Similar Items: Text Corpora as Concept Fields: Black-Box Hallucination and Novelty Measurement
- The Frequency Confound in Language-Model Surprisal and Metaphor Novelty
- A multilingual hallucination benchmark: MultiWikiQHalluA
- The First Token Knows: Single-Decode Confidence for Hallucination Detection
- Detecting Hallucinations in Large Language Models via Internal Attention Divergence Signals
- Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments
- FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents