RaFe: Ranking Feedback Improves Query Rewriting for RAG
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916257611120640 |
|---|---|
| author | Mao, Shengyu Jiang, Yong Chen, Boli Li, Xiao Wang, Peng Wang, Xinyu Xie, Pengjun Huang, Fei Chen, Huajun Zhang, Ningyu |
| author_facet | Mao, Shengyu Jiang, Yong Chen, Boli Li, Xiao Wang, Peng Wang, Xinyu Xie, Pengjun Huang, Fei Chen, Huajun Zhang, Ningyu |
| contents | As Large Language Models (LLMs) and Retrieval Augmentation Generation (RAG) techniques have evolved, query rewriting has been widely incorporated into the RAG system for downstream tasks like open-domain QA. Many works have attempted to utilize small models with reinforcement learning rather than costly LLMs to improve query rewriting. However, current methods require annotations (e.g., labeled relevant documents or downstream answers) or predesigned rewards for feedback, which lack generalization, and fail to utilize signals tailored for query rewriting. In this paper, we propose ours, a framework for training query rewriting models free of annotations. By leveraging a publicly available reranker, ours~provides feedback aligned well with the rewriting objectives. Experimental results demonstrate that ours~can obtain better performance than baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_14431 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RaFe: Ranking Feedback Improves Query Rewriting for RAG Mao, Shengyu Jiang, Yong Chen, Boli Li, Xiao Wang, Peng Wang, Xinyu Xie, Pengjun Huang, Fei Chen, Huajun Zhang, Ningyu Computation and Language Artificial Intelligence Information Retrieval As Large Language Models (LLMs) and Retrieval Augmentation Generation (RAG) techniques have evolved, query rewriting has been widely incorporated into the RAG system for downstream tasks like open-domain QA. Many works have attempted to utilize small models with reinforcement learning rather than costly LLMs to improve query rewriting. However, current methods require annotations (e.g., labeled relevant documents or downstream answers) or predesigned rewards for feedback, which lack generalization, and fail to utilize signals tailored for query rewriting. In this paper, we propose ours, a framework for training query rewriting models free of annotations. By leveraging a publicly available reranker, ours~provides feedback aligned well with the rewriting objectives. Experimental results demonstrate that ours~can obtain better performance than baselines. |
| title | RaFe: Ranking Feedback Improves Query Rewriting for RAG |
| topic | Computation and Language Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2405.14431 |