Instructions emphasizing conciseness, such as 'answer this question briefly,' degraded the factual reliability of the Large Language Models tested in the Phare benchmark.

Authors

• Person: Not available Organization: Giskard
  Phare LLM Benchmark: an analysis of hallucination in ...

Sources

• Phare LLM Benchmark: an analysis of hallucination in ... www.giskard.ai Giskard via serper

Referenced by nodes (1)

• Large Language Models concept