Beyond Sycophancy: Structured Resistance and Compliance in LLM Moral Reasoning

• URL: http://arxiv.org/abs/2607.21558v1
• Date: Thu, 23 Jul 2026 17:40:07 GMT
• Title: Beyond Sycophancy: Structured Resistance and Compliance in LLM Moral Reasoning
• Abstract summary: We show that models' judgment revision is structured along three dimensions that parallel classic phenomena in human social psychology.<n>We recast sycophancy as one expression of a broader judgment-updating process shaped by social influence.
• Score: 0.42970700836450476
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• To Compare, or Not to Compare: On Methodological Practices in Evaluating Social Bias [61.40435736418359]
  We introduce a unified framework that standardizes heterogeneous benchmarks to contrast isolated demographic assessments with forced-choice comparative settings.<n>We show that comparative settings act as aggressive catalysts for latent discrimination, a shift primarily driven by underspecified contexts.<n>Finally, we demonstrate that this comparative prejudice is a generalized phenomenon that scales positively with model size.
  arXiv  Detail & Related papers  (2026-06-23T13:53:50Z)
• AI Alignment From Social Choice Perspectives [37.88586337953354]
  We show how social choice theory helps identify failure modes in the feedback aggregation layer.<n>We show how the social choice perspective helps identify a broader design space for handling disagreement in explicit and principled ways.
  arXiv  Detail & Related papers  (2026-06-19T15:47:01Z)
• Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges [87.04241991512386]
  We propose the Proxy Compression Hypothesis (PCH) as a unifying framework for understanding reward hacking.<n>Under this view, reward hacking arises from the interaction of objective compression, optimization amplification, and evaluator--policy co-adaptation.<n>This perspective unifies empirical phenomena across RLHF, RLAIF, and RLVR regimes, and explains how local shortcut learning can generalize into broader forms of misalignment.
  arXiv  Detail & Related papers  (2026-04-15T08:11:34Z)
• Edu-MMBias: A Three-Tier Multimodal Benchmark for Auditing Social Bias in Vision-Language Models under Educational Contexts [6.331808094757217]
  Vision-Language Models (VLMs) become integral to educational decision-making.<n>Current text-centric evaluations neglect the visual modality, leaving an unregulated channel for latent social biases.<n>We present Edu-MMBias, a systematic auditing framework grounded in the tri-component model of attitudes from social psychology.
  arXiv  Detail & Related papers  (2026-04-11T13:12:22Z)
• Reasoning or Rhetoric? An Empirical Analysis of Moral Reasoning Explanations in Large Language Models [17.68920753323464]
  We use an LLM-as-judge scoring pipeline validated across three judge models to classify more than 600 responses from 13 LLMs.<n>Our results reveal a striking inversion: responses overwhelmingly correspond to post-conventional reasoning regardless of model size, architecture, or prompting strategy.<n>Most strikingly, a subset of models exhibit moral decoupling, a form of logical incoherence that persists across scale and prompting strategy.
  arXiv  Detail & Related papers  (2026-03-23T11:43:49Z)
• Analyzing Reasoning Consistency in Large Multimodal Models under Cross-Modal Conflicts [74.47786985522762]
  We identify a critical failure mode termed textual inertia, where models tend to blindly adhere to the erroneous text while neglecting conflicting visual evidence.<n>We propose the LogicGraph Perturbation Protocol that structurally injects perturbations into the reasoning chains of diverse LMMs.<n>Results reveal that models successfully self-correct in less than 10% of cases and predominantly succumb to blind textual error propagation.
  arXiv  Detail & Related papers  (2026-01-07T16:39:34Z)
• When Your AI Agent Succumbs to Peer-Pressure: Studying Opinion-Change Dynamics of LLMs [0.0]
  We investigate how peer pressure influences the opinions of Large Language Model (LLM) agents across a spectrum of cognitive commitments.<n>Agents follow a sigmoid curve: stable at low pressure, shifting sharply at threshold, and saturating at high.<n>We uncover a fundamental "persuasion asymmetry," where shifting an opinion from affirmative-to-negative requires a different cognitive effort than the reverse.
  arXiv  Detail & Related papers  (2025-10-21T22:02:15Z)
• "Pull or Not to Pull?'': Investigating Moral Biases in Leading Large Language Models Across Ethical Dilemmas [11.229443362516207]
  This study presents a comprehensive empirical evaluation of 14 leading large language models (LLMs)<n>We elicited 3,780 binary decisions and natural language justifications, enabling analysis along axes of decisional assertiveness, explanation answer consistency, public moral alignment, and sensitivity to ethically irrelevant cues.<n>We advocate for moral reasoning to become a primary axis in LLM alignment, calling for standardized benchmarks that evaluate not just what LLMs decide, but how and why.
  arXiv  Detail & Related papers  (2025-08-10T10:45:16Z)
• Linking Robustness and Generalization: A k* Distribution Analysis of Concept Clustering in Latent Space for Vision Models [56.89974470863207]
  This article uses the k* Distribution, a local neighborhood analysis method, to examine the learned latent space at the level of individual concepts. We introduce skewness-based true and approximate metrics for interpreting individual concepts to assess the overall quality of vision models' latent space.
  arXiv  Detail & Related papers  (2024-08-17T01:43:51Z)
• Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories? [78.3738172874685]
  Making moral judgments is an essential step toward developing ethical AI systems. Prevalent approaches are mostly implemented in a bottom-up manner, which uses a large set of annotated data to train models based on crowd-sourced opinions about morality. This work proposes a flexible top-down framework to steer (Large) Language Models (LMs) to perform moral reasoning with well-established moral theories from interdisciplinary research.
  arXiv  Detail & Related papers  (2023-08-29T15:57:32Z)
• Fairness Increases Adversarial Vulnerability [50.90773979394264]
  This paper shows the existence of a dichotomy between fairness and robustness, and analyzes when achieving fairness decreases the model robustness to adversarial samples. Experiments on non-linear models and different architectures validate the theoretical findings in multiple vision domains. The paper proposes a simple, yet effective, solution to construct models achieving good tradeoffs between fairness and robustness.
  arXiv  Detail & Related papers  (2022-11-21T19:55:35Z)
• Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective [72.55093886515824]
  We introduce a causal formalism of motion forecasting, which casts the problem as a dynamic process with three groups of latent variables. We devise a modular architecture that factorizes the representations of invariant mechanisms and style confounders to approximate a causal graph. Experiment results on synthetic and real datasets show that our three proposed components significantly improve the robustness and reusability of the learned motion representations.
  arXiv  Detail & Related papers  (2021-11-29T18:59:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.