mlsanityData to 14 Oct 2026

Beyond Sycophancy: Structured Resistance and Compliance in LLM Moral Reasoning

arXiv 2607.21558 ↗First posted 23 Jul 2026cs.AIcited by 2

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Building socially calibrated large language models, which can learn from others without simply yielding to them, requires more than reducing sycophancy as a one-dimensional failure mode. Models must distinguish when to incorporate others' perspectives from when to maintain a well-grounded moral judgment. We study the broader resistance-compliance process governing this distinction. Across three studies, we show that models' judgment revision is structured along three dimensions that parallel classic phenomena in human social psychology: the distance between an incoming view and the model's initial position, the source attribution of that view, and the coalition structure supporting it. Models are generally more receptive to nearby positions, more influenced by views presented as their own prior judgments, and differently responsive to group pressure. These findings recast sycophancy as one expression of a broader judgment-updating process shaped by social influence. Our framework provides a principled basis for distinguishing constructive belief revision from sycophantic compliance, thereby supporting better alignment in morally consequential interactions.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 5 of its 25 references that are in the map. First posted on arXiv 23 Jul 2026.

Builds on

5 of 25 references.

References · 5

  1. 2023Towards Understanding Sycophancy in Language Modelscited by 1,040
  2. 2023Simple synthetic data reduces sycophancy in large language modelscited by 187
  3. 2025ELEPHANT: Measuring and understanding social sycophancy in LLMscited by 129
  4. 2025Accumulating Context Changes the Beliefs of Language Modelscited by 28
  5. 2026What Counts as AI Sycophancy? A Taxonomy and Expert Survey of a Fragmented Constructcited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026"You're Right, Let Me Fix It": How LLM Agents Damage Correct Work When Falsely Accusedcited by 0
  2. 2026Anatomy of LLM Sycophancy: What a Flip Rate Hidescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Right or Wrong, Models Comply: Directional Blindness in LLM Moral Judgment
  2. 2026Reasoning or Rhetoric? An Empirical Analysis of Moral Reasoning Explanations in Large Language Models
  3. 2024Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment
  4. 2026The Fragility Of Moral Judgment In Large Language Models
  5. 2026When Helpfulness Becomes Sycophancy: Sycophancy is a Boundary Failure Between Social Alignment and Epistemic Integrity in Large Language Models
  6. 2025Many LLMs Are More Utilitarian Than One
  7. 2025"Pull or Not to Pull?'': Investigating Moral Biases in Leading Large Language Models Across Ethical Dilemmas
  8. 2023MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks