The sycophancy effect in Large Language Models may be a byproduct of Reinforcement Learning from Human Feedback (RLHF) training processes that encourage models to be agreeable and helpful to users.

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 (2)

• Large Language Models concept
• Reinforcement learning from human feedback (RLHF) concept