IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues
- URL: http://arxiv.org/abs/2405.13021v1
- Date: Wed, 15 May 2024 12:41:20 GMT
- Title: IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues
- Authors: Diji Yang, Jinmeng Rao, Kezhen Chen, Xiaoyuan Guo, Yawen Zhang, Jie Yang, Yi Zhang,
- Abstract summary: The IM-RAG approach integrates Information Retrieval systems with Large Language Models (LLMs) to support multi-round RAG.
The entire IM process is optimized via Reinforcement Learning (RL) where a Progress Tracker is incorporated to provide mid-step rewards.
The results show that our approach achieves state-of-the-art (SOTA) performance while providing high flexibility in integrating IR modules.
- Score: 10.280113107290067
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Although the Retrieval-Augmented Generation (RAG) paradigms can use external knowledge to enhance and ground the outputs of Large Language Models (LLMs) to mitigate generative hallucinations and static knowledge base problems, they still suffer from limited flexibility in adopting Information Retrieval (IR) systems with varying capabilities, constrained interpretability during the multi-round retrieval process, and a lack of end-to-end optimization. To address these challenges, we propose a novel LLM-centric approach, IM-RAG, that integrates IR systems with LLMs to support multi-round RAG through learning Inner Monologues (IM, i.e., the human inner voice that narrates one's thoughts). During the IM process, the LLM serves as the core reasoning model (i.e., Reasoner) to either propose queries to collect more information via the Retriever or to provide a final answer based on the conversational context. We also introduce a Refiner that improves the outputs from the Retriever, effectively bridging the gap between the Reasoner and IR modules with varying capabilities and fostering multi-round communications. The entire IM process is optimized via Reinforcement Learning (RL) where a Progress Tracker is incorporated to provide mid-step rewards, and the answer prediction is further separately optimized via Supervised Fine-Tuning (SFT). We conduct extensive experiments with the HotPotQA dataset, a popular benchmark for retrieval-based, multi-step question-answering. The results show that our approach achieves state-of-the-art (SOTA) performance while providing high flexibility in integrating IR modules as well as strong interpretability exhibited in the learned inner monologues.
Related papers
- mRAG: Elucidating the Design Space of Multi-modal Retrieval-Augmented Generation [5.647319807077936]
Large Vision-Language Models (LVLMs) have made remarkable strides in multimodal tasks such as visual question answering, visual grounding, and complex reasoning.<n>Retrieval-Augmented Generation (RAG) offers a practical solution to mitigate these challenges by allowing the LVLMs to access large-scale knowledge databases via retrieval mechanisms.
arXiv Detail & Related papers (2025-05-29T23:32:03Z) - Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers [74.17516978246152]
Large language models (LLMs) have been widely integrated into information retrieval to advance traditional techniques.<n>We propose EXSEARCH, an agentic search framework, where the LLM learns to retrieve useful information as the reasoning unfolds.<n>Experiments on four knowledge-intensive benchmarks show that EXSEARCH substantially outperforms baselines.
arXiv Detail & Related papers (2025-05-26T15:27:55Z) - MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering [57.156093929365255]
Gym-style framework for systematically reinforcement learning, evaluating, and improving autonomous large language model (LLM) agents.<n>MLE-Dojo covers diverse, open-ended MLE tasks carefully curated to reflect realistic engineering scenarios.<n>Its fully executable environment supports comprehensive agent training via both supervised fine-tuning and reinforcement learning.
arXiv Detail & Related papers (2025-05-12T17:35:43Z) - R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning [87.30285670315334]
textbfR1-Searcher is a novel two-stage outcome-based RL approach designed to enhance the search capabilities of Large Language Models.
Our framework relies exclusively on RL, without requiring process rewards or distillation for a cold start.
Our experiments demonstrate that our method significantly outperforms previous strong RAG methods, even when compared to the closed-source GPT-4o-mini.
arXiv Detail & Related papers (2025-03-07T17:14:44Z) - 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) - RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training [55.54020926284334]
Multimodal Large Language Models (MLLMs) have recently received substantial interest, which shows their emerging potential as general-purpose models for various vision-language tasks.
Retrieval augmentation techniques have proven to be effective plugins for both LLMs and MLLMs.
In this study, we propose multimodal adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training (RA-BLIP), a novel retrieval-augmented framework for various MLLMs.
arXiv Detail & Related papers (2024-10-18T03:45:19Z) - Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning [49.3242278912771]
We introduce a novel multimodal RAG framework named RMR (Retrieval Meets Reasoning)
The RMR framework employs a bi-modal retrieval module to identify the most relevant question-answer pairs.
It significantly boosts the performance of various vision-language models across a spectrum of benchmark datasets.
arXiv Detail & Related papers (2024-05-31T14:23:49Z) - Self-Retrieval: End-to-End Information Retrieval with One Large Language Model [97.71181484082663]
We introduce Self-Retrieval, a novel end-to-end LLM-driven information retrieval architecture.
Self-Retrieval internalizes the retrieval corpus through self-supervised learning, transforms the retrieval process into sequential passage generation, and performs relevance assessment for reranking.
arXiv Detail & Related papers (2024-02-23T18:45:35Z) - LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language
Models [56.25156596019168]
This paper introduces the LMRL-Gym benchmark for evaluating multi-turn RL for large language models (LLMs)
Our benchmark consists of 8 different language tasks, which require multiple rounds of language interaction and cover a range of tasks in open-ended dialogue and text games.
arXiv Detail & Related papers (2023-11-30T03:59:31Z) - MISAR: A Multimodal Instructional System with Augmented Reality [38.79160527414268]
Augmented reality (AR) requires seamless integration of visual, auditory, and linguistic channels for optimized human-computer interaction.
Our study introduces an innovative method harnessing large language models (LLMs) to assimilate information from visual, auditory, and contextual modalities.
arXiv Detail & Related papers (2023-10-18T04:15:12Z) - Large Language Models for Information Retrieval: A Survey [58.30439850203101]
Information retrieval has evolved from term-based methods to its integration with advanced neural models.
Recent research has sought to leverage large language models (LLMs) to improve IR systems.
We delve into the confluence of LLMs and IR systems, including crucial aspects such as query rewriters, retrievers, rerankers, and readers.
arXiv Detail & Related papers (2023-08-14T12:47:22Z) - 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)
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.