Skip to yearly menu bar Skip to main content


Oral
in
Workshop: ICML 2025 Workshop on Collaborative and Federated Agentic Workflows (CFAgentic @ ICML'25)

CAF-I: A Collaborative Multi-Agent Framework for Enhanced Irony Detection with Large Language Models

Ziqi Liu · Ziyang Zhou · Mingxuan Hu

[ ] [ Project Page ]
Sat 19 Jul 9:10 a.m. PDT — 9:20 a.m. PDT

Abstract:

Large language model (LLM) have become mainstream methods in the field of sarcasm detection. However, existing LLM methods face challenges in irony detection, including: 1. single-perspective limitations, 2. insufficient comprehensive understanding, and 3. lack of interpretability. This paper introduces the Collaborative Agent Framework for Irony (CAF-I), an LLM-driven multi-agent system designed to overcome these issues. CAF-I employs specialized agents for Context, Semantics, and Rhetoric, which perform multidimensional analysis and engage in interactive collaborative optimization. A Decision Agent then consolidates these perspectives, with a Refinement Evaluator Agent providing conditional feedback for optimization. Experiments on benchmark datasets establish CAF-I's state-of-the-art zero-shot performance. Achieving SOTA on the vast majority of metrics, CAF-I reaches an average Macro-F1 of 76.31%, a 4.98% absolute improvement over the strongest prior baseline. This success is attained by its effective simulation of human-like multi-perspective analysis, enhancing detection accuracy and interpretability.

Chat is not available.