AI RESEARCH
Enhancing Multilingual Counterfactual Generation through Alignment-as-Preference Optimization
arXiv CS.AI
•
ArXi:2605.11632v1 Announce Type: cross Self-generated counterfactual explanations (SCEs) are minimally modified inputs (minimality) generated by large language models (LLMs) that flip their own predictions (validity), offering a causally grounded approach to unraveling black-box LLM behavior. Yet extending them beyond English remains challenging: existing methods struggle to produce valid SCEs in non-dominant languages, and a persistent trade-off between validity and minimality undermines explanation quality. We.