Generics and Default Reasoning in Large Language Models
This addresses the problem of assessing LLMs' default reasoning capabilities for linguists, philosophers, and cognitive scientists, but it is incremental as it evaluates existing models without proposing new methods.
The paper evaluated 28 large language models on 20 defeasible reasoning patterns involving generics, finding that while some models performed well, performance varied widely, with chain-of-thought prompting often causing significant accuracy drops (mean -11.14%).
This paper evaluates the capabilities of 28 large language models (LLMs) to reason with 20 defeasible reasoning patterns involving generic generalizations (e.g., 'Birds fly', 'Ravens are black') central to non-monotonic logic. Generics are of special interest to linguists, philosophers, logicians, and cognitive scientists because of their complex exception-permitting behaviour and their centrality to default reasoning, cognition, and concept acquisition. We find that while several frontier models handle many default reasoning problems well, performance varies widely across models and prompting styles. Few-shot prompting modestly improves performance for some models, but chain-of-thought (CoT) prompting often leads to serious performance degradation (mean accuracy drop -11.14%, SD 15.74% in models performing above 75% accuracy in zero-shot condition, temperature 0). Most models either struggle to distinguish between defeasible and deductive inference or misinterpret generics as universal statements. These findings underscore both the promise and limits of current LLMs for default reasoning.