Hugging Face Trending Papers

Group Alignment-Induced Sycophancy: A Two-Sided Evaluation of Steerable Pluralistic Alignment

Read the original on Hugging Face Trending Papers →

Group alignment adapts a language model to a demographic group to produce responses that reflect the group's opinions, values, and preferences. Sycophancy, a well-documented by-product of alignment, causes the model to over-agree with the user regardless of factual and objective information.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning
Jul 24

How Robust Is Homogeneity Bias in LLMs? Evidence Across Models, Decoding Settings, and Identity Signals

arXiv:2501. 02211v3 Announce Type: replace-cross Abstract: Large language models (LLMs) reproduce homogeneity bias -- the tendency to portray marginalized groups as more internally similar than dominant groups -- but whether this bias generalizes across models, is stable under different inference settings, or depends on how group identity is signaled remains unstudied.

By Messi H. J. Lee
Hugging Face Trending Papers
Jul 8

Dissociating the Internal Representations of Sycophancy in LLMs

Large Language Models (LLMs) frequently exhibit sycophancy, where they agree with a user's statement even when incorrect. While sycophancy is often treated as a single defined behavior, it can manifest in substantially distinct ways and circumstances, raising the question of whether this multi-faceted nature is reflected in its internal mechanisms.