Metaphor Reasoning is Meta-reasoning

ACL ARR 2026 January Submission9845 Authors

Keywords: metaphor reasoning, large language model, natural language processing

Abstract:

Metaphor reasoning is an essential cognitive ability that maps knowledge from familiar domains to more abstract domains. This ability functions as a meta-ability underlying many types of reasoning. However, existing work rarely investigates how metaphor reasoning affects other reasoning abilities.
To bridge this gap, we systematically study how metaphor reasoning, particularly through metaphorical riddles, can enhance broader reasoning abilities in large language models.
We propose MetaR, an automated system for synthesizing metaphorical riddles that satisfy five quality dimensions: diverse, balanced, reasoning-oriented, challenging, and verifiable. Leveraging that answer categories determine riddle categories, we employ a hierarchical answer taxonomy for the former three criteria and a multi-agent refinement framework for the latter two, generating a high-quality dataset. Training with reinforcement learning on verifiable rewards using only thousands of metaphorical riddles, we demonstrate improvements across six out-of-distribution reasoning domains. Analysis reveals transfer effectiveness depends on model scale and pattern-target domain alignment. We will release our code and data.

Paper Type: Long

Research Area: Language Models

Research Area Keywords: chain-of-thought, applications

Contribution Types: NLP engineering experiment, Reproduction study, Publicly available software and/or pre-trained models, Data resources

Languages Studied: English

Submission Number: 9845