[2601.00263] Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation

Computer Science > Computation and Language arXiv:2601.00263 (cs) [Submitted on 1 Jan 2026 (v1), last revised 6 Apr 2026 (this version, v2)] Title:Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation Authors:Qianli Wang, Van Bach Nguyen, Yihong Liu, Fedor Splitt, Nils Feldhus, Christin Seifert, Hinrich Schütze, Sebastian Möller, Vera Schmitt View a PDF of the paper titled Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation, by Qianli Wang and 8 other authors View PDF HTML (experimental) Abstract:Counterfactuals refer to minimally edited inputs that cause a model's prediction to change, serving as a promising approach to explaining the model's behavior. Large language models (LLMs) excel at generating English counterfactuals and demonstrate multilingual proficiency. However, their effectiveness in generating multilingual counterfactuals remains unclear. To this end, we conduct a comprehensive study on multilingual counterfactuals. We first conduct automatic evaluations on both directly generated counterfactuals in the target languages and those derived via English translation across six languages. Although translation-based counterfactuals offer higher validity than their directly generated counterparts, they demand substantially more modifications and still fall short of matching the quality of the original English counterfactuals. Seco...