less than 1 minute read

📄 Read the full paper on ACL Proceedings or on arXiv

ACL arXiv MMLU-Adversarial HuggingFace Dataset GitHub

ACL2025 Logo

Paper accepted at ACL 2025!

Our paper, Right Answer, Wrong Score: Uncovering the Inconsistencies of LLM Evaluation in Multiple-Choice Question Answering, has been accepted to the ACL Findings 2025!

Check the original post here!

See you in Vienna 🇦🇹