Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xu, Ran, Shi, Wenqi, Zhuang, Yuchen, Yu, Yue, Ho, Joyce C., Wang, Haoyu, Yang, Carl
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908305021992960
author Xu, Ran
Shi, Wenqi
Zhuang, Yuchen
Yu, Yue
Ho, Joyce C.
Wang, Haoyu
Yang, Carl
author_facet Xu, Ran
Shi, Wenqi
Zhuang, Yuchen
Yu, Yue
Ho, Joyce C.
Wang, Haoyu
Yang, Carl
contents Retrieval-Augmented Generation (RAG) systems often struggle to handle multi-hop question-answering tasks accurately due to irrelevant context retrieval and limited complex reasoning capabilities. We introduce Collab-RAG, a collaborative training framework that leverages mutual enhancement between a white-box small language model (SLM) and a blackbox large language model (LLM) for RAG. Specifically, the SLM decomposes complex queries into simpler sub-questions, thus enhancing the accuracy of the retrieval and facilitating more effective reasoning by the black-box LLM. Concurrently, the black-box LLM provides feedback signals to improve the SLM's decomposition capability. We observe that Collab-RAG relies solely on supervision from an affordable black-box LLM without additional distillation from frontier LLMs, yet demonstrates strong generalization across multiple black-box LLMs. Experimental evaluations across five multi-hop QA datasets demonstrate that Collab-RAG substantially outperforms existing black-box-only and SLM fine-tuning baselines by 1.8%-14.2% on average. In particular, our fine-tuned 3B SLM surpasses a frozen 32B LLM in question decomposition, highlighting the efficiency of Collab-RAG in improving reasoning and retrieval for complex questions. The code of Collab-RAG is available on https://github.com/ritaranx/Collab-RAG/.
format Preprint
id arxiv_https___arxiv_org_abs_2504_04915
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration
Xu, Ran
Shi, Wenqi
Zhuang, Yuchen
Yu, Yue
Ho, Joyce C.
Wang, Haoyu
Yang, Carl
Computation and Language
Artificial Intelligence
Information Retrieval
Machine Learning
Retrieval-Augmented Generation (RAG) systems often struggle to handle multi-hop question-answering tasks accurately due to irrelevant context retrieval and limited complex reasoning capabilities. We introduce Collab-RAG, a collaborative training framework that leverages mutual enhancement between a white-box small language model (SLM) and a blackbox large language model (LLM) for RAG. Specifically, the SLM decomposes complex queries into simpler sub-questions, thus enhancing the accuracy of the retrieval and facilitating more effective reasoning by the black-box LLM. Concurrently, the black-box LLM provides feedback signals to improve the SLM's decomposition capability. We observe that Collab-RAG relies solely on supervision from an affordable black-box LLM without additional distillation from frontier LLMs, yet demonstrates strong generalization across multiple black-box LLMs. Experimental evaluations across five multi-hop QA datasets demonstrate that Collab-RAG substantially outperforms existing black-box-only and SLM fine-tuning baselines by 1.8%-14.2% on average. In particular, our fine-tuned 3B SLM surpasses a frozen 32B LLM in question decomposition, highlighting the efficiency of Collab-RAG in improving reasoning and retrieval for complex questions. The code of Collab-RAG is available on https://github.com/ritaranx/Collab-RAG/.
title Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration
topic Computation and Language
Artificial Intelligence
Information Retrieval
Machine Learning
url https://arxiv.org/abs/2504.04915