Paraphrase method reveals and fixes language model factual errors
Hallucination-R1: Robustness-Oriented Paraphrase Generation for Factual Consistency
Computation and LanguageArtificial Intelligence
Summary
Sometimes AI systems give wrong answers when a question is asked in different but equivalent ways, exposing a problem with how facts are understood. The authors created a method called HALLUCINATION-R1 that generates paraphrases that are still faithful to the original meaning but tricky enough to show where AI models make factual mistakes. This method helps reveal hidden errors in question-answering models and can produce training data that makes those models better at staying factually consistent across different question forms.
What this means in practice
- •For natural language processing developers: Identify and fix factual errors in QA systems by generating challenging but accurate paraphrases to test model consistency.
- •For ai model trainers: Improve robustness of language models by fine-tuning on data produced with HALLUCINATION-R1 that exposes factual instability.
Authors
Wenhan Yu, Wenxin Wu, Hao Wang, Lei Sha
Abstract
Factual hallucination is commonly defined by incorrect factual outputs. We study a paraphrase-induced hallucination setting, where a model answers a factual question correctly in its original form but generates an incorrect answer under a semantically equivalent paraphrase. Such inconsistencies expose latent factual instability under semantic invariance. However, general-purpose paraphrases are often insufficient as robustness-oriented supervision: near-copy paraphrases provide weak signals, while overly diverse paraphrases may break semantic equivalence. In this paper, we propose HALLUCINATION-R1, a robustness-oriented paraphrase generation framework that learns to produce semantically faithful yet robustness-challenging paraphrases for factual consistency. Through two-stage optimization, it first stabilizes meaning-preserving and diverse paraphrasing, then rewards paraphrases that reveal factual consistency degradation in downstream QA models. Experiments on SimpleQuestions, PopQA, and TruthfulQA show that HALLUCINATION-R1 achieves a strong consistency--diversity trade-off and exposes robustness failures across multiple model families and datasets. Further analyses indicate that these failures are not reducible to surface-level artifacts or semantic drift, but reveal non-trivial factual instability under meaning-preserving variation. A lightweight fine-tuning study also shows that HALLUCINATION-R1-generated data improves robust accuracy under paraphrase variations, suggesting its utility for robustness-oriented training. Our code and models are publicly available at https://github.com/yuwenhan07/Hallucination-R1.