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 https://github.com/yhong7/FoG .
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Hong, Y., Yang, Y., Wang, X., Jing, L., & Hu, Q. (2026). Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering. https://omanscience.com/en/articles/foresight-over-graph-reasoning-beyond-local-horizons-for-knowledge-base-question-answering
MLA 9
Hong, Yang, et al. "Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering." https://omanscience.com/en/articles/foresight-over-graph-reasoning-beyond-local-horizons-for-knowledge-base-question-answering.
Chicago (author–date)
Hong, Yang, Yajun Yang, Xin Wang, Liping Jing, and Qinghua Hu. 2026. "Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering." https://omanscience.com/en/articles/foresight-over-graph-reasoning-beyond-local-horizons-for-knowledge-base-question-answering.
Harvard
Hong, Y., Yang, Y., Wang, X., Jing, L. and Hu, Q. (2026) 'Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering', Available at: https://omanscience.com/en/articles/foresight-over-graph-reasoning-beyond-local-horizons-for-knowledge-base-question-answering.
Vancouver
Hong Y, Yang Y, Wang X, Jing L, Hu Q. Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering. https://omanscience.com/en/articles/foresight-over-graph-reasoning-beyond-local-horizons-for-knowledge-base-question-answering
IEEE
Y. Hong, Y. Yang, X. Wang, L. Jing, and Q. Hu, "Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering," https://omanscience.com/en/articles/foresight-over-graph-reasoning-beyond-local-horizons-for-knowledge-base-question-answering.