RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment

• URL: http://arxiv.org/abs/2412.13746v1
• Date: Wed, 18 Dec 2024 11:28:05 GMT
• Title: RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment
• Authors: Zhuoran Jin, Hongbang Yuan, Tianyi Men, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao,
• Abstract summary: 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.
• Score: 18.491114307921848
• License:
• Abstract: Despite the significant progress made by existing retrieval augmented language models (RALMs) in providing trustworthy responses and grounding in reliable sources, they often overlook effective alignment with human preferences. In the alignment process, reward models (RMs) act as a crucial proxy for human values to guide optimization. However, it remains unclear how to evaluate and select a reliable RM for preference alignment in RALMs. To this end, 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, including multi-hop reasoning, fine-grained citation, appropriate abstain, and conflict robustness. 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, exhibiting a strong correlation with human annotations. Based on the RAG-RewardBench, we conduct a comprehensive evaluation of 45 RMs and uncover their limitations in RAG scenarios. Additionally, we also reveal that existing trained RALMs show almost no improvement in preference alignment, highlighting the need for a shift towards preference-aligned training.We release our benchmark and code publicly at https://huggingface.co/datasets/jinzhuoran/RAG-RewardBench/ for future work.

Related papers

• RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference Optimization [53.63439735067081]
  Large language models (LLMs) have achieved impressive performance but face high computational costs and latency. Retrieval-augmented generation (RAG) helps by integrating external knowledge, but imperfect retrieval can introduce distracting noise that misleads SLMs. We propose RoseRAG, a robust RAG framework for SLMs via Margin-aware Preference Optimization.
  arXiv  Detail & Related papers  (2025-02-16T04:56:53Z)
• RAG-Reward: Optimizing RAG with Reward Modeling and RLHF [8.911260109659489]
  Retrieval-augmented generation (RAG) enhances Large Language Models (LLMs) with relevant and up-to-date knowledge. The role of reward models in reinforcement learning for optimizing RAG remains underexplored. We introduce textbfRAG-Reward, a framework designed to develop reward models.
  arXiv  Detail & Related papers  (2025-01-22T22:59:19Z)
• RMB: Comprehensively Benchmarking Reward Models in LLM Alignment [44.84304822376291]
  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.
  arXiv  Detail & Related papers  (2024-10-13T16:06:54Z)
• Reward-RAG: Enhancing RAG with Reward Driven Supervision [43.66966457772646]
  We introduce Reward-RAG, a novel approach designed to enhance the Retrieval-Augmented Generation (RAG) model through Reward-Driven Supervision. Unlike previous RAG methodologies, our method adapts retrieval information to specific domains by employing CriticGPT to train a dedicated reward model. This reward model generates synthesized datasets for fine-tuning the RAG, aligning its outputs more closely with human preferences.
  arXiv  Detail & Related papers  (2024-10-03T15:26:50Z)
• Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems [18.926129063000264]
  RAG (Retrieval-Augmented Generation) have recently gained significant attention for their enhanced ability to integrate external knowledge sources. We propose a fairness evaluation framework tailored to RAG methods, using scenario-based questions and analyzing disparities across demographic attributes.
  arXiv  Detail & Related papers  (2024-09-29T22:04:26Z)
• RRM: Robust Reward Model Training Mitigates Reward Hacking [51.12341734942797]
  Reward models (RMs) play a pivotal role in aligning large language models with human preferences. We introduce a causal framework that learns preferences independent of these artifacts. Experiments show that our approach successfully filters out undesirable artifacts, yielding a more robust reward model.
  arXiv  Detail & Related papers  (2024-09-20T01:46:07Z)
• Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation [64.7982176398485]
  Retrieval-augmented generation (RAG) has demonstrated effectiveness in mitigating the hallucination problem of large language models (LLMs) We propose DPA-RAG, a universal framework designed to align diverse knowledge preferences within RAG systems.
  arXiv  Detail & Related papers  (2024-06-26T18:26:53Z)
• Pistis-RAG: Enhancing Retrieval-Augmented Generation with Human Feedback [41.88662700261036]
  RAG systems face limitations when semantic relevance alone does not guarantee improved generation quality. We propose Pistis-RAG, a new RAG framework designed with a content-centric approach to better align LLMs with human preferences.
  arXiv  Detail & Related papers  (2024-06-21T08:52:11Z)
• WARM: On the Benefits of Weight Averaged Reward Models [63.08179139233774]
  We propose Weight Averaged Reward Models (WARM) to mitigate reward hacking. Experiments on summarization tasks, using best-of-N and RL methods, shows that WARM improves the overall quality and alignment of LLM predictions.
  arXiv  Detail & Related papers  (2024-01-22T18:27:08Z)
• Confronting Reward Model Overoptimization with Constrained RLHF [114.71591361764547]
  We show that correlation between component RMs has a significant effect on the locations of these points. Our method addresses the problem of weighting component RMs by learning dynamic weights, naturally expressed by Lagrange multipliers.
  arXiv  Detail & Related papers  (2023-10-06T16:59:17Z)

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.