The automated fact verification framework used in KGHaluBench may make mistakes, such as rejecting valid responses or scoring misaligned ones, despite achieving substantial agreement with human judgment.

Authors

• Person: Not available Organization: arXiv
  A Knowledge Graph-Based Hallucination Benchmark for Evaluating ...

Sources

• A Knowledge Graph-Based Hallucination Benchmark for Evaluating ... arxiv.org arXiv via serper

Referenced by nodes (1)

• KGHaluBench concept