Pairwise Calibrated Rewards for Pluralistic Alignment | Paper Citation Record

Observation 9cdf6fb2-6d4c-4115-b73a-32811ad29ac8 · outbound

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

Pairwise Calibrated Rewards for Pluralistic Alignment Training language models to follow instructions with human feedback

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.689640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70ba490e-66da-4f4c-94ce-725d94732517 · outbound

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

Pairwise Calibrated Rewards for Pluralistic Alignment Rank analysis of incomplete block designs: I

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.695097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7339a956-a618-4df3-a86c-75a82bd18d73 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Pairwise Calibrated Rewards for Pluralistic Alignment Constitutional AI: Harmlessness from AI Feedback

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.699662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa172a58-b6f2-454d-9fa6-f9d2ed86ca38 · outbound

This paper cites Ethical and social risks of harm from Language Models.

Pairwise Calibrated Rewards for Pluralistic Alignment Ethical and social risks of harm from Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.704781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e94affd-2d2d-4e06-9a65-da62c82a8978 · outbound

This paper cites Cultural palette: Pluralising culture alignment via multi-agent palette.

Pairwise Calibrated Rewards for Pluralistic Alignment Cultural palette: Pluralising culture alignment via multi-agent palette

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.709515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 639f046c-d067-47ec-9a8f-b984512cebb2 · outbound

This paper cites Cultural Incongruencies in Artificial Intelligence.

Pairwise Calibrated Rewards for Pluralistic Alignment Cultural Incongruencies in Artificial Intelligence

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.714150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e35e37ad-505c-43c1-8864-953fa84eed69 · outbound

This paper cites Foundational Challenges in Assuring Alignment and Safety of Large Language Models.

Pairwise Calibrated Rewards for Pluralistic Alignment Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.719440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce06337d-3332-4314-8b87-ac1269f7ba0a · outbound

This paper cites The PRISM alignment dataset: What participatory, representative and individualised human feedback reveals about the subjective and multicultural alignment of large language models.

Pairwise Calibrated Rewards for Pluralistic Alignment The PRISM alignment dataset: What participatory, representative and individualised human feedback reveals about the subjective and multicultural alignment of large language models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.724303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92a32861-6fb7-4f05-a88e-408eb1c934f7 · outbound

This paper cites MaxMin-RLHF: Alignment with Diverse Human Preferences.

Pairwise Calibrated Rewards for Pluralistic Alignment MaxMin-RLHF: Alignment with Diverse Human Preferences

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.728783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fdacdc4-d048-4817-bd2c-0e4a07642ded · outbound

This paper cites Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback.

Pairwise Calibrated Rewards for Pluralistic Alignment Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.734382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9f14b31-9c5f-464e-b28d-dcc493fa7fa7 · outbound

This paper cites Whose opinions do language models reflect? InProceedings of the 40th In- ternational Conference on Machine Learning (ICML), pages 29971–30004, 2023.

Pairwise Calibrated Rewards for Pluralistic Alignment Whose opinions do language models reflect? InProceedings of the 40th In- ternational Conference on Machine Learning (ICML), pages 29971–30004, 2023

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.739314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acf8846c-cc79-4603-b4c0-09a3af831728 · outbound

This paper cites Discovering Language Model Behaviors with Model-Written Evaluations.

Pairwise Calibrated Rewards for Pluralistic Alignment Discovering Language Model Behaviors with Model-Written Evaluations

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.743851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14c9880d-6b35-4781-ba18-26cdf04987b8 · outbound

This paper cites Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback.

Pairwise Calibrated Rewards for Pluralistic Alignment Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.748505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35151b6b-0437-41c1-849f-371af5026d5b · outbound

This paper cites Diverse preference learning for capabilities and alignment.

Pairwise Calibrated Rewards for Pluralistic Alignment Diverse preference learning for capabilities and alignment

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.753507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3af7a9e5-cea5-48c3-8f64-16e7292dfe43 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Pairwise Calibrated Rewards for Pluralistic Alignment Proximal Policy Optimization Algorithms

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.757851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 159f1a61-bbf6-4644-be8a-f63f2547f41a · outbound

This paper cites On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization.

Pairwise Calibrated Rewards for Pluralistic Alignment On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.762381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d13e0bd2-1a64-44d7-be10-88ee55e94d7d · outbound

This paper cites Evaluating the diversity and quality of LLM generated content.

Pairwise Calibrated Rewards for Pluralistic Alignment Evaluating the diversity and quality of LLM generated content

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.767496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ba3f9d5-8324-4c5f-a78c-d5bb1821f2f2 · outbound

This paper cites From Distributional to Overton Pluralism: Investigating Large Language Model Alignment.

Pairwise Calibrated Rewards for Pluralistic Alignment From Distributional to Overton Pluralism: Investigating Large Language Model Alignment

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-08-15T20:48:02.598897Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 68c4f98c-df94-4fab-8410-6d339079d768 · outbound

This paper cites Understanding the Effects of RLHF on LLM Generalisation and Diversity.

Pairwise Calibrated Rewards for Pluralistic Alignment Understanding the Effects of RLHF on LLM Generalisation and Diversity

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.776628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e10d18e0-7a0d-4760-b54c-eeff2e81da64 · outbound

This paper cites A distributional approach to con- trolled text generation.

Pairwise Calibrated Rewards for Pluralistic Alignment A distributional approach to con- trolled text generation

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.481429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 71fe6e7a-cebc-475c-aadb-d437e6ea5d12 · outbound

This paper cites Red Teaming Language Models with Language Models.

Pairwise Calibrated Rewards for Pluralistic Alignment Red Teaming Language Models with Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.785525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a83cf32-3f50-49fd-b428-a28cf50605b0 · outbound

This paper cites Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration.

Pairwise Calibrated Rewards for Pluralistic Alignment Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.790093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9a889e0-599c-4e59-93fe-719449655e14 · outbound

This paper cites A Roadmap to Pluralistic Alignment.

Pairwise Calibrated Rewards for Pluralistic Alignment A Roadmap to Pluralistic Alignment

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.795036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9afab7f9-7422-4192-9331-2eaeca87a3f1 · outbound

This paper cites RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation.

Pairwise Calibrated Rewards for Pluralistic Alignment RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.799802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f8c0b98-8283-40b6-9c97-c04c0b0df8ff · outbound

This paper cites Pal: Pluralistic align- ment framework for learning from heterogeneous preferences.

Pairwise Calibrated Rewards for Pluralistic Alignment Pal: Pluralistic align- ment framework for learning from heterogeneous preferences

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.465858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 63db3e0f-edad-4f23-b2da-10a5d65cdd18 · outbound

This paper cites Value profiles for encoding human variation.

Pairwise Calibrated Rewards for Pluralistic Alignment Value profiles for encoding human variation

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.809500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86f24656-82b8-4d5b-a69d-ab27df243774 · outbound

This paper cites Aligning language models to user opinions.

Pairwise Calibrated Rewards for Pluralistic Alignment Aligning language models to user opinions

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.450858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a0784958-be4e-4247-9404-df337da1a635 · outbound

This paper cites PERSONA: A Reproducible Testbed for Pluralistic Alignment.

Pairwise Calibrated Rewards for Pluralistic Alignment PERSONA: A Reproducible Testbed for Pluralistic Alignment

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.818699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 698c0fc2-e1ef-4d14-99e0-89377ea61f82 · outbound

This paper cites Position: Social choice should guide AI alignment in dealing with diverse human feedback.

Pairwise Calibrated Rewards for Pluralistic Alignment Position: Social choice should guide AI alignment in dealing with diverse human feedback

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.435220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 86a81d0f-acb5-4f2f-a64a-521805225db2 · outbound

This paper cites AI Alignment and Social Choice: Fundamental Limitations and Policy Implications.

Pairwise Calibrated Rewards for Pluralistic Alignment AI Alignment and Social Choice: Fundamental Limitations and Policy Implications

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.828061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56eddf10-da18-4237-864c-a12fde9743d9 · outbound

This paper cites Rewarded soups: towards Pareto-optimal alignment by inter- polating weights fine-tuned on diverse rewards.

Pairwise Calibrated Rewards for Pluralistic Alignment Rewarded soups: towards Pareto-optimal alignment by inter- polating weights fine-tuned on diverse rewards

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.419841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ae4a6ea4-8b0c-47e2-8838-33d4382ea6f5 · outbound

This paper cites Axioms for AI alignment from human feedback.

Pairwise Calibrated Rewards for Pluralistic Alignment Axioms for AI alignment from human feedback

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.404613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 29803dee-02c0-4edb-9639-44868b298edc · outbound

This paper cites MallowsPO: Fine-Tune Your LLM with Preference Dispersions.

Pairwise Calibrated Rewards for Pluralistic Alignment MallowsPO: Fine-Tune Your LLM with Preference Dispersions

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.841780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 785ee3d6-2cdb-4148-ae12-22e73a41099a · outbound

This paper cites Adaptive preference scaling for reinforcement learning with human feedback.Advances in Neural Information Processing Systems, 37:107249–107269, 2024.

Pairwise Calibrated Rewards for Pluralistic Alignment Adaptive preference scaling for reinforcement learning with human feedback.Advances in Neural Information Processing Systems, 37:107249–107269, 2024

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.389516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 75bbd463-a625-4d0f-9820-c32a7ecf21a8 · outbound

This paper cites Aligning language models with human preferences via a Bayesian approach.Advances in Neural Information Processing Systems, 36:49113–49132, 2023.

Pairwise Calibrated Rewards for Pluralistic Alignment Aligning language models with human preferences via a Bayesian approach.Advances in Neural Information Processing Systems, 36:49113–49132, 2023

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.375202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 03485a93-87f0-4c0d-9417-abe1c126be11 · outbound

This paper cites Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning.

Pairwise Calibrated Rewards for Pluralistic Alignment Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.856173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dab271b-b97c-45a1-9e9e-b1aaac5e938e · outbound

This paper cites Direct Alignment with Heterogeneous Preferences.

Pairwise Calibrated Rewards for Pluralistic Alignment Direct Alignment with Heterogeneous Preferences

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.861096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49435cce-d04d-408b-81a5-bc3dc7da52f0 · outbound

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

Pairwise Calibrated Rewards for Pluralistic Alignment Distributional preference learning: Understanding and accounting for hidden context in RLHF

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.359673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation affd01f2-7976-46e7-b9b2-8b12efb51183 · outbound

This paper cites Clone-robust AI alignment.

Pairwise Calibrated Rewards for Pluralistic Alignment Clone-robust AI alignment

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.344695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e95f78dc-4ad8-4b15-ba12-ff7ecfc780b4 · outbound

This paper cites Fine-tuning language models to find agreement among humans with diverse preferences.

Pairwise Calibrated Rewards for Pluralistic Alignment Fine-tuning language models to find agreement among humans with diverse preferences

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.330247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8d68ede3-4ed2-489e-99ac-ef9682074c62 · outbound

This paper cites Generative social choice.

Pairwise Calibrated Rewards for Pluralistic Alignment Generative social choice

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.314894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation efc9fa8e-acb6-4e16-97a0-f4712cbfc0ca · outbound

This paper cites Cambridge University Press, 2016.

Pairwise Calibrated Rewards for Pluralistic Alignment Cambridge University Press, 2016

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.299791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 253a9dc8-2cd6-4250-89ac-a830d7207e8e · outbound

This paper cites The MIT Press, 2012.

Pairwise Calibrated Rewards for Pluralistic Alignment The MIT Press, 2012

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.283693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ec96dc32-8717-49ca-af32-fc5850bab84c · outbound

This paper cites Friedman.The Elements of Statistical Learning: Data Mining, Inference, and Prediction.

Pairwise Calibrated Rewards for Pluralistic Alignment Friedman.The Elements of Statistical Learning: Data Mining, Inference, and Prediction

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.267712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fd56e2fd-a61f-438f-ba76-c7cc5bb8fbbc · outbound

This paper cites The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values.

Pairwise Calibrated Rewards for Pluralistic Alignment The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.897987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 227dcb78-9b0b-4339-a040-acbd71f33b58 · outbound

This paper cites Zhang, Xinyi Chen, Qiuyi Zhang, Rajesh Ranganath, and Kyunghyun Cho.

Pairwise Calibrated Rewards for Pluralistic Alignment Zhang, Xinyi Chen, Qiuyi Zhang, Rajesh Ranganath, and Kyunghyun Cho

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.251842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5c7c0e2d-2551-49a5-865e-9f608fd4fdad · outbound

This paper cites Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback.

Pairwise Calibrated Rewards for Pluralistic Alignment Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-08-15T20:48:02.354507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1280f3ce-1fdc-400d-b91c-575810737842 · outbound

This paper cites The History and Risks of Reinforcement Learning and Human Feedback.

Pairwise Calibrated Rewards for Pluralistic Alignment The History and Risks of Reinforcement Learning and Human Feedback

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.912071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d49b89c-d001-4ec0-9d58-7f6cb594d343 · outbound

This paper cites Online, 2024.

Pairwise Calibrated Rewards for Pluralistic Alignment Online, 2024

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.235927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fa6e8956-26d6-4f30-8159-29adfa2adbac · outbound

This paper cites On Releasing Annotator-Level Labels and Information in Datasets.

Pairwise Calibrated Rewards for Pluralistic Alignment On Releasing Annotator-Level Labels and Information in Datasets

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.921683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5077209-3c03-4eb2-bb8c-524b12307462 · outbound

This paper cites Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned.

Pairwise Calibrated Rewards for Pluralistic Alignment Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.926116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89f27be0-ed2b-4887-ae0f-e240261f9f85 · outbound

This paper cites Learning to summarize with human feedback.

Pairwise Calibrated Rewards for Pluralistic Alignment Learning to summarize with human feedback

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.218381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2d899908-36cb-4678-90c9-69fdc6380333 · outbound

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

Pairwise Calibrated Rewards for Pluralistic Alignment Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.935483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09229ffe-71b9-4f64-aee0-fd9c39e28639 · outbound

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

Pairwise Calibrated Rewards for Pluralistic Alignment Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.940245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 935f7d17-e601-4d86-abb9-3b473bba900a · outbound

This paper cites When does label smoothing help? InProceedings of the 32th Annual Conference on Neural Information Processing Systems (NeurIPS), 2019.

Pairwise Calibrated Rewards for Pluralistic Alignment When does label smoothing help? InProceedings of the 32th Annual Conference on Neural Information Processing Systems (NeurIPS), 2019

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.202026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0b0cd5c5-7278-4c5a-a7b3-0ea7ca8dfc02 · outbound

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

Pairwise Calibrated Rewards for Pluralistic Alignment Secrets of RLHF in Large Language Models Part II: Reward Modeling

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.949682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4290753-758c-4db0-b810-38f60de5c556 · outbound

This paper cites VPO: Leveraging the Number of Votes in Preference Optimization.

Pairwise Calibrated Rewards for Pluralistic Alignment VPO: Leveraging the Number of Votes in Preference Optimization

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-08-15T20:48:02.247236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7e1630d4-f7ad-49d5-bdd7-30ffd41f5755 · outbound

This paper cites Geometric-averaged preference optimization for soft preference labels.

Pairwise Calibrated Rewards for Pluralistic Alignment Geometric-averaged preference optimization for soft preference labels

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.186002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9489babc-f28a-4ba8-9f63-5fdaf4df6797 · outbound

This paper cites Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback.

Pairwise Calibrated Rewards for Pluralistic Alignment Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.963857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae0386f0-5bc1-4fcc-981f-322624dadc21 · outbound

This paper cites PersonalLLM: Tailoring LLMs to Individual Preferences.

Pairwise Calibrated Rewards for Pluralistic Alignment PersonalLLM: Tailoring LLMs to Individual Preferences

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.968836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 977e5d76-02ea-4199-9eea-5075d5515872 · outbound

This paper cites HelpSteer2: Open-source dataset for training top-performing reward models.

Pairwise Calibrated Rewards for Pluralistic Alignment HelpSteer2: Open-source dataset for training top-performing reward models

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.973467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b831d82-e439-4a7f-a594-3ffc7e19ef5e · outbound

This paper cites Ziegler, Ryan Lowe, Chelsea V oss, Alec Radford, Dario Amodei, and Paul Christiano.

Pairwise Calibrated Rewards for Pluralistic Alignment Ziegler, Ryan Lowe, Chelsea V oss, Alec Radford, Dario Amodei, and Paul Christiano

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.170230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1a43929c-4b10-478c-9bb4-17050343fb79 · outbound

This paper cites Llama 3 model card.

Pairwise Calibrated Rewards for Pluralistic Alignment Llama 3 model card

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.155048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7d242f85-8224-4cb8-b5b5-69003d1fa0bb · outbound

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

Pairwise Calibrated Rewards for Pluralistic Alignment WebGPT: Browser-assisted question-answering with human feedback

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.987206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 125a6178-0df6-44a6-8aba-c00ee0216d30 · outbound

This paper cites BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling.

Pairwise Calibrated Rewards for Pluralistic Alignment BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.991898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4bb9d17-40af-40bb-a3d9-8b1a3eb06701 · outbound

This paper cites A new measure of rank correlation.Biometrika, 30(1-2):81–93, 1938.

Pairwise Calibrated Rewards for Pluralistic Alignment A new measure of rank correlation.Biometrika, 30(1-2):81–93, 1938

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:01.996627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bb58212-792b-4008-9560-0ac9960e6996 · outbound

This paper cites Evaluating and inducing personality in pre-trained language models.

Pairwise Calibrated Rewards for Pluralistic Alignment Evaluating and inducing personality in pre-trained language models

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.130677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation eab3280e-fed5-450a-a9fd-8f7d7dc2f91d · outbound

This paper cites Survey of Cultural Awareness in Language Models: Text and Beyond.

Pairwise Calibrated Rewards for Pluralistic Alignment Survey of Cultural Awareness in Language Models: Text and Beyond

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:02.005763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42924a0b-aa6d-49a7-87f2-6afe057c1754 · outbound

This paper cites Randomness, Not Representation: The Unreliability of Evaluating Cultural Alignment in LLMs.

Pairwise Calibrated Rewards for Pluralistic Alignment Randomness, Not Representation: The Unreliability of Evaluating Cultural Alignment in LLMs

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:02.010384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 219c5de3-053a-42a4-8c06-6472c7dd5526 · outbound

This paper cites Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning.

Pairwise Calibrated Rewards for Pluralistic Alignment Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:02.015013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bca116a-dbfc-47a5-be7d-3a1b2742e3bd · outbound

This paper cites ¨Uber den variabilit ¨atsbereich der fourier’schen konstanten von positiven harmonischen funktionen.Rendiconti Del Circolo Matematico di Palermo (1884- 1940), 32(1):193–217, 1911.

Pairwise Calibrated Rewards for Pluralistic Alignment ¨Uber den variabilit ¨atsbereich der fourier’schen konstanten von positiven harmonischen funktionen.Rendiconti Del Circolo Matematico di Palermo (1884- 1940), 32(1):193–217, 1911

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.114625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d4454f1c-08e2-4ab3-9a8c-4e74cd6b6bc0 · outbound

This paper cites On the computational complexity of combinatorial problems.Networks, 5(1): 45–68, 1975.

Pairwise Calibrated Rewards for Pluralistic Alignment On the computational complexity of combinatorial problems.Networks, 5(1): 45–68, 1975

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.099723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 61349d3d-2ccb-49a0-acf2-c57b5db02030 · outbound

This paper cites Springer, 1988.

Pairwise Calibrated Rewards for Pluralistic Alignment Springer, 1988

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.085389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2b126805-a43a-40c7-bfbf-a4e9d037ac9c · outbound

This paper cites A theorem on the construction of voting paradoxes.Econometrica: Journal of the Econometric Society, pages 608–610, 1953.

Pairwise Calibrated Rewards for Pluralistic Alignment A theorem on the construction of voting paradoxes.Econometrica: Journal of the Econometric Society, pages 608–610, 1953

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:02.033787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e92c2591-2c5b-452f-a0f1-814ff55e3acb · outbound

This paper cites On the density of families of sets.Journal of Combinatorial Theory, Series A, 13(1):145–147, 1972.

Pairwise Calibrated Rewards for Pluralistic Alignment On the density of families of sets.Journal of Combinatorial Theory, Series A, 13(1):145–147, 1972

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.061482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 24962625-be95-4749-989a-69639c7ae85e · outbound

This paper cites Cambridge university press, 2014.

Pairwise Calibrated Rewards for Pluralistic Alignment Cambridge university press, 2014

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.047246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5dea04a9-bb1e-4647-a07c-a150c74e8629 · outbound

This paper cites Soap: Improving and stabilizing Shampoo using Adam.

Pairwise Calibrated Rewards for Pluralistic Alignment Soap: Improving and stabilizing Shampoo using Adam

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.032510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e2144797-bb48-4d96-9e3c-7fe1258269d2 · outbound

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

Pairwise Calibrated Rewards for Pluralistic Alignment Training language models to follow instructions with human feedback

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.017495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 98fe6b40-1563-4a90-aae7-40c68b68f360 · outbound

This paper cites Iterative data smoothing: Mitigating reward overfitting and overoptimization in RLHF.

Pairwise Calibrated Rewards for Pluralistic Alignment Iterative data smoothing: Mitigating reward overfitting and overoptimization in RLHF

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:03.002969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b4386d4c-eca6-4938-8944-e103e636dfe9 · outbound

This paper cites echo chambers,.

Pairwise Calibrated Rewards for Pluralistic Alignment echo chambers,

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:02.987514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0ee4aab4-3054-40a1-a8ac-84908bf2e539 · outbound

This paper cites We index xθ by pairsij withi<j , wherexθ ij =1[r θ(yi)≥r θ(yj)].

Pairwise Calibrated Rewards for Pluralistic Alignment We index xθ by pairsij withi<j , wherexθ ij =1[r θ(yi)≥r θ(yj)]

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:02.971244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5477df53-3d9c-4e1d-82a5-2a8f015b7584 · outbound

This paper cites disagreement score.

Pairwise Calibrated Rewards for Pluralistic Alignment disagreement score

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:02.955553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 44581390-4dd0-4177-8235-d6a148669929 · outbound

This paper cites Fix m points (z1,t 1),...,(z m,tm).

Pairwise Calibrated Rewards for Pluralistic Alignment Fix m points (z1,t 1),...,(z m,tm)

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:02.940766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a9c24194-7c3e-4518-8801-a976b1ac980b · outbound

This paper cites IfF 2 pseudo-shatters ((z1,y 1),t 1),...,((z m,ym),tm), thenF 1 pseudo-shatters (z1,t 1−y 1),...,(z m,tm−ym), implying that the pseudo-dimension ofF 2 is at most that ofF 1.

Pairwise Calibrated Rewards for Pluralistic Alignment IfF 2 pseudo-shatters ((z1,y 1),t 1),...,((z m,ym),tm), thenF 1 pseudo-shatters (z1,t 1−y 1),...,(z m,tm−ym), implying that the pseudo-dimension ofF 2 is at most that ofF 1

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:02.924732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 61edd47a-c44e-42a5-aed8-c9fe362532b1 · outbound

This paper cites overall” preference. In our experiments, we specifically use the “overall.

Pairwise Calibrated Rewards for Pluralistic Alignment overall” preference. In our experiments, we specifically use the “overall

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:02.908571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers