World model inspired sarcasm reasoning with large language model agents

TL;DR

This paper introduces WM-SAR, a novel sarcasm detection method that uses specialized LLM-based agents to explicitly model and quantify semantic inconsistency and intention, improving accuracy and interpretability.

Contribution

The work reformulates sarcasm understanding as a world model inspired reasoning process with explicit component decomposition and a lightweight inference model, advancing interpretability and performance.

Findings

WM-SAR outperforms existing methods on sarcasm detection benchmarks.

Explicit modeling of semantic inconsistency and intention improves detection accuracy.

Ablation studies confirm the importance of component integration for effectiveness.

Abstract

Sarcasm understanding is a challenging problem in natural language processing, as it requires capturing the discrepancy between the surface meaning of an utterance and the speaker's intentions as well as the surrounding social context. Although recent advances in deep learning and Large Language Models (LLMs) have substantially improved performance, most existing approaches still rely on black-box predictions of a single model, making it difficult to structurally explain the cognitive factors underlying sarcasm. Moreover, while sarcasm often emerges as a mismatch between semantic evaluation and normative expectations or intentions, frameworks that explicitly decompose and model these components remain limited. In this work, we reformulate sarcasm understanding as a world model inspired reasoning process and propose World Model inspired SArcasm Reasoning (WM-SAR), which decomposes literal meaning, context, normative expectation, and intention into specialized LLM-based agents. The discrepancy between literal evaluation and normative expectation is explicitly quantified as a deterministic inconsistency score, and together with an intention score, these signals are integrated by a lightweight Logistic Regression model to infer the final sarcasm probability. This design leverages the reasoning capability of LLMs while maintaining an interpretable numerical decision structure. Experiments on representative sarcasm detection benchmarks show that WM-SAR consistently outperforms existing deep learning and LLM-based methods. Ablation studies and case analyses further demonstrate that integrating semantic inconsistency and intention reasoning is essential for effective sarcasm detection, achieving both strong performance and high interpretability.