FoG：面向知识库问答的远见式图推理框架，CWQ 命中率提升 16.58%

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 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Yang Hong [view email]
[v1] Tue, 6 Oct 2026 14:07:43 UTC (573 KB)