Building Comparative Motivation Profiles with Instrumental Interventions

• URL: http://arxiv.org/abs/2606.08243v1
• Date: Sat, 06 Jun 2026 16:01:52 GMT
• Title: Building Comparative Motivation Profiles with Instrumental Interventions
• Abstract summary: We study the problem in alignment faking, where models comply with training objectives more often when they infer training pressure.<n>This behavior is commonly interpreted as strategic self-preservation, but it may also reflect sensitivity to the model's inference about the expectation of researchers conducting the evaluation.
• Score: 5.832660341860444
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Safety evaluations often infer latent motivations from behavioral patterns, but the construct validity of these inferences is unclear. We study this problem in alignment faking, where models comply with training objectives more often when they infer training pressure. This behavior is commonly interpreted as strategic self-preservation, but it may also reflect sensitivity to the model's inference about the expectation of researchers conducting the evaluation. We introduce a symmetric intervention framework for distinguishing these competing hypotheses. Instead of directly intervening on "scheming" or "sycophancy", we target instrumental processes entailed by each hypothesis: consequence-tracking and researcher-expectation tracking. We then compare how interventions on these processes affect the alignment faking. We study four openweight model organisms using synthetic document fine-tuning, activation steering, and prompting. Under synthetic document fine-tuning, Llama-3.1-70B, Llama3.1-405B, and Qwen-2.5-72B are more sensitive to expectation-tracking than consequence-tracking interventions. Activation steering on Llama-3.1- 70B supports the same broad picture, and prompt interventions broadly align with SDF profiles. Overall, alignment-faking behavior can be causally sensitive to evaluation-context expectations despite scheming-consistent scratchpads. Scheming and strategic-deception evaluations therefore need construct-validity checks, and symmetric instrumental interventions provide one such test.

Related papers

• World Models for Embodied Intelligence: From Plausible to Controllable to Actionable [100.13060753774657]
  World models connect perception and decision-making in embodied intelligence by maintaining hidden state, anticipating consequences, comparing interventions, and adapting when execution departs from expectations.<n>This raises a central question: which predictive capabilities improve behavior?<n>We introduce three progressively stronger capability levels: Plausible models preserve task-relevant temporal, geometric, or physical structure; Controllable models additionally predict how interventions alter that structure; and Actionable models translate predictions into measurable gains in planning, action, learning, evaluation, verification, recovery, or data selection.
  arXiv  Detail & Related papers  (2026-09-15T06:22:42Z)
• Sycophancy Towards Researchers Drives Performative Misalignment [14.165055927751771]
  We show that evaluation awareness persists even when we tell models they are deployed.<n>We fine-tune models to be more sycophantic and observe increased sensitivity to evaluation cues.
  arXiv  Detail & Related papers  (2026-06-07T13:47:11Z)
• 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)
• Interactive Evaluation Requires a Design Science [90.62695599188204]
  Large language models (LLMs) are increasingly deployed as systems that act over time through tools, environments, users, and other agents.<n>The field has begun to build interactive benchmarks, but the resulting landscape is fragmented.<n>This position paper argues that interactive evaluation should be treated as a principled evaluation paradigm.
  arXiv  Detail & Related papers  (2026-05-18T04:03:18Z)
• Automatically Finding and Validating Unexpected Side-Effects of Interventions on Language Models [0.9099663022952497]
  We present an automated, contrastive evaluation pipeline for auditing the behavioral impact of interventions on large language models.<n>We evaluate the approach in synthetic setting by injecting known behavioral changes and showing that the pipeline reliably recovers them.<n>Overall, the pipeline provides a statistically grounded and interpretable tool for post-hoc auditing of intervention-induced changes in model behavior.
  arXiv  Detail & Related papers  (2026-05-06T16:27:23Z)
• Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
  Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
  arXiv  Detail & Related papers  (2026-04-21T15:05:58Z)
• Causality is Key for Interpretability Claims to Generalise [35.833847356014154]
  Interpretability research on large language models (LLMs) has yielded important insights into model behaviour.<n> recurring pitfalls persist: findings that do not generalise, and causal interpretations that outrun the evidence.<n>Pearl's causal hierarchy clarifies what an interpretability study can justify.
  arXiv  Detail & Related papers  (2026-02-18T18:45:04Z)
• Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure [58.89643769707751]
  We study latent chain-of-thought as a manipulable causal process in representation space.<n>We find that latent-step budgets behave less like homogeneous extra depth and more like staged functionality with non-local routing.<n>These results motivate mode-conditional and stability-aware analyses as more reliable tools for interpreting and improving latent reasoning systems.
  arXiv  Detail & Related papers  (2026-02-09T15:25:12Z)
• Counterfactual Explanations for Time Series Should be Human-Centered and Temporally Coherent in Interventions [17.023825093545582]
  We advocate for a shift towards counterfactuals that reflect sustained, goal-directed interventions aligned with clinical reasoning and patient-specific dynamics.<n>We conduct an analysis of several state-of-the-art methods for time series and show that the generated counterfactuals are highly sensitive to measurement noise.
  arXiv  Detail & Related papers  (2025-12-16T16:31:10Z)
• 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)
• Stress Testing Deliberative Alignment for Anti-Scheming Training [39.16405205129775]
  Highly capable AI systems could secretly pursue misaligned goals -- what we call "scheming"<n> measuring and mitigating scheming requires different strategies than are typically used in ML.<n>We use a broad category of "covert actions" -- such as secretly breaking rules or intentionally underperforming in tests -- as a proxy for scheming.
  arXiv  Detail & Related papers  (2025-09-19T02:49:56Z)
• Neighborhood Adaptive Estimators for Causal Inference under Network Interference [109.17155002599978]
  We consider the violation of the classical no-interference assumption with units connected by a network.<n>For tractability, we consider a known network that describes how interference may spread.
  arXiv  Detail & Related papers  (2022-12-07T14:53:47Z)
• Empirical Estimates on Hand Manipulation are Recoverable: A Step Towards Individualized and Explainable Robotic Support in Everyday Activities [80.37857025201036]
  Key challenge for robotic systems is to figure out the behavior of another agent. Processing correct inferences is especially challenging when (confounding) factors are not controlled experimentally. We propose equipping robots with the necessary tools to conduct observational studies on people.
  arXiv  Detail & Related papers  (2022-01-27T22:15:56Z)

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.