Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation

• URL: http://arxiv.org/abs/2406.18676v2
• Date: Thu, 18 Jul 2024 08:28:09 GMT
• Title: Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation
• Authors: Guanting Dong, Yutao Zhu, Chenghao Zhang, Zechen Wang, Zhicheng Dou, Ji-Rong Wen,
• Abstract summary: 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.
• Score: 64.7982176398485
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Retrieval-augmented generation (RAG) has demonstrated effectiveness in mitigating the hallucination problem of large language models (LLMs). However, the difficulty of aligning the retriever with the diverse LLMs' knowledge preferences inevitably poses an inevitable challenge in developing a reliable RAG system. To address this issue, we propose DPA-RAG, a universal framework designed to align diverse knowledge preferences within RAG systems. Specifically, we initially introduce a preference knowledge construction pipline and incorporate five novel query augmentation strategies to alleviate preference data scarcity. Based on preference data, DPA-RAG accomplishes both external and internal preference alignment: 1) It jointly integrate pair-wise, point-wise, and contrastive preference alignment abilities into the reranker, achieving external preference alignment among RAG components. 2) It further introduces a pre-aligned stage before vanilla Supervised Fine-tuning (SFT), enabling LLMs to implicitly capture knowledge aligned with their reasoning preferences, achieving LLMs' internal alignment. Experimental results across four knowledge-intensive QA datasets demonstrate that DPA-RAG outperforms all baselines and seamlessly integrates both black-box and open-sourced LLM readers. Further qualitative analysis and discussions also provide empirical guidance for achieving reliable RAG systems. Our code is publicly available at https://github.com/dongguanting/DPA-RAG.

Related papers

• mR$^2$AG: Multimodal Retrieval-Reflection-Augmented Generation for Knowledge-Based VQA [78.45521005703958]
  multimodal Retrieval-Augmented Generation (mRAG) is naturally introduced to provide MLLMs with comprehensive and up-to-date knowledge. We propose a novel framework called textbfRetrieval-textbfReftextbfAugmented textbfGeneration (mR$2$AG) which achieves adaptive retrieval and useful information localization. mR$2$AG significantly outperforms state-of-the-art MLLMs on INFOSEEK and Encyclopedic-VQA
  arXiv  Detail & Related papers  (2024-11-22T16:15:50Z)
• Invar-RAG: Invariant LLM-aligned Retrieval for Better Generation [43.630437906898635]
  We propose a novel two-stage fine-tuning architecture called Invar-RAG. In the retrieval stage, an LLM-based retriever is constructed by integrating LoRA-based representation learning. In the generation stage, a refined fine-tuning method is employed to improve LLM accuracy in generating answers based on retrieved information.
  arXiv  Detail & Related papers  (2024-11-11T14:25:37Z)
• Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models [23.68266151581951]
  Retrieval-Augmented Generation (RAG) has been shown to enhance the factual accuracy of Large Language Models (LLMs) Existing methods often suffer from limited reasoning capabilities in effectively using the retrieved evidence. We introduce a novel framework, Open-RAG, designed to enhance reasoning capabilities in RAG with open-source LLMs.
  arXiv  Detail & Related papers  (2024-10-02T17:37:18Z)
• Intent Detection in the Age of LLMs [3.755082744150185]
  Intent detection is a critical component of task-oriented dialogue systems (TODS) Traditional approaches relied on computationally efficient supervised sentence transformer encoder models. The emergence of generative large language models (LLMs) with intrinsic world knowledge presents new opportunities to address these challenges.
  arXiv  Detail & Related papers  (2024-10-02T15:01:55Z)
• CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control [26.21425058462886]
  Retrieval-augmented generation (RAG) has emerged as a promising solution for mitigating hallucinations of large language models (LLMs) with retrieved external knowledge. We present the first attempts to solve adaptive RAG from a representation perspective and develop an inherent control-based framework, termed name. Experiments show that name is superior to existing adaptive RAG methods on a diverse set of tasks.
  arXiv  Detail & Related papers  (2024-05-29T03:17:16Z)
• Can large language models explore in-context? [87.49311128190143]
  We deploy Large Language Models as agents in simple multi-armed bandit environments. We find that the models do not robustly engage in exploration without substantial interventions.
  arXiv  Detail & Related papers  (2024-03-22T17:50:43Z)
• REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering [115.72130322143275]
  REAR is a RElevance-Aware Retrieval-augmented approach for open-domain question answering (QA) We develop a novel architecture for LLM-based RAG systems, by incorporating a specially designed assessment module. Experiments on four open-domain QA tasks show that REAR significantly outperforms previous a number of competitive RAG approaches.
  arXiv  Detail & Related papers  (2024-02-27T13:22:51Z)
• ActiveRAG: Autonomously Knowledge Assimilation and Accommodation through Retrieval-Augmented Agents [49.30553350788524]
  Retrieval-Augmented Generation (RAG) enables Large Language Models (LLMs) to leverage external knowledge. Existing RAG models often treat LLMs as passive recipients of information. We introduce ActiveRAG, a multi-agent framework that mimics human learning behavior.
  arXiv  Detail & Related papers  (2024-02-21T06:04:53Z)
• Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts [95.09994361995389]
  Relative Preference Optimization (RPO) is designed to discern between more and less preferred responses derived from both identical and related prompts. RPO has demonstrated a superior ability to align large language models with user preferences and to improve their adaptability during the training process.
  arXiv  Detail & Related papers  (2024-02-12T22:47:57Z)
• The Power of Noise: Redefining Retrieval for RAG Systems [19.387105120040157]
  Retrieval-Augmented Generation (RAG) has emerged as a method to extend beyond the pre-trained knowledge of Large Language Models. We focus on the type of passages IR systems within a RAG solution should retrieve.
  arXiv  Detail & Related papers  (2024-01-26T14:14:59Z)

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.