arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.17002cs.CL
收藏

RAM-SD:基于检索的多智能体框架用于讽刺检测

RAM-SD: Retrieval-Augmented Multi-agent framework for Sarcasm Detection

Xi’an Jiaotong–Liverpool University(西安交通大学利物浦大学)

Ziyang Zhou, Ziqi Liu, Yan Wang, Yiming Lin, Yangbin Chen

AI总结:

RAM-SD通过多智能体框架提升讽刺检测性能,实现77.74%的宏F1值,提供透明推理轨迹。

摘要:

讽刺检测仍是一个重大挑战,因为它依赖于细微的上下文理解、世界知识和多方面的语言线索,这些线索在不同的讽刺表达中差异显著。现有方法,从微调的Transformer到大语言模型,都采用统一的推理策略来处理所有输入,难以应对讽刺多样的分析需求。这些需求从建模上下文期望违反到需要外部知识支撑或识别特定修辞模式。为了解决这一限制,我们引入了RAM-SD,一种用于讽刺检测的检索增强型多智能体框架。该框架通过四个阶段运作:(1)上下文检索将查询置于讽刺和非讽刺示例中;(2)元规划器分类讽刺类型并从预定义集合中选择最优推理计划;(3)一组专门的智能体进行互补的多视角分析;(4)整合器将这些分析综合成最终可解释的判断并附带自然语言解释。在四个标准基准上评估,RAM-SD实现了最先进的宏F1值77.74%,比强大的GPT-4o+CoC基线高出7.01个百分点。我们的框架不仅设定了新的性能基准,还提供了透明且可解释的推理轨迹,揭示了讽刺理解背后的认知过程。

英文摘要:

Sarcasm detection remains a significant challenge due to its reliance on nuanced contextual understanding, world knowledge, and multi-faceted linguistic cues that vary substantially across different sarcastic expressions. Existing approaches, from fine-tuned transformers to large language models, apply a uniform reasoning strategy to all inputs, struggling to address the diverse analytical demands of sarcasm. These demands range from modeling contextual expectation violations to requiring external knowledge grounding or recognizing specific rhetorical patterns. To address this limitation, we introduce RAM-SD, a Retrieval-Augmented Multi-Agent framework for Sarcasm Detection. The framework operates through four stages: (1) contextual retrieval grounds the query in both sarcastic and non-sarcastic exemplars; (2) a meta-planner classifies the sarcasm type and selects an optimal reasoning plan from a predefined set; (3) an ensemble of specialized agents performs complementary, multi-view analysis; and (4) an integrator synthesizes these analyses into a final, interpretable judgment with a natural language explanation. Evaluated on four standard benchmarks, RAM-SD achieves a state-of-the-art Macro-F1 of 77.74%, outperforming the strong GPT-4o+CoC baseline by 7.01 points. Our framework not only sets a new performance benchmark but also provides transparent and interpretable reasoning traces, illuminating the cognitive processes behind sarcasm comprehension.

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。

↑