RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards
- URL: http://arxiv.org/abs/2410.13509v1
- Date: Thu, 17 Oct 2024 12:53:29 GMT
- Title: RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards
- Authors: Xinze Li, Sen Mei, Zhenghao Liu, Yukun Yan, Shuo Wang, Shi Yu, Zheni Zeng, Hao Chen, Ge Yu, Zhiyuan Liu, Maosong Sun, Chenyan Xiong,
- Abstract summary: Retrieval-Augmented Generation (RAG) has proven its effectiveness in mitigating hallucinations in Large Language Models (LLMs)
Current approaches use instruction tuning to optimize LLMs, improving their ability to utilize retrieved knowledge.
We propose a Differentiable Data Rewards ( DDR) method, which trains RAG systems by aligning data preferences between different RAG modules.
- Score: 78.74923079748521
- License:
- Abstract: Retrieval-Augmented Generation (RAG) has proven its effectiveness in mitigating hallucinations in Large Language Models (LLMs) by retrieving knowledge from external resources. To adapt LLMs for RAG pipelines, current approaches use instruction tuning to optimize LLMs, improving their ability to utilize retrieved knowledge. This supervised fine-tuning (SFT) approach focuses on equipping LLMs to handle diverse RAG tasks using different instructions. However, it trains RAG modules to overfit training signals and overlooks the varying data preferences among agents within the RAG system. In this paper, we propose a Differentiable Data Rewards (DDR) method, which end-to-end trains RAG systems by aligning data preferences between different RAG modules. DDR works by collecting the rewards to optimize each agent with a rollout method. This method prompts agents to sample some potential responses as perturbations, evaluates the impact of these perturbations on the whole RAG system, and subsequently optimizes the agent to produce outputs that improve the performance of the RAG system. Our experiments on various knowledge-intensive tasks demonstrate that DDR significantly outperforms the SFT method, particularly for LLMs with smaller-scale parameters that depend more on the retrieved knowledge. Additionally, DDR exhibits a stronger capability to align the data preference between RAG modules. The DDR method makes generation module more effective in extracting key information from documents and mitigating conflicts between parametric memory and external knowledge. All codes are available at https://github.com/OpenMatch/RAG-DDR.
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) - 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) - MARAGE: Transferable Multi-Model Adversarial Attack for Retrieval-Augmented Generation Data Extraction [6.917134562107388]
Retrieval-Augmented Generation (RAG) offers a solution to hallucinations in Large Language Models (LLMs) by grounding their outputs to knowledge retrieved from external sources.
Existing RAG extraction attacks often rely on manually crafted prompts, which limit their effectiveness.
We introduce a framework called MARAGE for optimizing an adversarial string that, when appended to user queries submitted to a target RAG system, causes outputs containing the retrieved RAG data.
arXiv Detail & Related papers (2025-02-05T00:17:01Z) - Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning [51.54046200512198]
Retrieval-augmented generation (RAG) is extensively utilized to incorporate external, current knowledge into large language models.
A standard RAG pipeline may comprise several components, such as query rewriting, document retrieval, document filtering, and answer generation.
To overcome these challenges, we propose treating the RAG pipeline as a multi-agent cooperative task, with each component regarded as an RL agent.
arXiv Detail & Related papers (2025-01-25T14:24:50Z) - RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions [25.952471869592443]
RAG-Instruct is a general method for synthesizing diverse and high-quality RAG instruction data based on any source corpus.
We construct a 40K instruction dataset from Wikipedia, comprehensively covering diverse RAG scenarios and tasks.
Experiments demonstrate that RAG-Instruct effectively enhances LLMs' RAG capabilities, achieving strong zero-shot performance.
arXiv Detail & Related papers (2024-12-31T09:00:51Z) - 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) - ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systems [2.8692611791027893]
Retrieval-Augmented Generation (RAG) systems generate inaccurate responses due to the retrieval of irrelevant or loosely related information.
We propose ChunkRAG, a framework that enhances RAG systems by evaluating and filtering retrieved information at the chunk level.
arXiv Detail & Related papers (2024-10-25T14:07:53Z) - LLMEmb: Large Language Model Can Be a Good Embedding Generator for Sequential Recommendation [57.49045064294086]
Large Language Model (LLM) has the ability to capture semantic relationships between items, independent of their popularity.
We introduce LLMEmb, a novel method leveraging LLM to generate item embeddings that enhance Sequential Recommender Systems (SRS) performance.
arXiv Detail & Related papers (2024-09-30T03:59:06Z) - Robust Implementation of Retrieval-Augmented Generation on Edge-based Computing-in-Memory Architectures [26.183960625493807]
Large Language Models (LLMs) deployed on edge devices learn through fine-tuning and updating a certain portion of their parameters.
Retrieval-Augmented Generation (RAG) is a resource-efficient LLM learning method.
We propose a novel framework to accelerate RAG via Computing-in-Memory (CiM) architectures.
arXiv Detail & Related papers (2024-05-07T22:31:50Z) - 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)
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.