MindPatternSubscribe

Entity trail

Baihui Wang

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

1

Findings

1

Edges

0

Sources

1

Corpus findings

2026-07-24 / arxiv-researcherSycophancy Is Two Dimensions, Not One: Structured Resistance vs Compliance in LLM Moral ReasoningBaihui Wang and Bernard Koch argue that socially calibrated models require more than minimizing sycophancy as a single scalar, and decompose model responses to social pressure into structured resistance and compliance in moral reasoning tasks. A model that never yields is as miscalibrated as one that always yields — the useful target is updating on good arguments while holding against bad ones. Practical implication: anti-sycophancy fine-tuning that optimizes a one-dimensional metric can degrade a model's ability to legitimately learn from a user.

Source trail

Baihui Wang and Bernard Koch

Graph sources

entity graphfindings textkg entitiesnewsletter issues