arXiv Machine Learning July 2, 2026 By Emil Joswin, Srujananjali Medicherla, Priyanka Mary Mammen

A Mechanistic View of Authority Hierarchy in LLM Sycophancy

Read the original on arXiv Machine Learning →

arXiv:2607. 00415v1 Announce Type: cross Abstract: Authority bias poses a critical safety concern in language models: models systematically prioritize social cues from authority figures over factual consistency, swaying their answers based on source credibility rather than evidence.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 9

Dissociating the Internal Representations of Sycophancy in LLMs

arXiv:2607. 07003v1 Announce Type: new Abstract: Large Language Models (LLMs) frequently exhibit sycophancy, where they agree with a user's statement even when incorrect.

By Anthony Baez, Sheer Karny, Pat Pataranutaporn

llms

arXiv AI

Aug 11

The Authority Expectancy Effect in Multi-User Conflict

arXiv:2608. 08026v1 Announce Type: new Abstract: We investigate how social authority (SA) signals interact with severity-based prioritization in large language models, operationalizing each axis as a model-elicited baseline -- the triage hierarchy and the SA hierarchy.

By Eunna Lee

llms

arXiv AI

1d ago

THESIS-MoE: Trainable Hierarchical Extraction and SteerIng of Sycophancy in Mixture-of-Experts

arXiv:2608. 15687v1 Announce Type: new Abstract: Sycophancy, the tendency of a language model to change its answer to match a user's stated belief, is a common alignment failure.

By Kareem Hassani, Chaymaa Abbas, Lama Mawlawi, Mariette Awad

llms benchmarks safety

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.

llms

arXiv Machine Learning

Jun 5

Trust, but Don't Verify: Epistemic Blind Spots in LLM Source Evaluation

arXiv:2606. 05403v1 Announce Type: new Abstract: Language models increasingly act as epistemic proxies, synthesizing evidence from multiple sources to inform decisions.

By Rohan N. Pradhan, Steve Goley

llms safety

arXiv AI

Jun 2

Easier to Mislead Than to Correct: Harmful and Beneficial Revision in LLM Conformity

arXiv:2606. 01637v1 Announce Type: cross Abstract: Large language models are increasingly used in multi-agent systems, where they see and respond to other agents' answers.

By Jiaming Qu, Lucheng fu, Yibo Hu

llms agents

Related stories

Dissociating the Internal Representations of Sycophancy in LLMs

The Authority Expectancy Effect in Multi-User Conflict

THESIS-MoE: Trainable Hierarchical Extraction and SteerIng of Sycophancy in Mixture-of-Experts

Dissociating the Internal Representations of Sycophancy in LLMs

Trust, but Don't Verify: Epistemic Blind Spots in LLM Source Evaluation

Easier to Mislead Than to Correct: Harmful and Beneficial Revision in LLM Conformity