#hallucination
- CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence (178 HF upvotes) Peking University / Shanghai Artificial Intelligence Laboratory research
- The Self-Correction Illusion: LLMs Fix Others' Errors but Not Their Own — Role Labels Are the Cause research
- Hallucination in World Models is Predictable and Preventable UC San Diego research
- Enoki: multi-level hallucination detection from one open IE pipeline Skoltech research