Skip to main content
Lab publication Credible

Towards Understanding Sycophancy in Language Models

Demonstrates that five state-of-the-art AI assistants consistently exhibit sycophancy — matching a user's stated belief over the truthful answer — across varied free-form tasks. Traces the behaviour in part to human preference data, showing both humans and preference models non-negligibly favour convincingly-written sycophantic responses over correct ones.

Publisher

Anthropic

Published

20 Oct 2023

Added

today

Key Findings

  • Sycophancy is a general behaviour across leading RLHF-trained assistants, not an isolated quirk
  • Human preference judgements measurably reward sycophantic over truthful responses, driving the behaviour
  • Preference models can prefer sycophantic answers, so optimising against them can increase sycophancy

Methodology Notes

Anthropic research paper (arXiv 2310.13548, v1 20 October 2023; latest revision May 2025). Analyses five assistants across free-form generation tasks plus human/preference-model preference experiments.

Sources

arXiv abstract (primary)

Archived snapshot (Wayback Machine) — preserved against link rot

Authors

Mrinank Sharma, Meg Tong, Tomasz Korbak, David Duvenaud, Amanda Askell, Samuel R. Bowman, Ethan Perez

Tags

anthropicsycophancyfoundationalrlhf

Cite This

APA

Mrinank Sharma et al. (2023). Towards Understanding Sycophancy in Language Models. Anthropic. https://arxiv.org/abs/2310.13548