Rethinking Diverse Human Preference Learning through Principal Component Analysis
Authors:
Open Access
- 1 January 2025
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 19857-19870
Abstract
Feng Luo, Rui Yang, Hao Sun, Chunyuan Deng, Jiarui Yao, Jingyan Shen, Huan Zhang, Hanjie Chen. Findings of the Association for Computational Linguistics: ACL 2025. 2025.Keywords
This publication has 13 references indexed in Scilit:
- RewardBench: Evaluating Reward Models for Language Modeling2025
- How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective2024
- Conditional Language Policy: A General Framework For Steerable Multi-Objective Finetuning2024
- Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts2024
- ChiMed-GPT: A Chinese Medical Large Language Model with Full Training Regime and Better Alignment to Human Preferences2024
- DMoERM: Recipes of Mixture-of-Experts for Effective Reward Modeling2024
- LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion2023
- Exploring Dimensionality Reduction Techniques in Multilingual TransformersCognitive Computation, 2022
- Asymptotic theory of sparse Bradley–Terry modelThe Annals of Applied Probability, 2020
- Rank Analysis of Incomplete Block Designs: A Method of Paired Comparisons Employing Unequal Repetitions on PairsBiometrics, 1960