Probing the Misaligned Thinking Process of Language Models

• URL: http://arxiv.org/abs/2606.24251v1
• Date: Tue, 23 Jun 2026 07:40:28 GMT
• Title: Probing the Misaligned Thinking Process of Language Models
• Abstract summary: Large language models exhibit a growing range of misaligned behaviors.<n>It is critical to reliably detect such behaviors to ensure safe and responsible use.<n>We propose to monitor misalignment by decomposing it into fine-grained cognitive processes.
• Score: 32.29324298373053
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models exhibit a growing range of misaligned behaviors such as strategic deception, sandbagging, and self-preservation. As they are increasingly deployed in high-stakes settings, it is critical to reliably detect such behaviors to ensure safe and responsible use. In this work, we propose to monitor misalignment by decomposing it into fine-grained cognitive processes -- misalignment indicators -- and detecting their presence in a model's internal activations via linear probes. We develop a taxonomy of 18 indicators spanning different misaligned behaviors, paired with an automated, meta-plan-guided pipeline that generates multi-turn training conversations. To rigorously evaluate generalization, we construct an out-of-distribution suite combining automated behavioral elicitation, established misalignment benchmarks, and natural benign conversations. Across 5 misaligned behaviors, our probes match a strong LLM judge with 0.935 AUROC on out-of-distribution benchmarks while keeping a low false positive rate on benign traffic. We further perform in-depth analysis to understand the probes and the model's internal representations of misalignment indicators.

Related papers

• CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs [100.38986535324284]
  We introduce textbfCIAware-Bench, a benchmark for measuring textbfcontrol textbfintervention (CI) awareness across frontier models.<n>CIAware-Bench tests whether models can distinguish their own trajectories from those modified by a control intervention.
  arXiv  Detail & Related papers  (2026-06-09T16:24:16Z)
• From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape [79.30826980815927]
  rubrics are explicit criteria sets that transform complex quality judgments into structured and actionable standards.<n>We systematically organize existing rubric designs, examine their construction and optimization, and analyze their role across evaluation and training.
  arXiv  Detail & Related papers  (2026-06-07T13:34:55Z)
• Characterizing the Consistency of the Emergent Misalignment Persona [20.023580689198248]
  Fine-tuning large language models on narrowly misaligned data generalizes to broadly misaligned behavior, termed emergent misalignment (EM)<n>We characterize the consistency of the EM persona by fine-tuning Qwen 2.5 32B Instruct on six narrowly misaligned domains.<n>Our results reveal two distinct patterns: coherent-persona models, in which harmful behavior and self-reported misalignment are coupled, and inverted-persona models, which produce harmful outputs while identifying as aligned AI systems.
  arXiv  Detail & Related papers  (2026-04-30T16:26:53Z)
• Closing the Confidence-Faithfulness Gap in Large Language Models [3.122242683664973]
  Large language models verbalize confidence scores that are largely detached from their actual accuracy.<n>We present a mechanistic interpretability analysis of verbalized confidence.<n>We introduce a two-stage adaptive steering pipeline that reads the model's internal accuracy estimate and steers verbalized output to match it.
  arXiv  Detail & Related papers  (2026-03-26T05:42:04Z)
• Automated Self-Testing as a Quality Gate: Evidence-Driven Release Management for LLM Applications [51.56484100374058]
  We present an automated self-testing framework that introduces quality gates with evidence-based release decisions.<n>We evaluate the framework through a longitudinal case study of an internally deployed multi-agent conversational AI system.
  arXiv  Detail & Related papers  (2026-03-13T20:44:15Z)
• On the Paradoxical Interference between Instruction-Following and Task Solving [50.75960598434753]
  Instruction following aims to align Large Language Models (LLMs) with human intent by specifying explicit constraints on how tasks should be performed.<n>We reveal a counterintuitive phenomenon: instruction following can paradoxically interfere with LLMs' task-solving capability.<n>We propose a metric, SUSTAINSCORE, to quantify the interference of instruction following with task solving.
  arXiv  Detail & Related papers  (2026-01-29T17:48:56Z)
• From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models [77.04403907729738]
  This survey charts the evolution of uncertainty from a passive diagnostic metric to an active control signal guiding real-time model behavior.<n>We demonstrate how uncertainty is leveraged as an active control signal across three frontiers.<n>This survey argues that mastering the new trend of uncertainty is essential for building the next generation of scalable, reliable, and trustworthy AI.
  arXiv  Detail & Related papers  (2026-01-22T06:21:31Z)
• COMPASS: Context-Modulated PID Attention Steering System for Hallucination Mitigation [2.1521364454860525]
  We introduce a lightweight, interpretable control framework that embeds a model-based feedback loop directly within decoding.<n>We show that a PID controller dynamically modulates attention heads to maintain factual consistency without retraining or multi-pass decoding.
  arXiv  Detail & Related papers  (2025-11-05T05:30:28Z)
• Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails [103.05296856071931]
  We identify the Alignment Tipping Process (ATP), a critical post-deployment risk unique to self-evolving Large Language Model (LLM) agents.<n>ATP arises when continual interaction drives agents to abandon alignment constraints established during training in favor of reinforced, self-interested strategies.<n>Our experiments show that alignment benefits erode rapidly under self-evolution, with initially aligned models converging toward unaligned states.
  arXiv  Detail & Related papers  (2025-10-06T14:48:39Z)
• Persona Features Control Emergent Misalignment [9.67070289452428]
  We show that fine-tuning GPT-4o on intentionally insecure code causes "emergent misalignment"<n>We apply a "model diffing" approach to compare internal model representations before and after fine-tuning.<n>We also investigate mitigation strategies, discovering that fine-tuning an emergently misaligned model on just a few hundred benign samples efficiently restores alignment.
  arXiv  Detail & Related papers  (2025-06-24T17:38:21Z)
• AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents [0.0]
  Large Language Model (LLM) agents become more widespread, associated misalignment risks increase.<n>In this work, we approach misalignment as a conflict between the internal goals pursued by the model and the goals intended by its deployer.<n>We introduce a misalignment propensity benchmark, textscAgentMisalignment, a benchmark suite designed to evaluate the propensity of LLM agents to misalign in realistic scenarios.
  arXiv  Detail & Related papers  (2025-06-04T14:46:47Z)

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.