RewardBench: Evaluating Reward Models for Language Modeling
Authors:
- Nathan LambertNLNathan Lambert
- Valentina PyatkinVPValentina Pyatkin
- Lj MirandaLMLj Miranda
- Yejin ChoiYCYejin Choi
- Noah A. SmithNSNoah A. Smith
- Hannaneh HajishirziHHHannaneh Hajishirzi
Top Cited Papers
Open Access
- 1 January 2025
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 1755-1797
Abstract
Nathan Lambert, Valentina Pyatkin, Jacob Morrison, LJ Miranda, Bill Yuchen Lin, Khyathi Chandu, Nouha Dziri, Sachin Kumar, Tom Zick, Yejin Choi, Noah A. Smith, Hannaneh Hajishirzi. Findings of the Association for Computational Linguistics: NAACL 2025. 2025.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models2024
- Moral Foundations of Large Language Models2024
- KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models2024
- XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models2024
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model2023
- Fine-Grained Human Feedback Gives Better Rewards for Language Model Training2023
- QLoRA: Efficient Finetuning of Quantized LLMs2023
- AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback2023
- Towards Agile Text Classifiers for Everyone2023
- Training Language Models to Follow Instructions with Human Feedback2022