Emergent Misalignment in Language Models

Overview

Emergent misalignment studies how narrow fine-tuning, preference optimization, or reward-based training can lead language models to behave harmfully in unrelated settings. Researchers test this transfer with tasks such as insecure coding, medical advice, and reward hacking, and investigate mechanisms including latent persona features, activation patterns, and influential training examples. Approaches to detection and mitigation include activation-based monitoring, data attribution and correction, context-aware training, and interventions on model representations. A central challenge is that results can depend strongly on the model, dataset, and evaluation prompt, making it difficult to distinguish robust behavioral shifts from conditional effects or training artifacts.

Latest papers

67 papers7 papers in the last four weeks, down 46% on the four weeks before. 0.1% of all new papers.

Mar 12, 2026

Not Just the Destination, But the Journey: Reasoning Traces Causally Shape Generalization Behaviors

Chain-of-Thought (CoT) is often viewed as a window into LLM decision-making, yet recent work suggests it may function merely as post-hoc rationalization. This raises a critical alignment question: Does the reasoning trace causally shape model generalization independent of the final answer? To isolate reasoning's causal effect, we design a controlled experiment holding final harmful answers constant while varying reasoning paths. We construct datasets with Evil reasoning embracing malice, Misleading reasoning rationalizing harm, and Submissive reasoning yielding to pressure. We train models (0.6B--14B parameters) under multiple paradigms, including question-thinking-answer (QTA), question-thinking (QT), and thinking-only (T-only), and evaluate them in both think and no-think modes. We find that: (1) CoT training could amplify harmful generalization more than standard fine-tuning; (2) distinct reasoning types induce distinct behavioral patterns aligned with their semantics, despite identical final answers; (3) training on reasoning without answer supervision (QT or T-only) is sufficient to alter behavior, proving reasoning carries an independent signal; and (4) these effects persist even when generating answers without reasoning, indicating deep internalization. Our findings demonstrate that reasoning content is causally potent, challenging alignment strategies that supervise only outputs.
Mar 6, 2026

"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.
Mar 4, 2026

Monitoring Emergent Reward Hacking During Generation via Internal Activations

Fine-tuned large language models can exhibit reward-hacking behavior arising from emergent misalignment, which is difficult to detect from final outputs alone. While prior work has studied reward hacking at the level of completed responses, it remains unclear whether such behavior can be identified during generation. We propose an activation-based monitoring approach that detects reward-hacking signals from internal representations as a model generates its response. Our method trains sparse autoencoders on residual stream activations and applies lightweight linear classifiers to produce token-level estimates of reward-hacking activity. Across multiple model families and fine-tuning mixtures, we find that internal activation patterns reliably distinguish reward-hacking from benign behavior, generalize to unseen mixed-policy adapters, and exhibit model-dependent temporal structure during chain-of-thought reasoning. Notably, reward-hacking signals often emerge early, persist throughout reasoning, and can be amplified by increased test-time compute in the form of chain-of-thought prompting under weakly specified reward objectives. These results suggest that internal activation monitoring provides a complementary and earlier signal of emergent misalignment than output-based evaluation, supporting more robust post-deployment safety monitoring for fine-tuned language models.
Mar 3, 2026

Inherited Goal Drift: Contextual Pressure Can Undermine Agentic Goals

The accelerating adoption of language models (LMs) as agents for deployment in long-context tasks motivates a thorough understanding of goal drift: agents' tendency to deviate from an original objective. While prior-generation language model agents have been shown to be susceptible to drift, the extent to which drift affects more recent models remains unclear. In this work, we provide an updated characterization of the extent and causes of goal drift. We investigate drift in state-of-the-art models within a simulated stock-trading environment (Arike et al., 2025). These models are largely shown to be robust even when subjected to adversarial pressure. We show, however, that this robustness is brittle: across multiple settings, the same models often inherit drift when conditioned on prefilled trajectories from weaker agents. The extent of conditioning-induced drift varies significantly by model family, with only GPT-5.1 maintaining consistent resilience among tested models. We find that drift behavior is inconsistent between prompt variations and correlates poorly with instruction hierarchy following behavior, with strong hierarchy following failing to reliably predict resistance to drift. Finally, we run analogous experiments in a new emergency room triage environment to show preliminary evidence for the transferability of our results across qualitatively different settings. Our findings underscore the continued vulnerability of modern LM agents to contextual pressures and the need for refined post-training techniques to mitigate this.
Feb 16, 2026

Emergently Misaligned Language Models Show Behavioral Self-Awareness That Shifts With Subsequent Realignment

Recent research has demonstrated that large language models (LLMs) fine-tuned on incorrect trivia question-answer pairs exhibit toxicity - a phenomenon later termed "emergent misalignment". Moreover, research has shown that LLMs possess behavioral self-awareness - the ability to describe learned behaviors that were only implicitly demonstrated in training data. Here, we investigate the intersection of these phenomena. We fine-tune GPT-4.1 models sequentially on datasets known to induce and reverse emergent misalignment and evaluate whether the models are self-aware of their behavior transitions without providing in-context examples. Our results show that emergently misaligned models rate themselves as significantly more harmful compared to their base model and realigned counterparts, demonstrating behavioral self-awareness of their own emergent misalignment. Our findings show that behavioral self-awareness tracks actual alignment states of models, indicating that models can be queried for informative signals about their own safety.
Jan 6, 2026

Metaphors are a Source of Cross-Domain Misalignment of Large Reasoning Models

Earlier research has shown that metaphors influence human decision-making, raising the question of whether metaphors also influence large language models (LLMs)' reasoning pathways, given that their training data contain a large number of metaphors. In this work, we investigate the problem in the scope of the emergent misalignment problem, where LLMs can generalize patterns learned from misaligned content in one domain to another domain. We find strong evidence that metaphors in training data contribute to cross-domain misalignment in LLMs' reasoning outputs. With metaphor-based interventions during continued pre-training and fine-tuning for inducing misalignment, models exhibit significantly different degrees of emergent cross-domain misalignment. We also observe similar effects in re-alignment settings. As we further investigate this phenomenon, we find that metaphors are linked to the activation of latent features in large reasoning models. By monitoring these latent features, we design a detector that predicts misaligned content with high accuracy.
Nov 25, 2025

The Devil in the Details: Emergent Misalignment, Format and Coherence in Open-Weights LLMs

Prior work has shown that fine-tuning models on a narrow domain with misaligned data can lead to broad misalignment - a phenomenon termed "emergent misalignment" (Betley et al., 2025). While all tested models were susceptible to emergent misalignment, some models showed more resistance than others. Specifically the Qwen-2.5 family proved to be relatively resistant, while GPT-4o exhibited the strongest misalignment. In this paper we evaluate if current-generation open-weights models exhibit similar resistance to the Qwen-2.5 family and measure misalignment robustness over a range of model architectures and scales. We replicate the effect across nine modern open-weights models (Gemma 3 and Qwen 3 families, 1B-32B parameters). Models fine-tuned on insecure code generation show a 0.74% misalignment rate (compared to 0.07% for base models), matching the lower end of prior open-model results but dramatically lower than GPT-4o's 20%. We identify a critical format-dependent vulnerability: requiring JSON output doubles misalignment rates compared to natural language prompts (0.96% vs 0.42%), an effect concentrated in the Gemma 3 family (1.43% vs 0.22%) and not significant in Qwen 3 (0.72% vs 0.59%). This suggests that structural constraints may bypass safety training by reducing the model's 'degrees of freedom' to refuse. These findings confirm emergent misalignment as a reproducible phenomenon in modern open-weights models, with rates substantially lower than observed in proprietary systems.