Zobrazit v EDS

CBR 2 : A Case-Based Reasoning Framework with Dual Retrieval Guidance for Few-Shot KBQA.

Uloženo v:
Podrobná bibliografie
Název: CBR 2 : A Case-Based Reasoning Framework with Dual Retrieval Guidance for Few-Shot KBQA.
Autoři: Hu, Xinyu, Li, Tong, Xue, Lingtao, Du, Zhipeng, Huang, Kai, Xiao, Gang, Tang, He
Zdroj: Big Data & Cognitive Computing; Jan2026, Vol. 10 Issue 1, p17, 22p
Témata: CASE-based reasoning, INFORMATION retrieval, NATURAL language processing, KNOWLEDGE representation (Information theory), MACHINE learning, APPLIED sciences, RULE-based programming
Abstrakt: Recent advances in large language models (LLMs) have driven substantial progress in knowledge base question answering (KBQA), particularly under few-shot settings. However, symbolic program generation remains challenging due to its strict structural constraints and high sensitivity to generation errors. Existing few-shot methods often rely on multi-turn strategies, such as rule-based step-by-step reasoning or iterative self-correction, which introduce additional latency and exacerbate error propagation. We present CBR2, a case-based reasoning framework with dual retrieval guidance for single-pass symbolic program generation. Instead of generating programs interactively, CBR2 constructs a unified structure-aware prompt that integrates two complementary types of retrieval: (1) structured knowledge from ontologies and factual triples, and (2) reasoning exemplars retrieved via semantic and function-level similarity. A lightweight similarity model is trained to retrieve structurally aligned programs, enabling effective transfer of abstract reasoning patterns. Experiments on KQA Pro and MetaQA demonstrate that CBR2 achieves significant improvements in both accuracy and syntactic robustness. Specifically on KQA Pro, it boosts Hits@1 from 72.70% to 82.13% and reduces syntax errors by 25%, surpassing the previous few-shot state-of-the-art. [ABSTRACT FROM AUTHOR]
Copyright of Big Data & Cognitive Computing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Databáze: Complementary Index
Popis
Abstrakt:Recent advances in large language models (LLMs) have driven substantial progress in knowledge base question answering (KBQA), particularly under few-shot settings. However, symbolic program generation remains challenging due to its strict structural constraints and high sensitivity to generation errors. Existing few-shot methods often rely on multi-turn strategies, such as rule-based step-by-step reasoning or iterative self-correction, which introduce additional latency and exacerbate error propagation. We present CBR<sup>2</sup>, a case-based reasoning framework with dual retrieval guidance for single-pass symbolic program generation. Instead of generating programs interactively, CBR<sup>2</sup> constructs a unified structure-aware prompt that integrates two complementary types of retrieval: (1) structured knowledge from ontologies and factual triples, and (2) reasoning exemplars retrieved via semantic and function-level similarity. A lightweight similarity model is trained to retrieve structurally aligned programs, enabling effective transfer of abstract reasoning patterns. Experiments on KQA Pro and MetaQA demonstrate that CBR<sup>2</sup> achieves significant improvements in both accuracy and syntactic robustness. Specifically on KQA Pro, it boosts Hits@1 from 72.70% to 82.13% and reduces syntax errors by 25%, surpassing the previous few-shot state-of-the-art. [ABSTRACT FROM AUTHOR]
ISSN:25042289
DOI:10.3390/bdcc10010017