Toward General Instruction-Following Alignment for Retrieval-Augmented Generation
- URL: http://arxiv.org/abs/2410.09584v1
- Date: Sat, 12 Oct 2024 16:30:51 GMT
- Title: Toward General Instruction-Following Alignment for Retrieval-Augmented Generation
- Authors: Guanting Dong, Xiaoshuai Song, Yutao Zhu, Runqi Qiao, Zhicheng Dou, Ji-Rong Wen,
- Abstract summary: Following natural instructions is crucial for the effective application of Retrieval-Augmented Generation (RAG) systems.
We propose VIF-RAG, the first automated, scalable, and verifiable synthetic pipeline for instruction-following alignment in RAG systems.
- Score: 63.611024451010316
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Following natural instructions is crucial for the effective application of Retrieval-Augmented Generation (RAG) systems. Despite recent advancements in Large Language Models (LLMs), research on assessing and improving instruction-following (IF) alignment within the RAG domain remains limited. To address this issue, we propose VIF-RAG, the first automated, scalable, and verifiable synthetic pipeline for instruction-following alignment in RAG systems. We start by manually crafting a minimal set of atomic instructions (<100) and developing combination rules to synthesize and verify complex instructions for a seed set. We then use supervised models for instruction rewriting while simultaneously generating code to automate the verification of instruction quality via a Python executor. Finally, we integrate these instructions with extensive RAG and general data samples, scaling up to a high-quality VIF-RAG-QA dataset (>100k) through automated processes. To further bridge the gap in instruction-following auto-evaluation for RAG systems, we introduce FollowRAG Benchmark, which includes approximately 3K test samples, covering 22 categories of general instruction constraints and four knowledge-intensive QA datasets. Due to its robust pipeline design, FollowRAG can seamlessly integrate with different RAG benchmarks. Using FollowRAG and eight widely-used IF and foundational abilities benchmarks for LLMs, we demonstrate that VIF-RAG markedly enhances LLM performance across a broad range of general instruction constraints while effectively leveraging its capabilities in RAG scenarios. Further analysis offers practical insights for achieving IF alignment in RAG systems. Our code and datasets are released at https://FollowRAG.github.io.
Related papers
- Chain-of-Retrieval Augmented Generation [72.06205327186069]
This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer.
Our proposed method, CoRAG, allows the model to dynamically reformulate the query based on the evolving state.
arXiv Detail & Related papers (2025-01-24T09:12:52Z) - 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) - OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain [62.89809156574998]
We introduce an omnidirectional and automatic RAG benchmark, OmniEval, in the financial domain.
Our benchmark is characterized by its multi-dimensional evaluation framework.
Our experiments demonstrate the comprehensiveness of OmniEval, which includes extensive test datasets.
arXiv Detail & Related papers (2024-12-17T15:38:42Z) - SFR-RAG: Towards Contextually Faithful LLMs [57.666165819196486]
Retrieval Augmented Generation (RAG) is a paradigm that integrates external contextual information with large language models (LLMs) to enhance factual accuracy and relevance.
We introduce SFR-RAG, a small LLM that is instruction-textual with an emphasis on context-grounded generation and hallucination.
We also present ConBench, a new evaluation framework compiling multiple popular and diverse RAG benchmarks.
arXiv Detail & Related papers (2024-09-16T01:08:18Z) - RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs [60.38044044203333]
Large language models (LLMs) typically utilize the top-k contexts from a retriever in retrieval-augmented generation (RAG)
We propose a novel instruction fine-tuning framework RankRAG, which instruction-tunes a single LLM for the dual purpose of context ranking and answer generation in RAG.
For generation, we compare our model with many strong baselines, including GPT-4-0613, GPT-4-turbo-2024-0409, and ChatQA-1.5, an open-sourced model with the state-of-the-art performance on RAG benchmarks.
arXiv Detail & Related papers (2024-07-02T17:59:17Z) - RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems [0.0]
Retrieval-Augmented Generation (RAG) has become a standard architectural pattern for domain-specific knowledge into user-facing chat applications.
We introduce RAGBench: the first comprehensive, large-scale RAG benchmark dataset of 100k examples.
We formalize the TRACe evaluation framework: a set of explainable and actionable RAG evaluation metrics applicable across all RAG domains.
arXiv Detail & Related papers (2024-06-25T20:23:15Z) - FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research [32.820100519805486]
FlashRAG is an efficient and modular open-source toolkit designed to assist researchers in reproducing existing RAG methods and in developing their own RAG algorithms within a unified framework.
Our toolkit has various features, including customizable modular framework, rich collection of pre-implemented RAG works, comprehensive datasets, efficient auxiliary pre-processing scripts, and extensive and standard evaluation metrics.
arXiv Detail & Related papers (2024-05-22T12:12:40Z) - Retrieval Augmented Generation Systems: Automatic Dataset Creation,
Evaluation and Boolean Agent Setup [5.464952345664292]
Retrieval Augmented Generation (RAG) systems have seen huge popularity in augmenting Large-Language Model (LLM) outputs with domain specific and time sensitive data.
In this paper we present a rigorous dataset creation and evaluation workflow to quantitatively compare different RAG strategies.
arXiv Detail & Related papers (2024-02-26T12:56:17Z) - CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models [49.16989035566899]
Retrieval-Augmented Generation (RAG) is a technique that enhances the capabilities of large language models (LLMs) by incorporating external knowledge sources.
This paper constructs a large-scale and more comprehensive benchmark, and evaluates all the components of RAG systems in various RAG application scenarios.
arXiv Detail & Related papers (2024-01-30T14:25:32Z)
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.