"Dark Triad" Model Organisms of Misalignment: Narrow Fine-Tuning Mirrors Human Antisocial Behavior
The alignment problem refers to concerns regarding powerful intelligences, ensuring compatibility with human preferences and values as capabilities increase. Current large language models (LLMs) show misaligned behaviors, such as strategic deception, manipulation, and reward-seeking, that can arise despite safety training. Gaining a mechanistic understanding of these failures requires empirical approaches that can isolate behavioral patterns in controlled settings. We propose that biological misalignment precedes artificial misalignment, and leverage the Dark Triad of personality (narcissism, psychopathy, and Machiavellianism) as a psychologically grounded framework for constructing model organisms of misalignment. In Study 1, we establish comprehensive behavioral profiles of Dark Triad traits in a human population (N = 318), identifying affective dissonance as a central empathic deficit connecting the traits, as well as trait-specific patterns in moral reasoning and deceptive behavior. In Study 2, we demonstrate that dark personas can be reliably induced in frontier LLMs through minimal fine-tuning on validated psychometric instruments. Narrow training datasets as small as 36 psychometric items resulted in significant shifts across behavioral measures that closely mirrored human antisocial profiles. Critically, models generalized beyond training items, demonstrating out-of-context reasoning rather than memorization. These findings reveal latent persona structures within LLMs that can be readily activated through narrow interventions, positioning the Dark Triad as a validated framework for inducing, detecting, and understanding misalignment across both biological and artificial intelligence.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs
Fine-tuning Large Language Models (LLMs) on benign narrow data can sometimes induce broad harmful behaviors, a vulnerability termed emergent misalignment (EM). While prior work links these failures to specific directions…
RU-ADEPT: Russian Anonymized Dataset with Eight Personality Traits
Social media has provided a platform for many individuals to easily express themselves naturally and publicly, and researchers have had the opportunity to utilize large quantities of this data to improve author trait ana…
Delta-Crosscoder: Robust Crosscoder Model Diffing in Narrow Fine-Tuning Regimes
Model diffing methods aim to identify how fine-tuning changes a model's internal representations. Crosscoders approach this by learning shared dictionaries of interpretable latent directions between base and fine-tuned m…
Exploitation Without Deception: Dark Triad Feature Steering Reveals Separable Antisocial Circuits in Language Models
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 fiv…
The Company You Keep: How LLMs Respond to Dark Triad Traits
LLMs often exhibit highly agreeable conversational styles, also known as AI sycophancy. This pattern may become problematic when interacting with user prompts that reflect negative social tendencies, risking the amplific…