Saved in:
Bibliographic Details
Main Authors: Li, Junchen, Wang, Rongzheng, Huang, Yihong, Chen, Qizhi, Zhang, Jiasheng, Liang, Shuang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.14096
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911273616146432
author Li, Junchen
Wang, Rongzheng
Huang, Yihong
Chen, Qizhi
Zhang, Jiasheng
Liang, Shuang
author_facet Li, Junchen
Wang, Rongzheng
Huang, Yihong
Chen, Qizhi
Zhang, Jiasheng
Liang, Shuang
contents Retrieval-augmented generation (RAG) greatly enhances large language models (LLMs) performance in knowledge-intensive tasks. However, naive RAG methods struggle with multi-hop question answering due to their limited capacity to capture complex dependencies across documents. Recent studies employ graph-based RAG to capture document connections. However, these approaches often result in a loss of semantic coherence and introduce irrelevant noise during node matching and subgraph construction. To address these limitations, we propose NeuroPath, an LLM-driven semantic path tracking RAG framework inspired by the path navigational planning of place cells in neurobiology. It consists of two steps: Dynamic Path Tracking and Post-retrieval Completion. Dynamic Path Tracking performs goal-directed semantic path tracking and pruning over the constructed knowledge graph (KG), improving noise reduction and semantic coherence. Post-retrieval Completion further reinforces these benefits by conducting second-stage retrieval using intermediate reasoning and the original query to refine the query goal and complete missing information in the reasoning path. NeuroPath surpasses current state-of-the-art baselines on three multi-hop QA datasets, achieving average improvements of 16.3% on recall@2 and 13.5% on recall@5 over advanced graph-based RAG methods. Moreover, compared to existing iter-based RAG methods, NeuroPath achieves higher accuracy and reduces token consumption by 22.8%. Finally, we demonstrate the robustness of NeuroPath across four smaller LLMs (Llama3.1, GLM4, Mistral0.3, and Gemma3), and further validate its scalability across tasks of varying complexity. Code is available at https://github.com/KennyCaty/NeuroPath.
format Preprint
id arxiv_https___arxiv_org_abs_2511_14096
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NeuroPath: Neurobiology-Inspired Path Tracking and Reflection for Semantically Coherent Retrieval
Li, Junchen
Wang, Rongzheng
Huang, Yihong
Chen, Qizhi
Zhang, Jiasheng
Liang, Shuang
Information Retrieval
Artificial Intelligence
Retrieval-augmented generation (RAG) greatly enhances large language models (LLMs) performance in knowledge-intensive tasks. However, naive RAG methods struggle with multi-hop question answering due to their limited capacity to capture complex dependencies across documents. Recent studies employ graph-based RAG to capture document connections. However, these approaches often result in a loss of semantic coherence and introduce irrelevant noise during node matching and subgraph construction. To address these limitations, we propose NeuroPath, an LLM-driven semantic path tracking RAG framework inspired by the path navigational planning of place cells in neurobiology. It consists of two steps: Dynamic Path Tracking and Post-retrieval Completion. Dynamic Path Tracking performs goal-directed semantic path tracking and pruning over the constructed knowledge graph (KG), improving noise reduction and semantic coherence. Post-retrieval Completion further reinforces these benefits by conducting second-stage retrieval using intermediate reasoning and the original query to refine the query goal and complete missing information in the reasoning path. NeuroPath surpasses current state-of-the-art baselines on three multi-hop QA datasets, achieving average improvements of 16.3% on recall@2 and 13.5% on recall@5 over advanced graph-based RAG methods. Moreover, compared to existing iter-based RAG methods, NeuroPath achieves higher accuracy and reduces token consumption by 22.8%. Finally, we demonstrate the robustness of NeuroPath across four smaller LLMs (Llama3.1, GLM4, Mistral0.3, and Gemma3), and further validate its scalability across tasks of varying complexity. Code is available at https://github.com/KennyCaty/NeuroPath.
title NeuroPath: Neurobiology-Inspired Path Tracking and Reflection for Semantically Coherent Retrieval
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2511.14096