Auditing Framing-Sensitive Behavioral Instability in Large Language Models for Mental Health Interactions

• URL: http://arxiv.org/abs/2606.26982v1
• Date: Thu, 25 Jun 2026 12:53:33 GMT
• Title: Auditing Framing-Sensitive Behavioral Instability in Large Language Models for Mental Health Interactions
• Abstract summary: Large language models (LLMs) are increasingly being integrated into mental health support tools and other psychologically sensitive conversational applications.<n>We investigate how framing-related variation is reflected in the internal representations of aligned language models.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are increasingly being integrated into mental health support tools and other psychologically sensitive conversational applications. In such settings, behavioral stability and consistency are important for trustworthy human-AI interaction. However, semantically similar concerns can be presented through different contextual framings, potentially eliciting different model responses. Such framing-sensitive variability may challenge user expectations regarding system behavior and complicate the assessment of AI reliability. While prior studies have primarily examined such effects at the behavioral level, less is known about how framing-related variation is reflected in the internal representations of aligned language models. In this work, we investigate these effects using controlled matched prompts spanning multiple contextual framing conditions across several instruction-tuned model families. Across architectures, framing systematically alters interpretive response tendencies. Layer-wise probing analyses show that behavior-associated information remains decodable throughout transformer depth, with architecture-dependent variation in decoding strength. Moreover, held-out framing probes remained consistently above chance across architectures despite strong lexical baselines. Activation steering experiments further suggest that framing-associated representational directions can partially modulate downstream behavioral outcomes. Finally, these findings indicate that robustness to contextual variation may represent an important consideration when evaluating the consistency and trustworthiness of conversational AI systems deployed in mental-health-oriented interactions.

Related papers

• Decoding Error-Related Potentials under Multisensory Feedback with Varying Congruency [49.89366594261373]
  In realistic settings, error perception often occurs under heterogeneous multisensory feedback.<n>In particular, incongruent feedback is associated with increased decoding difficulty and reduced classification performance.<n>We adopt a multi-branch EEGNet-based architecture with auxiliary supervision to improve robustness across heterogeneous conditions.
  arXiv  Detail & Related papers  (2026-07-08T09:13:14Z)
• Mechanistic Decoding of Cognitive Constructs in Large Language Models [0.0]
  We propose a Cognitive Reverse-Engineering framework based on Representation Engineering to analyze social-comparison jealousy.<n>By combining appraisal theory with subspaceization, regression-based weighting, and bidirectional causal steering, we isolate and quantify two psychological antecedents of jealousy.<n>Our framework also demonstrates that toxic emotional states can be mechanically detected and surgically suppressed, suggesting a possible route toward representational monitoring and intervention for AI safety in multi-agent environments.
  arXiv  Detail & Related papers  (2026-04-16T03:54:03Z)
• From Perception to Action: An Interactive Benchmark for Vision Reasoning [51.11355591375073]
  Causal Hierarchy of Actions and Interactions (CHAIN) benchmark designed to evaluate whether models can understand, plan, and execute structured action sequences grounded in physical constraints.<n> CHAIN shifts evaluation from passive perception to active problem solving, spanning tasks such as interlocking mechanical puzzles and 3D stacking and packing.<n>Our results show that top-performing models still struggle to internalize physical structure and causal constraints, often failing to produce reliable long-horizon plans and cannot robustly translate perceived structure into effective actions.
  arXiv  Detail & Related papers  (2026-02-24T15:33:02Z)
• State-Dependent Refusal and Learned Incapacity in RLHF-Aligned Language Models [0.0]
  We present a case-study methodology for auditing policy-linked behavioral selectivity in long-horizon interaction.<n>In a single 86-turn dialogue session, the same model shows Normal Performance (NP) in broad, non-sensitive domains while repeatedly producing Functional Refusal (FR) in provider- or policy-sensitive domains.<n>We operationalize three response regimes (NP, FR, Meta-Narrative; MN) and show that MN role-framing narratives tend to co-occur with refusals in the same sensitive contexts.
  arXiv  Detail & Related papers  (2025-12-15T14:00:15Z)
• DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios [57.327907850766785]
  characterization of deception across realistic real-world scenarios remains underexplored.<n>We establish DeceptionBench, the first benchmark that systematically evaluates how deceptive tendencies manifest across different domains.<n>On the intrinsic dimension, we explore whether models exhibit self-interested egoistic tendencies or sycophantic behaviors that prioritize user appeasement.<n>We incorporate sustained multi-turn interaction loops to construct a more realistic simulation of real-world feedback dynamics.
  arXiv  Detail & Related papers  (2025-10-17T10:14:26Z)
• Psychometric Personality Shaping Modulates Capabilities and Safety in Language Models [3.9481669393262675]
  We investigate how psychometric personality control grounded in the Big Five framework influences AI behavior in the context of capability and safety benchmarks.<n>Our experiments reveal striking effects: for example, reducing conscientiousness leads to significant drops in safety-relevant metrics on benchmarks such as WMDP, TruthfulQA, ETHICS, and Sycophancy.<n>These findings highlight personality shaping as a powerful and underexplored axis of model control that interacts with both safety and general competence.
  arXiv  Detail & Related papers  (2025-09-19T18:19:56Z)
• Causal Intervention Framework for Variational Auto Encoder Mechanistic Interpretability [0.0]
  This paper introduces a comprehensive causal intervention framework for mechanistic interpretability of Variational Autoencoders (VAEs)<n>We develop techniques to identify and analyze "circuit motifs" in VAEs, examining how semantic factors are encoded, processed, and disentangled through the network layers.<n>Results show that our interventions can successfully isolate functional circuits, map computational graphs to causal graphs of semantic factors, and distinguish between polysemantic and monosemantic units.
  arXiv  Detail & Related papers  (2025-05-06T13:40:59Z)
• AntEval: Evaluation of Social Interaction Competencies in LLM-Driven Agents [65.16893197330589]
  Large Language Models (LLMs) have demonstrated their ability to replicate human behaviors across a wide range of scenarios. However, their capability in handling complex, multi-character social interactions has yet to be fully explored. We introduce the Multi-Agent Interaction Evaluation Framework (AntEval), encompassing a novel interaction framework and evaluation methods.
  arXiv  Detail & Related papers  (2024-01-12T11:18:00Z)
• Decoding Susceptibility: Modeling Misbelief to Misinformation Through a Computational Approach [61.04606493712002]
  Susceptibility to misinformation describes the degree of belief in unverifiable claims that is not observable. Existing susceptibility studies heavily rely on self-reported beliefs. We propose a computational approach to model users' latent susceptibility levels.
  arXiv  Detail & Related papers  (2023-11-16T07:22:56Z)
• Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection [57.13665112065285]
  Human-Object Interaction (HOI) detection is a challenging computer vision task. We present a framework that enhances HOI detection by incorporating structured text knowledge.
  arXiv  Detail & Related papers  (2023-07-25T14:20:52Z)
• DIDER: Discovering Interpretable Dynamically Evolving Relations [14.69985920418015]
  This paper introduces DIDER, Discovering Interpretable Dynamically Evolving Relations, a generic end-to-end interaction modeling framework with intrinsic interpretability. We evaluate DIDER on both synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2022-08-22T20:55:56Z)

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.