The paper 'The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs' argues that current evaluation practices for hallucination detection in large language models are fundamentally flawed because they rely on metrics like ROUGE that misalign with human judgments.

Authors

• Person: Not available Organization: arXiv
  The Illusion of Progress: Re-evaluating Hallucination Detection in ...

Sources

• The Illusion of Progress: Re-evaluating Hallucination Detection in ... arxiv.org arXiv via serper

Referenced by nodes (4)

• Large Language Models concept
• hallucination detection concept
• ROUGE concept
• The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs concept