paper-with-me

홈 › Papers

FoRAG: Factuality-optimized Retrieval Augmented Generation for Web-enhanced Long-form Question Answering

2024-06-19 · Tianchi Cai, Zhiwen Tan, Xierui Song, Tao Sun, Jiyan Jiang, Yunqi Xu, Yinger Zhang, Jinjie Gu

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.

📄 PDF Abstract BibTeX arXiv:2406.13779

Code (0)

등록된 구현이 없습니다.

Tasks

Answer GenerationFormLong Form Question AnsweringQuestion AnsweringRAGRetrievalRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
WordPiece 설명 없음
Residual Connection 설명 없음
Weight Decay 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information Foraging

2025-05-14 · Hongjin Qian, Zheng Liu

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 Generation

Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection

2023-10-17 · Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil 외

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+2

Improving Factuality with Explicit Working Memory

2024-12-24 · Mingda Chen, Yang Li, Karthik Padthe, Rulin Shao 외

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+1

Provenance: A Light-weight Fact-checker for Retrieval Augmented LLM Generation Output

2024-11-01 · Hithesh Sankararaman, Mohammed Nasheed Yasin, Tanner Sorensen, Alessandro Di Bari 외

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+2

RAC: Efficient LLM Factuality Correction with Retrieval Augmentation

2024-10-21 · Changmao Li, Jeffrey Flanigan

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