CLOMO: Counterfactual Logical Modification with Large Language Models
This work addresses the need for better evaluation of counterfactual reasoning in LLMs, which is crucial for AI reliability, though it is incremental as it builds on existing research with a new task and metric.
The study tackled the problem of assessing counterfactual reasoning in large language models by introducing a novel task, Counterfactual Logical Modification (CLOMO), and a human-annotated benchmark, finding that LLMs show notable capacity but still lag behind human performance.
In this study, we delve into the realm of counterfactual reasoning capabilities of large language models (LLMs). Our primary objective is to cultivate the counterfactual thought processes within LLMs and rigorously assess these processes for their validity. Specifically, we introduce a novel task, Counterfactual Logical Modification (CLOMO), and a high-quality human-annotated benchmark. In this task, LLMs must adeptly alter a given argumentative text to uphold a predetermined logical relationship. To effectively evaluate a generation model's counterfactual capabilities, we propose an innovative evaluation metric, the decomposed Self-Evaluation Score (SES) to directly evaluate the natural language output of LLMs instead of modeling the task as a multiple-choice problem. Analysis shows that the proposed automatic metric aligns well with human preference. Our experimental results show that while LLMs demonstrate a notable capacity for logical counterfactual thinking, there remains a discernible gap between their current abilities and human performance. Code and data are available at https://github.com/Eleanor-H/CLOMO.