Kalai et al. (2025) argue that post-training benchmarks exacerbate hallucinations in Large Language Models by penalizing uncertainty, which incentivizes models to guess rather than abstain from answering.

Authors

• Person: Not available Organization: arXiv
  A Survey on the Theory and Mechanism of Large Language Models

Sources

• A Survey on the Theory and Mechanism of Large Language Models arxiv.org arXiv via serper

Referenced by nodes (1)

• Large Language Models concept