Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering

原文：Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering

作者：Yang Hong, Yajun Yang, Xin Wang, Liping Jing, Qinghua Hu

来源：arXiv cs.CL（自然语言）

正文

Computer Science > Computation and Language

arXiv:2610.08388v1 (cs)

[Submitted on 6 Oct 2026]

Title:Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering

Authors:Yang Hong, Yajun Yang, Xin Wang, Liping Jing, Qinghua Hu

View a PDF of the paper titled Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering, by Yang Hong and 4 other authors

View PDF

HTML (experimental)

Abstract:Large language models (LLMs) have demonstrated strong capabilities in question answering, yet they still frequently suffer from hallucinations on knowledge-intensive tasks. Knowledge graphs (KGs) provide LLMs with structured, interpretable, and updatable factual grounding, making them a promising external knowledge source for reliable reasoning. However, existing LLM-guided graph reasoning methods typically rely on hop-wise greedy or beam-style pruning during evidence retrieval. Such local decision processes are inherently myopic: evidence that appears weak near the source may become crucial only after deeper graph context is explored, causing answer-critical branches to be discarded prematurely and making the reasoning chain difficult to recover. To address this limitation, we propose Foresight-over-Graph (FoG), a foresight-aware evidence retrieval framework for knowledge base question answering (KBQA). FoG iteratively constructs a question-relevant evidence subgraph and uses far-to-near feedback to guide path exploration, and maintains a compact memory subgraph to support continued exploration. Extensive experiments on widely used KBQA benchmarks demonstrate that FoG achieves state-of-the-art performance, with a particularly large improvement of 16.58% in Hit on CWQ, while also reducing LLM calls and token usage. Our code is available at this https URL .

Comments:

25 pages, 10 figures. Accepted at NeurIPS 2026

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

Cite as:

arXiv:2610.08388 [cs.CL]

(or

arXiv:2610.08388v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2610.08388

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

主题

自然语言处理 · 人工智能

由「前沿雷达」于 2026-10-06 采集。正文取自原文页面，已保留出处链接。标题与正文版权归原作者所有。