Towards Multi-Source Retrieval-Augmented Generation via Synergizing Reasoning and Preference-Driven Retrieval

• URL: http://arxiv.org/abs/2411.00689v1
• Date: Fri, 01 Nov 2024 15:50:58 GMT
• Title: Towards Multi-Source Retrieval-Augmented Generation via Synergizing Reasoning and Preference-Driven Retrieval
• Authors: Qingfei Zhao, Ruobing Wang, Xin Wang, Daren Zha, Nan Mu,
• Abstract summary: Existing Adaptive RAG (ARAG) systems struggle to effectively explore multiple retrieval sources due to their inability to select the right source at the right time. We propose a multi-source ARAG framework, termed MSPR, which synergizes reasoning and preference-driven retrieval to adaptive decide "when and what to retrieve" and "which retrieval source to use"
• Score: 4.862780562808097
• License:
• Abstract: Retrieval-Augmented Generation (RAG) has emerged as a reliable external knowledge augmentation technique to mitigate hallucination issues and parameterized knowledge limitations in Large Language Models (LLMs). Existing Adaptive RAG (ARAG) systems struggle to effectively explore multiple retrieval sources due to their inability to select the right source at the right time. To address this, we propose a multi-source ARAG framework, termed MSPR, which synergizes reasoning and preference-driven retrieval to adaptive decide "when and what to retrieve" and "which retrieval source to use". To better adapt to retrieval sources of differing characteristics, we also employ retrieval action adjustment and answer feedback strategy. They enable our framework to fully explore the high-quality primary source while supplementing it with secondary sources at the right time. Extensive and multi-dimensional experiments conducted on three datasets demonstrate the superiority and effectiveness of MSPR.

Related papers

• Optimizing Knowledge Integration in Retrieval-Augmented Generation with Self-Selection [72.92366526004464]
  Retrieval-Augmented Generation (RAG) has proven effective in enabling Large Language Models (LLMs) to produce more accurate and reliable responses. We propose a novel Self-Selection RAG framework, where the LLM is made to select from pairwise responses generated with internal parametric knowledge solely.
  arXiv  Detail & Related papers  (2025-02-10T04:29:36Z)
• DeepRAG: Thinking to Retrieval Step by Step for Large Language Models [92.87532210660456]
  We propose DeepRAG, a framework that models retrieval-augmented reasoning as a Markov Decision Process (MDP) By iteratively decomposing queries, DeepRAG dynamically determines whether to retrieve external knowledge or rely on parametric reasoning at each step. Experiments show that DeepRAG improves retrieval efficiency while improving answer accuracy by 21.99%, demonstrating its effectiveness in optimizing retrieval-augmented reasoning.
  arXiv  Detail & Related papers  (2025-02-03T08:22:45Z)
• RPO: Retrieval Preference Optimization for Robust Retrieval-Augmented Generation [33.85528514353727]
  We introduce the Retrieval Preference Optimization (RPO) to adaptively leverage multi-source knowledge based on retrieval relevance. RPO is the only RAG-dedicated alignment approach that quantifies the awareness of retrieval relevance in training. Experiments on four datasets demonstrate that RPO outperforms RAG by 4-10% in accuracy without any extra component.
  arXiv  Detail & Related papers  (2025-01-23T14:58:56Z)
• Retrieval-Augmented Generation with Estimation of Source Reliability [15.69681944254975]
  Reliability-Aware RAG (RA-RAG) estimates the reliability of multiple sources and incorporates this information into both retrieval and aggregation processes. We introduce a benchmark designed to reflect real-world scenarios with heterogeneous source reliability.
  arXiv  Detail & Related papers  (2024-10-30T12:09:29Z)
• Retriever-and-Memory: Towards Adaptive Note-Enhanced Retrieval-Augmented Generation [72.70046559930555]
  We propose a generic RAG approach called Adaptive Note-Enhanced RAG (Adaptive-Note) for complex QA tasks. Specifically, Adaptive-Note introduces an overarching view of knowledge growth, iteratively gathering new information in the form of notes. In addition, we employ an adaptive, note-based stop-exploration strategy to decide "what to retrieve and when to stop" to encourage sufficient knowledge exploration.
  arXiv  Detail & Related papers  (2024-10-11T14:03:29Z)
• MATTER: Memory-Augmented Transformer Using Heterogeneous Knowledge Sources [12.783393023641505]
  We introduce an efficient memory-augmented transformer called MATTER. MATTER retrieves and reads from both unstructured sources (paragraphs) and semi-structured sources (QA pairs) in the form of fixed-length neural memories. We demonstrate that our model outperforms existing efficient retrieval-augmented models on popular QA benchmarks in terms of both accuracy and speed.
  arXiv  Detail & Related papers  (2024-06-07T06:35:37Z)
• A Multi-Source Retrieval Question Answering Framework Based on RAG [3.731892340350648]
  This study proposes a method that replaces traditional retrievers with GPT-3.5. We also propose a web retrieval based method to implement fine-grained knowledge retrieval. In order to mitigate the illusion of GPT retrieval and reduce noise in Web retrieval,we proposes a multi-source retrieval framework, named MSRAG.
  arXiv  Detail & Related papers  (2024-05-29T15:47:57Z)
• Source Echo Chamber: Exploring the Escalation of Source Bias in User, Data, and Recommender System Feedback Loop [65.23044868332693]
  We investigate the impact of source bias on the realm of recommender systems. We show the prevalence of source bias and reveal a potential digital echo chamber with source bias amplification. We introduce a black-box debiasing method that maintains model impartiality towards both HGC and AIGC.
  arXiv  Detail & Related papers  (2024-05-28T09:34:50Z)
• Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue System [40.33178881317882]
  We propose the application of maximal marginal likelihood to train a perceptive retriever by utilizing signals from response generation for supervision. We evaluate our approach on three task-oriented dialogue datasets using T5 and ChatGPT as the backbone models.
  arXiv  Detail & Related papers  (2023-10-13T06:03:47Z)
• Synergistic Interplay between Search and Large Language Models for Information Retrieval [141.18083677333848]
  InteR allows RMs to expand knowledge in queries using LLM-generated knowledge collections. InteR achieves overall superior zero-shot retrieval performance compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-12T11:58:15Z)
• Resource Allocation via Model-Free Deep Learning in Free Space Optical Communications [119.81868223344173]
  The paper investigates the general problem of resource allocation for mitigating channel fading effects in Free Space Optical (FSO) communications. Under this framework, we propose two algorithms that solve FSO resource allocation problems.
  arXiv  Detail & Related papers  (2020-07-27T17:38:51Z)

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.