Showing cs.CLShow all
2 papers · 1 filter
cs.CL2025
Position: On the Methodological Pitfalls of Evaluating Base LLMs for Reasoning
Jason Chan, Zhixue Zhao, Robert Gaizauskas
Existing work investigates the reasoning capabilities of large language models (LLMs) to uncover their limitations, human-like biases and underlying processes. Such studies include…
cs.CL2024
RULEBREAKERS: Challenging LLMs at the Crossroads between Formal Logic and Human-like Reasoning
Jason Chan, Robert Gaizauskas, Zhixue Zhao
Formal logic enables computers to reason in natural language by representing sentences in symbolic forms and applying rules to derive conclusions. However, in what our study charac…