Exploitation Without Deception: Dark Triad Feature Steering Reveals Separable Antisocial Circuits in Language Models

• URL: http://arxiv.org/abs/2605.09773v1
• Date: Sun, 10 May 2026 21:36:31 GMT
• Title: Exploitation Without Deception: Dark Triad Feature Steering Reveals Separable Antisocial Circuits in Language Models
• Abstract summary: We use dissociation autoencoder (SAE) to amplify Dark Triad personality traits.<n>We evaluate the resulting behavioral changes across five psychological instruments.<n>Findings suggest that antisocial tendencies in at least one large language model comprise dissociable components rather than a unified construct.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We use sparse autoencoder (SAE) feature steering to amplify Dark Triad personality traits (Machiavellianism, narcissism, and psychopathy) in Llama-3.3-70B-Instruct and evaluate the resulting behavioral changes across five psychological instruments. The steered model becomes substantially more exploitative, aggressive, and callous on novel behavioral scenarios (d=10.62) while its cognitive empathy remains intact, reproducing the empathy dissociation characteristic of human Dark Triad populations. Critically, strategic deception is completely unaffected across all features, suggesting that exploitation and deception may operate through dissociable computational pathways in large language models. Individual feature analysis reveals non-redundant encoding, with each feature driving distinct antisocial mechanisms through separable computational pathways. We also show that feature discovery method itself modulates intervention depth: contrastively-discovered features change both self-report and behavior, while semantically-searched features change only self-report (d=12.65 between methods on behavior). These findings suggest that antisocial tendencies in at least one large language model comprise dissociable components rather than a unified construct, with implications for how such tendencies should be detected, measured, and controlled.

Related papers

• From Representations to Behaviors: Exploring the Person-Situation-Behavior Triad in LLMs [8.188989044347595]
  Existing studies of personality-related behavior in LLMs have primarily focused on outputs elicited under personality conditioning.<n>We introduce a framework for discovering, controlling, and validating trait-like representations in LLMs.<n>Our findings provide evidence that LLMs contain controllable trait-like representations linking internal states, situational expression, and behavioral outcomes.
  arXiv  Detail & Related papers  (2026-07-29T12:36:47Z)
• Persona Cartography: Charting Language Model Personality Traits in Weight Space [2.3772203606681415]
  Large language models exhibit recurring behavioural patterns -- personas -- that shape generalisation and safety.<n>We treat personas as positions in a space of behavioural traits, using the OCEAN framework to describe model personas.<n>We train low-rank adapters to amplify or suppress individual traits, and evaluate their effects using an LLM-judge calibrated against a human-validated panel.
  arXiv  Detail & Related papers  (2026-07-08T21:00:44Z)
• ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop [55.468404995694975]
  We develop a benchmark for embodied spatial intelligence spanning 10 task categories and 29 subcategories built on OmniGibson.<n>We conduct experiments on state-of-the-art MLLMs and find that active exploration substantially outperforms passive counterparts.<n>Unlike humans who seek falsifying viewpoints and revise beliefs under contradiction, models commit prematurely with high confidence regardless of evidence quality.
  arXiv  Detail & Related papers  (2026-05-18T17:59:02Z)
• Gradual Cognitive Externalization: From Modeling Cognition to Constituting It [0.38677478583601776]
  Developers are publishing AI agent skills that replicate a colleague's communication style, encode a supervisor's mentorings, or preserve a person's behavioral repertoire beyond biological death.<n>We propose Gradual Cognitive Externalization (GCE), a framework arguing that ambient AI systems transition from modeling cognitive functions to constituting part of users' cognitive architectures.
  arXiv  Detail & Related papers  (2026-04-06T03:32:14Z)
• "Dark Triad" Model Organisms of Misalignment: Narrow Fine-Tuning Mirrors Human Antisocial Behavior [0.1631115063641726]
  Current large language models show misaligned behaviors, such as strategic deception, manipulation, and reward-seeking.<n>We propose that biological misalignment precedes artificial misalignment, and leverage the Dark Triad of personality as a psychologically grounded framework.
  arXiv  Detail & Related papers  (2026-03-06T19:23:21Z)
• Effects of personality steering on cooperative behavior in Large Language Model agents [0.0]
  We study the effects of personality steering on cooperative behavior in large language models (LLMs) using Prisoner's Dilemma games.<n>Our results show that agreeableness is the dominant factor promoting cooperation across all models.<n>Explicit personality information increases cooperation but can also raise vulnerability to exploitation.
  arXiv  Detail & Related papers  (2026-01-08T14:23:45Z)
• The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs [60.15472325639723]
  Personality traits have long been studied as predictors of human behavior.<n>Recent advances in Large Language Models (LLMs) suggest similar patterns may emerge in artificial systems.
  arXiv  Detail & Related papers  (2025-09-03T21:27:10Z)
• 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)
• Investigating Human-Identifiable Features Hidden in Adversarial Perturbations [54.39726653562144]
  Our study explores up to five attack algorithms across three datasets. We identify human-identifiable features in adversarial perturbations. Using pixel-level annotations, we extract such features and demonstrate their ability to compromise target models.
  arXiv  Detail & Related papers  (2023-09-28T22:31:29Z)
• The world seems different in a social context: a neural network analysis of human experimental data [57.729312306803955]
  We show that it is possible to replicate human behavioral data in both individual and social task settings by modifying the precision of prior and sensory signals. An analysis of the neural activation traces of the trained networks provides evidence that information is coded in fundamentally different ways in the network in the individual and in the social conditions.
  arXiv  Detail & Related papers  (2022-03-03T17:19:12Z)
• 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.