# CAFE: Retrieval Head-based Coarse-to-Fine Information Seeking to Enhance Multi-Document QA Capability

arXiv: https://arxiv.org/abs/2505.10063 · HTML: https://mlsanity.com/paper/2505.10063/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 41 references that are in the map.
- First posted on arXiv 15 May 2025.

## Builds on (most cited first, 30 of 32)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks](https://mlsanity.com/paper/2412.15204/) (2024)
- [∞Bench: Extending Long Context Evaluation Beyond 100K Tokens](https://mlsanity.com/paper/2402.13718/) (2024)
- [Effective Long-Context Scaling of Foundation Models](https://mlsanity.com/paper/2309.16039/) (2023)
- [DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads](https://mlsanity.com/paper/2410.10819/) (2024)
- [Retrieval Head Mechanistically Explains Long-Context Factuality](https://mlsanity.com/paper/2404.15574/) (2024)
- [Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention](https://mlsanity.com/paper/2404.07143/) (2024)
- [Data Engineering for Scaling Language Models to 128K Context](https://mlsanity.com/paper/2402.10171/) (2024)
- [Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA](https://mlsanity.com/paper/2406.17419/) (2024)
- [Make Your LLM Fully Utilize the Context](https://mlsanity.com/paper/2404.16811/) (2024)
- [RazorAttention: Efficient KV Cache Compression Through Retrieval Heads](https://mlsanity.com/paper/2407.15891/) (2024)
- [Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs](https://mlsanity.com/paper/2311.02262/) (2023)
- [Long-Context Language Modeling with Parallel Context Encoding](https://mlsanity.com/paper/2402.16617/) (2024)
- [RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement](https://mlsanity.com/paper/2412.12881/) (2024)
- [Large Language Models Can Self-Improve in Long-context Reasoning](https://mlsanity.com/paper/2411.08147/) (2024)
- [Making Long-Context Language Models Better Multi-Hop Reasoners](https://mlsanity.com/paper/2408.03246/) (2024)
- [ALR2: A Retrieve-then-Reason Framework for Long-context Question Answering](https://mlsanity.com/paper/2410.03227/) (2024)
- [DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations](https://mlsanity.com/paper/2410.18860/) (2024)
- [How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric Learning](https://mlsanity.com/paper/2402.02872/) (2024)
- [Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering](https://mlsanity.com/paper/2409.10790/) (2024)
- [HoPE: A Novel Positional Encoding Without Long-Term Decay for Enhanced Context Awareness and Extrapolation](https://mlsanity.com/paper/2410.21216/) (2024)
- [LongReD: Mitigating Short-Text Degradation of Long-Context Large Language Models via Restoration Distillation](https://mlsanity.com/paper/2502.07365/) (2025)

## Built on by (most cited first, 4 of 4)

- [Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs](https://mlsanity.com/paper/2508.14896/) (2025)
- [Position Bias Mitigates Position Bias:Mitigate Position Bias Through Inter-Position Knowledge Distillation](https://mlsanity.com/paper/2508.15709/) (2025)
- [Bridging External and Parametric Knowledge: Mitigating Hallucination of LLMs with Shared-Private Semantic Synergy in Dual-Stream Knowledge](https://mlsanity.com/paper/2506.06240/) (2025)
- [Beyond Memory Majority: Latent-Source Reasoning for Multi-Agent Memory Arbitration](https://mlsanity.com/paper/2608.19701/) (2026)

## Abstract (arXiv)

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 head 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 CAFE outperforms baselines, achieving up to 22.1% and 13.7% SubEM improvement over SFT and RAG methods on the Mistral model, respectively.