Entity · paper

Beyond Sycophancy: Structured Resistance and Compliance in LLM Moral Reasoning

paperactiveprovisionalbeyond-sycophancy-structured-resistance-and-compliance-in-llm-moral-reasoning-929700b5·1 events·first seen 2d ago

Aliases: Beyond Sycophancy: Structured Resistance and Compliance in LLM Moral Reasoning

More like this (12)

Moral Safety in LLMs: Exposing Performative Compliance with Puzzled Cues From Plausible to Actionable: A Position on LLM Self-Explanations Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias What Do Safety-Aligned LLMs Learn From Mixed Compliance Demonstrations?Which Values Do LLMs Confuse? A Schwartz-Based Recognition Study MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates Metacognition in LLMs: Foundations, Progress, and Opportunities Metacognition in LLMs: Foundations, Progress, and Opportunities Flaws in the LLM Automation Narrative Two Axes of LLM Abstention: Answer Correctness and Question Answerability RAS: Measuring LLM Safety Through Refusal Alignment

Recent events (1)

6arXiv · cs.AI·2d ago·source ↗

Structured resistance-compliance framework recasts LLM sycophancy as social influence phenomenon

A new arXiv paper proposes a three-dimensional framework for understanding how LLMs revise moral judgments under social pressure, drawing parallels to human social psychology. Across three studies, the authors find that models' judgment updates are structured by the distance of an incoming view from the model's initial position, source attribution, and coalition pressure. The work reframes sycophancy not as a one-dimensional failure but as one expression of a broader social-influence-driven updating process. The framework aims to provide principled criteria for distinguishing constructive belief revision from sycophantic compliance in alignment-relevant contexts.

Evaluation and Benchmarking AI Safety Research Beyond Sycophancy: Structured Resistance and Compliance in LLM Moral Reasoning +1 more