2025.emnlp-main.655@ACL

Total: 1

#1 CAFE: Retrieval Head-based Coarse-to-Fine Information Seeking to Enhance Multi-Document QA Capability [PDF] [Copy] [Kimi] [REL]

Authors: Han Peng, Jinhao Jiang, Zican Dong, Xin Zhao, Lei Fang

Advancements in Large Language Models (LLMs) have extended their input context length, yet they still struggle with retrieval and reasoning in long-context inputs. Existing methods propose to utilize the prompt strategy and Retrieval-Augmented Generation (RAG) to alleviate this limitation. However, they still face challenges in balancing retrieval precision and recall, impacting their efficacy in answering questions. To address this, we introduce **CAFE**, a two-stage coarse-to-fine method to enhance multi-document question-answering capacities. By gradually eliminating the negative impacts of background and distracting documents, CAFE makes the responses more reliant on the evidence documents. Initially, a coarse-grained filtering method leverages retrieval heads to identify and rank relevant documents. Then, a fine-grained steering method guides attention to the most relevant content. Experiments across benchmarks show that CAFE outperforms baselines, achieving an average SubEM improvement of up to 22.1% and 13.7% over SFT and RAG methods, respectively, across three different models. Our code is available at https://github.com/RUCAIBox/CAFE.

Subject: EMNLP.2025 - Main