Go to ACL ARR 2025 February homepageTreeCut: A Synthetic Unanswerable Math Word Problem Dataset for LLM Hallucination Evaluation
Abstract: Large language models (LLMs) now achieve near-human performance on standard math word problem benchmarks (e.g., GSM8K), yet their true reasoning ability remains disputed. A key concern is that models often produce confident, yet unfounded, answers to unanswerable problems. We introduce TreeCut, a synthetic dataset that systematically generates infinite unanswerable math word problems and their answerable counterparts, by representing each question as a tree and removing chosen necessary conditions. Experiments show TreeCut effectively induce hallucinations in large language models, including GPT-4o and o3-mini, with rates of 61% and 42% in their respective worst-case scenarios. Further analysis highlights that deeper or more complex trees, composite item names, and removing necessary condition near the middle of a path all increase the likelihood of hallucinations, underscoring the persistent challenges LLMs face in identifying unanswerable math problems.
Paper Type: Short
Research Area: Question Answering
Research Area Keywords: math QA, evaluation, mathematical NLP
Contribution Types: Model analysis & interpretability, Data resources
Languages Studied: English
Submission Number: 1707
Loading