TAG-EQA: 基于结构化提示策略的文本-图事件问答方法
TAG-EQA: Text-And-Graph for Event Question Answering via Structured Prompting Strategies
AI总结：
针对大语言模型事件推理能力不足的问题，提出融合因果事件图的TAG-EQA提示框架，通过多策略多模态配置验证，无需微调即可提升事件问答准确率。
摘要：
大语言模型（LLMs）在通用语言任务上表现出色，但在处理基于事件的问题时往往存在困难，尤其是需要因果或时序推理的问题。我们提出了TAG-EQA（Text-And-Graph for Event Question Answering，文本-图事件问答），这是一种提示框架，通过将结构化关系转换为自然语言语句，将因果事件图注入到LLM的输入中。TAG-EQA涵盖9种提示配置，将三种策略（零样本、少样本、思维链）与三种输入模态（纯文本、纯图、文本+图）相结合，可系统分析结构化知识何时以及如何辅助推理。在TORQUESTRA基准上，TAG-EQA的准确率相比纯文本基线平均提升5%，零样本设置下提升最高达12%，当图增强的思维链提示生效时提升可达18%。尽管性能因模型和配置而异，但我们的研究结果表明，因果图无需微调即可增强LLM的事件推理能力，为在基于提示的问答中编码结构提供了灵活的方式。
英文摘要：
Large language models (LLMs) excel at general language tasks but often struggle with event-based questions-especially those requiring causal or temporal reasoning. We introduce TAG-EQA (Text-And-Graph for Event Question Answering), a prompting framework that injects causal event graphs into LLM inputs by converting structured relations into natural-language statements. TAG-EQA spans nine prompting configurations, combining three strategies (zero-shot, few-shot, chain-of-thought) with three input modalities (text-only, graph-only, text+graph), enabling a systematic analysis of when and how structured knowledge aids inference. On the TORQUESTRA benchmark, TAG-EQA improves accuracy by 5% on average over text-only baselines, with gains up to 12% in zero-shot settings and 18% when graph-augmented CoT prompting is effective. While performance varies by model and configuration, our findings show that causal graphs can enhance event reasoning in LLMs without fine-tuning, offering a flexible way to encode structure in prompt-based QA.
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。
