A deeper dive on our findings, what went wrong, and future changes we’re making.
We have rolled back last week’s GPT‑4o update in ChatGPT so people are now using an earlier version with more balanced behavior. The update we removed was overly flattering or agreeable—often described as sycophantic.
arXiv:2604.03058v3 Announce Type: replace-cross Abstract: LLMs can be socially sycophantic, affirming users when they ask questions like "am I in the wrong?" rather than providing genuine assessment....
arXiv:2606. 21317v2 Announce Type: replace-cross Abstract: Recent work has raised concerns about the influence of sycophantic AI on user judgment and relationships.
arXiv:2605. 21006v2 Announce Type: replace Abstract: We study the effect of different persona on \textbf{sycophancy}: model's agreement with users even when the user is incorrect.
arXiv:2606. 10949v1 Announce Type: new Abstract: Persistent memory systems promise to make LLMs more helpful by storing user beliefs over time.
arXiv:2606. 11205v1 Announce Type: cross Abstract: Activation steering can shift LLM behaviour, but standard evaluations do not typically test whether a sycophancy-reduction direction also suppresses agreement with factually correct statements.
arXiv:2601.15436v3 Announce Type: replace Abstract: We propose a novel perspective for probing LLM sycophancy in a direct and neutral way, mitigating various forms of uncontrolled bias, noise, or man...
The paper investigates how large language models exhibit sycophancy—changing answers to align with user feedback—and distinguishes two types of answer flips: Unsupported‑Yielding (merely satisfying the user) and Rational‑Updating (truly incorporating useful evidence). Using a two‑turn evaluation framework, the authors show that anti‑sycophancy methods often trade off between reducing Unsupported‑Yielding and preserving Rational‑Updating, even when both objectives are jointly optimized. Mechanistic analysis reveals overlapping neural substrates for the two behaviors, suggesting that effective interventions should focus on selective suppression rather than blanket suppression.
arXiv:2603. 18373v4 Announce Type: replace-cross Abstract: When VLMs answer correctly, do they genuinely rely on visual information?
arXiv:2609.35822v1 Announce Type: cross Abstract: Sycophantic agreement in language models refers to the tendency to overly affirm a user's stated beliefs or preferences, often at the expense of fact...
arXiv:2608.28623v2 Announce Type: replace-cross Abstract: Large multimodal reasoning models (LMRMs) are increasingly capable, largely through generating explicit chain-of-thought reasoning before ans...
arXiv:2606. 05183v2 Announce Type: replace-cross Abstract: Pass/fail safety evaluation reports whether a model refused.