RMB: Comprehensively Benchmarking Reward Models in LLM Alignment
- URL: http://arxiv.org/abs/2410.09893v1
- Date: Sun, 13 Oct 2024 16:06:54 GMT
- Title: RMB: Comprehensively Benchmarking Reward Models in LLM Alignment
- Authors: Enyu Zhou, Guodong Zheng, Binghai Wang, Zhiheng Xi, Shihan Dou, Rong Bao, Wei Shen, Limao Xiong, Jessica Fan, Yurong Mou, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang,
- Abstract summary: Reward models (RMs) guide the alignment of large language models (LLMs)
We propose RMB, a comprehensive RM benchmark that covers over 49 real-world scenarios.
Based on our benchmark, we conduct extensive analysis on the state-of-the-art RMs.
- Score: 44.84304822376291
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Reward models (RMs) guide the alignment of large language models (LLMs), steering them toward behaviors preferred by humans. Evaluating RMs is the key to better aligning LLMs. However, the current evaluation of RMs may not directly correspond to their alignment performance due to the limited distribution of evaluation data and evaluation methods that are not closely related to alignment objectives. To address these limitations, we propose RMB, a comprehensive RM benchmark that covers over 49 real-world scenarios and includes both pairwise and Best-of-N (BoN) evaluations to better reflect the effectiveness of RMs in guiding alignment optimization. We demonstrate a positive correlation between our benchmark and the downstream alignment task performance. Based on our benchmark, we conduct extensive analysis on the state-of-the-art RMs, revealing their generalization defects that were not discovered by previous benchmarks, and highlighting the potential of generative RMs. Furthermore, we delve into open questions in reward models, specifically examining the effectiveness of majority voting for the evaluation of reward models and analyzing the impact factors of generative RMs, including the influence of evaluation criteria and instructing methods. Our evaluation code and datasets are available at https://github.com/Zhou-Zoey/RMB-Reward-Model-Benchmark.
Related papers
- The Lessons of Developing Process Reward Models in Mathematical Reasoning [62.165534879284735]
Process Reward Models (PRMs) aim to identify and mitigate intermediate errors in the reasoning processes.
We develop a consensus filtering mechanism that effectively integrates Monte Carlo (MC) estimation with Large Language Models (LLMs)
We release a new state-of-the-art PRM that outperforms existing open-source alternatives.
arXiv Detail & Related papers (2025-01-13T13:10:16Z) - RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment [18.491114307921848]
We propose RAG-RewardBench, the first benchmark for evaluating RMs in RAG settings.
First, we design four crucial and challenging RAG-specific scenarios to assess RMs.
Then, we incorporate 18 RAG subsets, six retrievers, and 24 RALMs to increase the diversity of data sources.
Finally, we adopt an LLM-as-a-judge approach to improve preference annotation efficiency and effectiveness.
arXiv Detail & Related papers (2024-12-18T11:28:05Z) - Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree? [46.396681032860414]
We investigate how differences in RM accuracy translate into gaps in optimized policy performance.
We recognize that accuracy, when used for measuring RM quality, can fail to fully capture the potential RM overoptimization.
arXiv Detail & Related papers (2024-10-08T00:52:03Z) - Revisiting BPR: A Replicability Study of a Common Recommender System Baseline [78.00363373925758]
We study the features of the BPR model, indicating their impact on its performance, and investigate open-source BPR implementations.
Our analysis reveals inconsistencies between these implementations and the original BPR paper, leading to a significant decrease in performance of up to 50% for specific implementations.
We show that the BPR model can achieve performance levels close to state-of-the-art methods on the top-n recommendation tasks and even outperform them on specific datasets.
arXiv Detail & Related papers (2024-09-21T18:39:53Z) - Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators [48.54465599914978]
Large Language Models (LLMs) have demonstrated promising capabilities as automatic evaluators in assessing the quality of generated natural language.
LLMs still exhibit biases in evaluation and often struggle to generate coherent evaluations that align with human assessments.
We introduce Pairwise-preference Search (PAIRS), an uncertainty-guided search-based rank aggregation method that employs LLMs to conduct pairwise comparisons locally and efficiently ranks candidate texts globally.
arXiv Detail & Related papers (2024-03-25T17:11:28Z) - Don't Make Your LLM an Evaluation Benchmark Cheater [142.24553056600627]
Large language models(LLMs) have greatly advanced the frontiers of artificial intelligence, attaining remarkable improvement in model capacity.
To assess the model performance, a typical approach is to construct evaluation benchmarks for measuring the ability level of LLMs.
We discuss the potential risk and impact of inappropriately using evaluation benchmarks and misleadingly interpreting the evaluation results.
arXiv Detail & Related papers (2023-11-03T14:59:54Z) - Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis,
and LLMs Evaluations [111.88727295707454]
This paper reexamines the research on out-of-distribution (OOD) robustness in the field of NLP.
We propose a benchmark construction protocol that ensures clear differentiation and challenging distribution shifts.
We conduct experiments on pre-trained language models for analysis and evaluation of OOD robustness.
arXiv Detail & Related papers (2023-06-07T17:47:03Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.