Bradley-Terry and Multi-Objective Reward Modeling Are Complementary | Paper Citation Record

Observation cd50d613-d633-4991-8971-8b128e83bfaf · outbound

This paper cites A survey on evaluation of large language models.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary A survey on evaluation of large language models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:26.817729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b4481ec-ba23-4c3d-b178-99c05edaff16 · outbound

This paper cites Using an llm to help with code understanding.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Using an llm to help with code understanding

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.883557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0001cbad-5f0e-480a-8c10-ab04577d1bc4 · outbound

This paper cites A Survey of Large Language Models.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary A Survey of Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:26.955072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30c80e4a-ccfe-41b7-ab00-f763bfd2ca55 · outbound

This paper cites A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:26.988505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25a11b13-7de4-405b-b82f-73cda5024c44 · outbound

This paper cites A Survey on Large Language Models for Code Generation.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary A Survey on Large Language Models for Code Generation

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:27.064082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 916dd231-eeeb-4be9-8b3f-46bbd95effa9 · outbound

This paper cites Nguyen, Quang Pham, and Nghi D.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Nguyen, Quang Pham, and Nghi D

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.871249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5e740f70-b253-4026-90f8-c7df0600ac8c · outbound

This paper cites Rational decision-making agent with learning internal utility judgment.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Rational decision-making agent with learning internal utility judgment

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.859303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 349be0f5-8bb4-44e0-a2ab-341f001069a5 · outbound

This paper cites How Far are LLMs from Real Search? A Comprehensive Study on Efficiency, Completeness, and Inherent Capabilities.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary How Far are LLMs from Real Search? A Comprehensive Study on Efficiency, Completeness, and Inherent Capabilities

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:51:33.411523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 77e7bd53-557f-4cd7-973b-dded99fde893 · outbound

This paper cites Safe RLHF: Safe reinforcement learning from human feedback.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Safe RLHF: Safe reinforcement learning from human feedback

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.847033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 69708228-e735-41ca-9311-dc586d66fc1f · outbound

This paper cites Data-adaptive Safety Rules for Training Reward Models.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Data-adaptive Safety Rules for Training Reward Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:27.438057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7f6c85d-63e3-48c7-817c-802b866accaa · outbound

This paper cites Large Language Model Alignment: A Survey.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Large Language Model Alignment: A Survey

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:27.506062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96ebcb40-f4e9-4f43-b29b-46b60683ab82 · outbound

This paper cites Catastrophic failure of LLM unlearning via quantization.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Catastrophic failure of LLM unlearning via quantization

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.832930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0ad21580-69cc-445f-aa0b-1c0e961d356a · outbound

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

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:27.611461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd1fea6c-175a-4353-82c2-3ac45f6e46bc · outbound

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

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Training language models to follow instructions with human feedback

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:27.687717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b7edfe9-52ea-4f00-8d2a-2cbe30e2a777 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Proximal Policy Optimization Algorithms

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:27.723709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82fcb283-bb09-4b1a-9049-a6cfe95800a0 · outbound

This paper cites Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:27.774892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e15905dd-f349-45d5-99cc-214640b79ca9 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:27.849321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74b6565b-6ce5-4490-8d0f-4d062136a615 · outbound

This paper cites Scaling laws for reward model overoptimization.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Scaling laws for reward model overoptimization

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:27.880391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f5c8744-c079-420c-8e47-fd3f29ceef97 · outbound

This paper cites Regularizing hidden states enables learning generalizable reward model for LLMs.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Regularizing hidden states enables learning generalizable reward model for LLMs

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.804692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 72d56fc1-8a58-440d-b9d7-9e5b9069b774 · outbound

This paper cites Reinforced Self-Training (ReST) for Language Modeling.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Reinforced Self-Training (ReST) for Language Modeling

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:27.973611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f5ebdff-d09b-4348-a0a6-29c5c232a9a6 · outbound

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

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary RAFT: Reward ranked finetuning for generative foundation model alignment

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:28.021151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fe264a2-4475-4269-a0e8-7d2a74d1a5dc · outbound

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

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary BoNBon alignment for large language models and the sweetness of best-of-n sampling

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.783735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e5ff2773-3700-4367-8456-dbbaae253d92 · outbound

This paper cites Reward model ensembles help mitigate overoptimization.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Reward model ensembles help mitigate overoptimization

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.771629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2eceda81-b0f9-4057-8cee-6fd326be5e8f · outbound

This paper cites Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:28.145339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 814af997-c937-4d52-ae31-db71d34520ce · outbound

This paper cites Improving Reinforcement Learning from Human Feedback with Efficient Reward Model Ensemble.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Improving Reinforcement Learning from Human Feedback with Efficient Reward Model Ensemble

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:28.177191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1327b6b7-25c7-43f0-9cc9-2622a2a96aa8 · outbound

This paper cites Reward-Robust RLHF in LLMs.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Reward-Robust RLHF in LLMs

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:28.248727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 608ab5de-8333-4751-8d8c-66a9fe2ffdbd · outbound

This paper cites WARM: On the Benefits of Weight Averaged Reward Models.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary WARM: On the Benefits of Weight Averaged Reward Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:28.316657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32f17fb1-6713-426e-a30e-02e9f03beac8 · outbound

This paper cites Mitigating reward overoptimization via lightweight uncertainty estimation.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Mitigating reward overoptimization via lightweight uncertainty estimation

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.759487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 15f94c9c-a771-4795-8152-1f2b9969f667 · outbound

This paper cites Confronting reward model overoptimization with constrained RLHF.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Confronting reward model overoptimization with constrained RLHF

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.746959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation fd5e772f-2917-46fd-8d86-01b375aaf96e · outbound

This paper cites Provably mitigating overoptimization in RLHF: Your SFT loss is implicitly an adversarial regularizer.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Provably mitigating overoptimization in RLHF: Your SFT loss is implicitly an adversarial regularizer

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.733403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0c6ff2cd-dc93-4461-8ad5-5cef5b5228ba · outbound

This paper cites Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:28.518998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2670194a-a4ac-4f5c-9ff8-66c87f5a78b3 · outbound

This paper cites Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:28.540210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 494dedb6-ce66-4401-a30c-8228dcc88c96 · outbound

This paper cites Odin: Disentangled reward mitigates hacking in rlhf.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Odin: Disentangled reward mitigates hacking in rlhf

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.721348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d0ba9d10-7228-4b8c-a064-a26c851f1978 · outbound

This paper cites Mitigating reward over- optimization in RLHF via behavior-supported regularization.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Mitigating reward over- optimization in RLHF via behavior-supported regularization

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.709515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c8f808c6-1a69-4724-93a9-71a55743c510 · outbound

This paper cites Zhang, Makesh Narsimhan Sreedhar, and Oleksii Kuchaiev.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Zhang, Makesh Narsimhan Sreedhar, and Oleksii Kuchaiev

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.697634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7d77ce26-f716-45ca-bb5b-e2e43879b913 · outbound

This paper cites Interpretable prefer- ences via multi-objective reward modeling and mixture-of-experts.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Interpretable prefer- ences via multi-objective reward modeling and mixture-of-experts

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.685515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4d3b46b3-7012-40a1-ac29-651d3c92f037 · outbound

This paper cites Ultrafeedback: Boosting language models with high-quality feedback.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Ultrafeedback: Boosting language models with high-quality feedback

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:28.928468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6344dd9b-6b44-4d70-b083-52e5626041df · outbound

This paper cites Prometheus: Inducing fine-grained evaluation capability in language models.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Prometheus: Inducing fine-grained evaluation capability in language models

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.665354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1478dc94-e347-43a8-92da-4b5205119c2f · outbound

This paper cites From generation to judgment: Opportunities and challenges of llm-as-a-judge.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary From generation to judgment: Opportunities and challenges of llm-as-a-judge

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:29.094023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96f1ab52-5e08-4ef2-b706-13e379c3b536 · outbound

This paper cites A Survey on LLM-as-a-Judge.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary A Survey on LLM-as-a-Judge

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:29.160362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea44deb3-73ba-46be-8e99-2794c093ef3d · outbound

This paper cites Zhang, Makesh Narsimhan Sreedhar, and Oleksii Kuchaiev.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Zhang, Makesh Narsimhan Sreedhar, and Oleksii Kuchaiev

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.653319Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9f64425d-4872-4be7-a1e0-8c8d38b36f77 · outbound

This paper cites Smith, and Hannaneh Hajishirzi.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Smith, and Hannaneh Hajishirzi

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:29.240975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40709b58-5608-47ca-9a4d-baea0722a49d · outbound

This paper cites RM-bench: Benchmarking reward models of language models with subtlety and style.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary RM-bench: Benchmarking reward models of language models with subtlety and style

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.633063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1dc1b6a7-b1a6-4575-8604-bfd8e6e670a3 · outbound

This paper cites Rank analysis of incomplete block designs: I.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Rank analysis of incomplete block designs: I

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:29.387430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79436223-3dc2-4bc3-9038-6c364252e5ef · outbound

This paper cites HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:29.472946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2287ce39-6a6c-4864-8fb8-e7df4d8ab03a · outbound

This paper cites Arithmetic control of llms for diverse user preferences: Directional preference alignment with multi-objective rewards.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Arithmetic control of llms for diverse user preferences: Directional preference alignment with multi-objective rewards

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.612922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b72a5710-a58b-4182-82b3-2cbee629ab2d · outbound

This paper cites Learning to summarize with human feedback.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Learning to summarize with human feedback

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.600888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5f5d77c5-b60c-443c-8d50-71c554792d2e · outbound

This paper cites Pairwise proximal policy optimization: Language model alignment with comparative RL.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Pairwise proximal policy optimization: Language model alignment with comparative RL

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.588864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ec020fda-7a9c-441e-8d44-2e09e60de4c1 · outbound

This paper cites Reward shaping to mitigate reward hacking in rlhf.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Reward shaping to mitigate reward hacking in rlhf

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:29.921637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab2be653-9f15-48ff-adac-e8727d1f82d8 · outbound

This paper cites Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:29.978327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16cdb465-159a-4ae4-b6a3-f0fb8839c954 · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Gemma: Open Models Based on Gemini Research and Technology

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:30.078239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1560d3f1-fc0a-4acf-8370-8e9b79abaaec · outbound

This paper cites Reward Model Ensembles Help Mitigate Overoptimization.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Reward Model Ensembles Help Mitigate Overoptimization

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:30.200216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd38fb7b-20d0-4846-8fab-b52ad404bc98 · outbound

This paper cites an unresolved cited work.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Unresolved cited work

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:30.310756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67cd64a5-987a-4f44-983c-2810c38f8a4d · outbound

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

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:30.361244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27fdfeb5-0952-486b-a2b7-02ddb351d597 · outbound

This paper cites Secrets of RLHF in Large Language Models Part II: Reward Modeling.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Secrets of RLHF in Large Language Models Part II: Reward Modeling

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:30.462615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 205cb3df-66f4-4bad-8e25-0bb8575dc0c0 · outbound

This paper cites The Llama 3 Herd of Models.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary The Llama 3 Herd of Models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:30.537923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a96ce776-6d65-4285-b50a-1ad17fcbb364 · outbound

This paper cites RLHF Workflow: From Reward Modeling to Online RLHF.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary RLHF Workflow: From Reward Modeling to Online RLHF

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:30.659729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31ae3f94-581a-41da-8b50-e41d5176c51d · outbound

This paper cites Rethinking reward model evaluation: Are we barking up the wrong tree? In The Thirteenth International Conference on Learning Representations, 2025.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Rethinking reward model evaluation: Are we barking up the wrong tree? In The Thirteenth International Conference on Learning Representations, 2025

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.568393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4c137bbb-d842-4347-acf9-3bff36a85cbd · outbound

This paper cites What makes a reward model a good teacher? an optimization perspective.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary What makes a reward model a good teacher? an optimization perspective

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:30.935528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b1f0d2a-e239-4670-9539-70369bca1236 · outbound

This paper cites Mitigating the Alignment Tax of RLHF.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Mitigating the Alignment Tax of RLHF

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:31.112415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 918f8fce-fff4-4e9b-a382-65f69b82e97e · outbound

This paper cites Rethinking reward modeling in preference-based large language model alignment.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Rethinking reward modeling in preference-based large language model alignment

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.555746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 19f775c6-3d58-40b9-b8df-4c1f5703f672 · outbound

This paper cites Starling-7b: Improving llm helpfulness & harmlessness with rlaif.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Starling-7b: Improving llm helpfulness & harmlessness with rlaif

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.543076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 50cbdeac-a90e-489e-b035-53ad11c6274f · outbound

This paper cites Nemotron-4 340B Technical Report.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Nemotron-4 340B Technical Report

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:31.488714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a7e88c4-c5a8-42ca-bc98-9dae587c9d73 · outbound

This paper cites Fine-grained human feedback gives better rewards for language model training.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Fine-grained human feedback gives better rewards for language model training

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.530381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4885c4c4-937c-4e54-8052-92db587a203a · outbound

This paper cites Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment

Reference 65

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:51:32.838655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5f377fcb-db82-4eea-b21d-cbae3044e640 · outbound

This paper cites Chatbot arena: An open platform for evaluating llms by human preference.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Chatbot arena: An open platform for evaluating llms by human preference

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:31.757972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16812e59-4a34-4979-a196-8c672c4d8ea9 · outbound

This paper cites WebGPT: Browser-assisted question-answering with human feedback.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary WebGPT: Browser-assisted question-answering with human feedback

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:31.868564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25ade06b-4789-40c3-a681-cd6ab4084a6c · outbound

This paper cites Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:31.991836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 150a17bd-89d2-431a-a845-643f1bb027d4 · outbound

This paper cites Improve Mathematical Reasoning in Language Models by Automated Process Supervision.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Improve Mathematical Reasoning in Language Models by Automated Process Supervision

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:32.091323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0051497e-7fd1-4459-bdf7-3d22cd2c7d92 · outbound

This paper cites The Lessons of Developing Process Reward Models in Mathematical Reasoning.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary The Lessons of Developing Process Reward Models in Mathematical Reasoning

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:32.153438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99066ce0-bf66-45e2-bff9-babc6bf79869 · outbound

This paper cites Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:32.278911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7c2a574-043f-4123-b3fc-d777dbdac109 · outbound

This paper cites RRM: Robust reward model training mitigates reward hacking.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary RRM: Robust reward model training mitigates reward hacking

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.509788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 666bbd5d-4176-40a4-904b-9923fbbc7e61 · outbound

This paper cites Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:32.462708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa9054b3-3428-413d-b2ae-2c0022526db6 · outbound

This paper cites Inform: Mitigating reward hacking in rlhf via information-theoretic reward modeling.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Inform: Mitigating reward hacking in rlhf via information-theoretic reward modeling

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.497789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9a15a556-a843-4b42-99f9-210db24ee158 · outbound

This paper cites Convexity, classification, and risk bounds.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Convexity, classification, and risk bounds

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:32.639857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85d2ff92-4fe3-4ed2-9710-3c5df2a99dfa · outbound

This paper cites Fundamentals of statistical signal processing: estimation theory.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Fundamentals of statistical signal processing: estimation theory

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.476326Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e6a67e93-2552-4e32-97b0-f01c49869cd0 · outbound

This paper cites ARGS: Alignment as Reward-Guided Search.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary ARGS: Alignment as Reward-Guided Search

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:32.704726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b7b5efa-c7a1-4ef0-ad2d-3ba0f589c4ab · outbound

This paper cites Transformers: State- of-the-art natural language processing.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Transformers: State- of-the-art natural language processing

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:51:33.464271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers