| Autor: |
Cai, Tianchi, Tan, Zhiwen, Song, Xierui, Sun, Tao, Jiang, Jiyan, Xu, Yunqi, Zhang, Yinger, Gu, Jinjie |
| Rok vydání: |
2024 |
| Předmět: |
|
| Zdroj: |
KDD 2024 |
| Druh dokumentu: |
Working Paper |
| DOI: |
10.1145/3637528.3672065 |
| Popis: |
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. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
