arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.08148cs.CLcs.AI
收藏

逐步挖掘外部知识以实现隐式复杂问题回答

Gradually Excavating External Knowledge for Implicit Complex Question Answering

Chang Liu, Xiaoguang Li, Lifeng Shang, Xin Jiang, Qun Liu, Edmund Y. Lam, Ngai Wong

AI总结:

本文提出一种渐进式知识挖掘框架,通过迭代获取外部知识并动态调整策略,提升开放领域复杂问题回答的准确率和效率。

摘要:

最近,大语言模型(LLMs)因展现出与人类相当的能力和巨大的潜力而受到广泛关注。然而,对于开放领域隐式问题回答任务,LLMs可能并非最终解决方案,原因包括:1)未覆盖或过时的领域知识,2)单次生成因此限制了全面性。为此,本文提出了一种渐进式知识挖掘框架,用于开放领域复杂问题回答,其中LLMs迭代且主动获取外部信息,然后基于已获取的历史知识进行推理。具体而言,在解决问题的每个步骤中,模型会选择执行的动作,例如查询外部知识或执行单步逻辑推理,逐步向最终答案迈进。我们的方法可以有效利用即插即用的外部知识,并动态调整解决复杂问题的策略。在StrategyQA数据集上的评估表明,我们的方法在参数量少于竞争对手的6%的情况下,实现了78.17%的准确率,为约10B规模的LLM设定了新的SOTA。

英文摘要:

Recently, large language models (LLMs) have gained much attention for the emergence of human-comparable capabilities and huge potential. However, for open-domain implicit question-answering problems, LLMs may not be the ultimate solution due to the reasons of: 1) uncovered or out-of-date domain knowledge, 2) one-shot generation and hence restricted comprehensiveness. To this end, this work proposes a gradual knowledge excavation framework for open-domain complex question answering, where LLMs iteratively and actively acquire external information, and then reason based on acquired historical knowledge. Specifically, during each step of the solving process, the model selects an action to execute, such as querying external knowledge or performing a single logical reasoning step, to gradually progress toward a final answer. Our method can effectively leverage plug-and-play external knowledge and dynamically adjust the strategy for solving complex questions. Evaluated on the StrategyQA dataset, our method achieves 78.17% accuracy with less than 6% parameters of its competitors, setting new SOTA for ~10B-scale LLMs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑