FoRAG: Factuality-optimized Retrieval Augmented Generation for Web-enhanced Long-form Question Answering
Retrieval Augmented Generation (RAG) has become prevalent in question-answering (QA) tasks due to its ability of utilizing search engine to enhance the quality of long-form question-answering (LFQA). Despite the emergence of various open source methods and web-enhanced commercial systems such as Bing Chat, two critical problems remain unsolved, i.e., the lack of factuality and clear logic in the generated long-form answers. In this paper, we remedy these issues via a systematic study on answer generation in web-enhanced LFQA. Specifically, we first propose a novel outline-enhanced generator to achieve clear logic in the generation of multifaceted answers and construct two datasets accordingly. Then we propose a factuality optimization method based on a carefully designed doubly fine-grained RLHF framework, which contains automatic evaluation and reward modeling in different levels of granularity. Our generic framework comprises conventional fine-grained RLHF methods as special cases. Extensive experiments verify the superiority of our proposed \textit{Factuality-optimized RAG (FoRAG)} method on both English and Chinese benchmarks. In particular, when applying our method to Llama2-7B-chat, the derived model FoRAG-L-7B outperforms WebGPT-175B in terms of three commonly used metrics (i.e., coherence, helpfulness, and factuality), while the number of parameters is much smaller (only 1/24 of that of WebGPT-175B). Our datasets and models are made publicly available for better reproducibility: https://huggingface.co/forag.
Code (0)
등록된 구현이 없습니다.
Tasks
Answer GenerationFormLong Form Question AnsweringQuestion AnsweringRAGRetrievalRetrieval-augmented GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information Foraging
Augmenting large language models (LLMs) with external retrieval has become a standard method to address their inherent knowledge cutoff limitations. However, traditional retrieval-augmented generation methods employ stat…
Question AnsweringRetrievalRetrieval-augmented GenerationSelf-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
Despite their remarkable capabilities, large language models (LLMs) often produce responses containing factual inaccuracies due to their sole reliance on the parametric knowledge they encapsulate. Retrieval-Augmented Gen…
Fact VerificationQuestion AnsweringRAGResponse Generation+2Improving Factuality with Explicit Working Memory
Large language models can generate factually inaccurate content, a problem known as hallucination. Recent works have built upon retrieved-augmented generation to improve factuality through iterative prompting but these m…
Fact CheckingHallucinationRAGRetrieval+1Provenance: A Light-weight Fact-checker for Retrieval Augmented LLM Generation Output
We present a light-weight approach for detecting nonfactual outputs from retrieval-augmented generation (RAG). Given a context and putative output, we compute a factuality score that can be thresholded to yield a binary …
Fact CheckingNatural Language InferenceQuestion AnsweringRAG+2RAC: Efficient LLM Factuality Correction with Retrieval Augmentation
Large Language Models (LLMs) exhibit impressive results across a wide range of natural language processing (NLP) tasks, yet they can often produce factually incorrect outputs. This paper introduces a simple but effective…
RAGRetrievalRetrieval-augmented Generation