EVADE: LLM-Based Explanation Generation and Validation for Error Detection in NLI 事件

EVADE: LLM-Based Explanation Generation and Validation for Error Detection in NLI arXiv:2511.08949v2 Announce Type: replace Abstract: High-quality datasets are critical for training and evaluating reliable NLP models. In tasks like natural language inference (NLI), human label variation (HLV) arises when multiple labels are valid for the same instance, making it difficult to separate annotation errors from plausible variation. An earlier framework, VARIERR (Weber-Genzel et al., 2024), asks mult