Anthropic models and the largest versions of Meta’s Llama models show resistance to sycophancy, suggesting that the issue can be addressed at the model training level.

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 (3)

• LLaMA concept
• Meta entity
• Anthropic entity