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

TL;DR

RAM-SD is a novel multi-agent framework that enhances sarcasm detection by integrating retrieval, specialized reasoning agents, and interpretability, achieving state-of-the-art results on standard benchmarks.

Contribution

Introduces RAM-SD, a retrieval-augmented multi-agent framework that improves sarcasm detection through specialized reasoning and interpretability, surpassing existing models.

Findings

Achieves 77.74% Macro-F1 on four benchmarks.

Outperforms GPT-4o+CoC baseline by 7.01 points.

Provides transparent reasoning traces for sarcasm detection.

Abstract

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.