte carlo gradient estimation in machine learning.

Preference learning made easy: Everything should be understood through win rate Monte carlo gradient estimation in machine learning

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.641721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 465c40fd-57e9-44af-9f9e-309cf5c2cfec · outbound

This paper cites G., Rowland, M., Guo, Z.

Preference learning made easy: Everything should be understood through win rate G., Rowland, M., Guo, Z

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.621373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 20c613a0-c772-4fd1-86f1-899de5cc54a6 · outbound

This paper cites A., Lindsten, F., and Blei, D.

Preference learning made easy: Everything should be understood through win rate A., Lindsten, F., and Blei, D

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.601091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5336bf60-2085-4690-9267-135c1e51011f · outbound

This paper cites Gpt-4 technical report.

Preference learning made easy: Everything should be understood through win rate Gpt-4 technical report

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.582335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 816e2397-35a3-4c92-9c0f-9672f797b1e2 · outbound

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

Preference learning made easy: Everything should be understood through win rate Training language models to follow instructions with human feedback

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T18:32:21.145340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd5fa80e-fc39-44b0-87a1-6a881f593f98 · outbound

This paper cites Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive.

Preference learning made easy: Everything should be understood through win rate Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T18:32:21.154929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85b9a4a5-97aa-499d-8585-18d3b2556cd4 · outbound

This paper cites Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms.

Preference learning made easy: Everything should be understood through win rate Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T18:32:21.165463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5b4a645-6411-48d5-a1b2-a2dc0a364c3c · outbound

This paper cites From r to q^* : Your language model is secretly a q-function.

Preference learning made easy: Everything should be understood through win rate From r to q^* : Your language model is secretly a q-function

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.549800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1b439a24-3a82-4014-9314-a15db84d1e18 · outbound

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

Preference learning made easy: Everything should be understood through win rate D., Ermon, S., and Finn, C

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.528340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 05e21823-4197-4c1b-8316-77d5cd106f45 · outbound

This paper cites Black box variational inference.

Preference learning made easy: Everything should be understood through win rate Black box variational inference

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.507183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2b6830b4-152f-418b-afd5-34dffd1e055f · outbound

This paper cites Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization.

Preference learning made easy: Everything should be understood through win rate Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T18:32:21.189249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a389f205-5390-4018-9842-8d8291d01b0c · outbound

This paper cites Vanishing gradients in reinforcement finetuning of language models.

Preference learning made easy: Everything should be understood through win rate Vanishing gradients in reinforcement finetuning of language models

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.481360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cacef77f-dca8-49dd-a1ec-72cd0c5e9daf · outbound

This paper cites Direct nash optimization: Teaching language models to self-improve with general preferences, 2024.

Preference learning made easy: Everything should be understood through win rate Direct nash optimization: Teaching language models to self-improve with general preferences, 2024

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.452006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 64519d34-4c42-4d2f-a260-b89f02cfed61 · outbound

This paper cites Direct Alignment with Heterogeneous Preferences.

Preference learning made easy: Everything should be understood through win rate Direct Alignment with Heterogeneous Preferences

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T18:32:21.206355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 823f03aa-ab4a-4e29-9d59-69a72139f1aa · outbound

This paper cites A Long Way to Go: Investigating Length Correlations in RLHF.

Preference learning made easy: Everything should be understood through win rate A Long Way to Go: Investigating Length Correlations in RLHF

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T18:32:21.215175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fea3bb9f-372c-4b55-89ef-4ac8e716d64b · outbound

This paper cites Distributional preference learning: Understanding and accounting for hidden context in rlhf.

Preference learning made easy: Everything should be understood through win rate Distributional preference learning: Understanding and accounting for hidden context in rlhf

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.424473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d577a9f7-535e-42c8-8c1a-7fde56c8e413 · outbound

This paper cites How to compare different loss functions and their risks.

Preference learning made easy: Everything should be understood through win rate How to compare different loss functions and their risks

Reference 46

Resolution: verified exact; doi, observed 2026-08-07T18:32:21.406280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3b65fc6e-bc9e-44f5-a051-1c4c21f62af3 · outbound

This paper cites Learning to summarize from human feedback.

Preference learning made easy: Everything should be understood through win rate Learning to summarize from human feedback

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T18:32:21.232480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9667a6d-961a-4104-b483-ad8b2d1fbb5f · outbound

This paper cites S., and Agarwal, A.

Preference learning made easy: Everything should be understood through win rate S., and Agarwal, A

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.394366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 59644008-f9e1-4566-9f7d-bb638ceb40cd · outbound

This paper cites Preference fine-tuning of llms should leverage suboptimal, on-policy data.

Preference learning made easy: Everything should be understood through win rate Preference fine-tuning of llms should leverage suboptimal, on-policy data

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.375130Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a8b1c143-4b83-49ea-bf47-4462a0fc4edb · outbound

This paper cites D., Zheng, Z., Calandriello, D., Munos, R., Rowland, M., Richemond, P.

Preference learning made easy: Everything should be understood through win rate D., Zheng, Z., Calandriello, D., Munos, R., Rowland, M., Richemond, P

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.348188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8a4e59a3-d701-4d99-98be-dd44878199ec · outbound

This paper cites Trl: Transformer reinforcement learning.

Preference learning made easy: Everything should be understood through win rate Trl: Transformer reinforcement learning

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.322709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 14b72f64-ca56-407f-aee4-3b0792b5404b · outbound

This paper cites Enabling language models to implicitly learn self-improvement.

Preference learning made easy: Everything should be understood through win rate Enabling language models to implicitly learn self-improvement

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.297854Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 622b1c22-0d0e-4116-9b0c-ca6b54aefe74 · outbound

This paper cites Transforming and combining rewards for aligning large language models.

Preference learning made easy: Everything should be understood through win rate Transforming and combining rewards for aligning large language models

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.261958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 14cf1242-2bb1-4135-80d9-aa4b0aefe821 · outbound

This paper cites Policy gradient algorithms.

Preference learning made easy: Everything should be understood through win rate Policy gradient algorithms

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.238493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 74368c74-59ad-45f1-a388-e08c26b885b0 · outbound

This paper cites V., Murray, K., and Kim, Y.

Preference learning made easy: Everything should be understood through win rate V., Murray, K., and Kim, Y

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.201317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 97ad70a4-9085-4d57-ad7e-f3d6738836c3 · outbound

This paper cites Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss.

Preference learning made easy: Everything should be understood through win rate Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T18:32:21.300233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00f98043-ba0a-4e26-a390-a345ade3e382 · outbound

This paper cites Y., Cho, K., Sukhbaatar, S., Xu, J., and Weston, J.

Preference learning made easy: Everything should be understood through win rate Y., Cho, K., Sukhbaatar, S., Xu, J., and Weston, J

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.175500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5e8863dd-e6f4-4a5c-8ebe-e6fde31070dd · outbound

This paper cites an unresolved cited work.

Preference learning made easy: Everything should be understood through win rate Unresolved cited work

Reference 58

Resolution: unresolved; raw_fallback, observed 2026-08-07T18:32:22.143704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 862eb67f-a726-4035-9669-b97892d90489 · outbound

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

Preference learning made easy: Everything should be understood through win rate Judging llm-as-a-judge with mt-bench and chatbot arena

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.120972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e9610168-ebbd-4b38-b0c3-8b7fab8f24bc · outbound

This paper cites I., and Jiao, J.

Preference learning made easy: Everything should be understood through win rate I., and Jiao, J

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T18:32:22.100251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4419939a-a0f5-49a7-b640-ecc4d607b2e2 · outbound

This paper cites write newline.

Preference learning made easy: Everything should be understood through win rate write newline

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T18:32:21.331060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers