# Optimizing Multi-Hop Document Retrieval Through Intermediate Representations

arXiv: https://arxiv.org/abs/2503.04796 · HTML: https://mlsanity.com/paper/2503.04796/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 2 Mar 2025.

## Placed in

- Retrieval-augmented generation / [Knowledge-graph and structured-knowledge RAG](https://mlsanity.com/rag/knowledge-graph-and-structured-knowledge-rag/)

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity](https://mlsanity.com/paper/2403.14403/) (2024)
- [Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy](https://mlsanity.com/paper/2305.15294/) (2023)
- [Neural Networks and the Chomsky Hierarchy](https://mlsanity.com/paper/2207.02098/) (2022)
- [Not All Layers of LLMs Are Necessary During Inference](https://mlsanity.com/paper/2403.02181/) (2024)
- [Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization](https://mlsanity.com/paper/2405.15071/) (2024)
- [Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries](https://mlsanity.com/paper/2406.12775/) (2024)
- [Understanding Transformer Memorization Recall Through Idioms](https://mlsanity.com/paper/2210.03588/) (2022)
- [A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task](https://mlsanity.com/paper/2402.11917/) (2024)
- [How Much Can RAG Help the Reasoning of LLM?](https://mlsanity.com/paper/2410.02338/) (2024)
- [EfficientRAG: Efficient Retriever for Multi-Hop Question Answering](https://mlsanity.com/paper/2408.04259/) (2024)
- [Transformer-Based Models Are Not Yet Perfect At Learning to Emulate Structural Recursion](https://mlsanity.com/paper/2401.12947/) (2024)

## Built on by (most cited first, 5 of 5)

- [Do not Abstain! Identify and Solve the Uncertainty](https://mlsanity.com/paper/2506.00780/) (2025)
- [MeMo: Memory as a Model](https://mlsanity.com/paper/2605.15156/) (2026)
- [ILRe: Intermediate Layer Retrieval for Context Compression in Causal Language Models](https://mlsanity.com/paper/2508.17892/) (2025)
- [Probe, Don't Prompt: A Hidden-State Probe for Metadata Filtering in Multi-Meta-RAG](https://mlsanity.com/paper/2607.03929/) (2026)
- [W-RAG: Source-Aware Retrieval for Enterprise Document Generation from Heterogeneous Knowledge Bases](https://mlsanity.com/paper/2608.22081/) (2026)

## Abstract (arXiv)

Retrieval-augmented generation (RAG) encounters challenges when addressing complex queries, particularly multi-hop questions. While several methods tackle multi-hop queries by iteratively generating internal queries and retrieving external documents, these approaches are computationally expensive. In this paper, we identify a three-stage information processing pattern in LLMs during layer-by-layer reasoning, consisting of extraction, processing, and subsequent extraction steps. This observation suggests that the representations in intermediate layers contain richer information compared to those in other layers. Building on this insight, we propose Layer-wise RAG (L-RAG). Unlike prior methods that focus on generating new internal queries, L-RAG leverages intermediate representations from the middle layers, which capture next-hop information, to retrieve external knowledge. L-RAG achieves performance comparable to multi-step approaches while maintaining inference overhead similar to that of standard RAG. Experimental results show that L-RAG outperforms existing RAG methods on open-domain multi-hop question-answering datasets, including MuSiQue, HotpotQA, and 2WikiMultiHopQA. The code is available in https://github.com/Olive-2019/L-RAG