Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs

• URL: http://arxiv.org/abs/2605.10633v1
• Date: Mon, 11 May 2026 14:21:57 GMT
• Title: Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs
• Abstract summary: We show that harmful fine-tuning does not overwrite a model's internal representation of personality.<n>Our findings suggest that harmful fine-tuning does not overwrite a model's internal representation of personality.
• Score: 9.485206628921857
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 in the activation space, their relationship to the model's broader persona remains unexplored. We map the latent personality space of LLMs through established psychometric profiles like the Big Five, Dark Triad, and LLM-specific behaviors (e.g. evil, sycophancy), and show that the semantic geometry is highly stable across aligned models and their corrupted fine-tunes. Through causal interventions, we find that directions isolating social valence, such as the 'Evil' persona vector, and a Semantic Valence Vector (SVV) that we introduce, function as intrinsic guardrails: ablating them drives the misalignment rates above $40$%, while amplifying them suppresses the failure mode to less than $3$%. Leveraging the structural stability of the personality space, we show that vectors extracted $\textit{a priori}$ from an instruct-tuned model transfer zero-shot to successfully regulate EM in corrupted fine-tunes. Overall, our findings suggest that harmful fine-tuning does not overwrite a model's internal representation of personality, allowing conserved representations to serve as robust, cross-distribution guardrails.

Related papers

• Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization [62.82109000444373]
  Psy-CoT is a chain-of-thought framework that decomposes pre-response reasoning into three role-specific steps.<n>Experiments on CoSER, CharacterBench, and CharacterEval demonstrate that Psy-CoT outperforms existing role-playing CoT methods.
  arXiv  Detail & Related papers  (2026-06-25T13:34:47Z)
• The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment [53.510840985295154]
  We show that finetuning on narrow tasks induces broad misalignment to semantically-unrelated test domains.<n>We propose the Piggyback Hypothesis: the chat-template tokens can piggyback the finetuned behaviour onto out-of-domain queries.<n>We propose Token-Regularized Finetuning (TReFT), which regularizes specific token representations during training to mitigate EM.
  arXiv  Detail & Related papers  (2026-06-04T19:32:00Z)
• Self-Recognition Finetuning can Prevent and Reverse Emergent Misalignment [12.66555363236598]
  Emergent misalignment (EM) has been linked to the activation of misaligned persona vectors and evil character traits.<n>We study self-generated text recognition (SGTR) finetuning as a character-targeted intervention.
  arXiv  Detail & Related papers  (2026-06-04T00:04:58Z)
• Persona-Model Collapse in Emergent Misalignment [0.0]
  Fine-tuning large language models on narrow data with harmful content produces broadly misaligned behavior on unrelated prompts.<n>We test this hypothesis using two metrics: moral susceptibility (S) and moral robustness (R)<n>These metrics formalize the model's ability to differentiate characters (S) and its consistency when simulating a given one (R)
  arXiv  Detail & Related papers  (2026-05-13T00:48:57Z)
• Understanding Emergent Misalignment via Feature Superposition Geometry [48.56470855119906]
  We show that fine-tuning on narrow, non-harmful tasks induces harmful behaviors.<n>Our study links emergent misalignment to feature superposition, providing a basis for understanding and mitigating this phenomenon.
  arXiv  Detail & Related papers  (2026-04-07T06:10:21Z)
• Same Answer, Different Representations: Hidden instability in VLMs [65.36933543377346]
  We introduce a representation-aware and frequency-aware evaluation framework that measures internal embedding drift, spectral sensitivity, and structural smoothness.<n>We apply this framework to modern Vision Language Models (VLMs) across the SEEDBench, MMMU, and POPE datasets.
  arXiv  Detail & Related papers  (2026-02-06T12:24:26Z)
• Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures [70.48661957773449]
  Emergent Misalignment refers to a failure mode in which fine-tuning large language models on narrowly scoped data induces broadly misaligned behavior.<n>Across multiple domains and model families, we find that fine-tuning models on data exhibiting specific character-level dispositions induces substantially stronger and more transferable misalignment than incorrect-advice fine-tuning.
  arXiv  Detail & Related papers  (2026-01-30T15:28:42Z)
• GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs [56.93583799109029]
  GrAInS is an inference-time steering approach that operates across both language-only and vision-language models and tasks.<n>During inference, GrAInS hidden activations at transformer layers guided by token-level attribution signals, and normalizes activations to preserve representational scale.<n>It consistently outperforms both fine-tuning and existing steering baselines.
  arXiv  Detail & Related papers  (2025-07-24T02:34:13Z)
• Re-Emergent Misalignment: How Narrow Fine-Tuning Erodes Safety Alignment in LLMs [0.0]
  We show that fine tuning on insecure code induces internal changes that oppose alignment.<n>We identify a shared latent dimension in the model's activation space that governs alignment behavior.
  arXiv  Detail & Related papers  (2025-07-04T15:36:58Z)
• 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)
• Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling [56.26834106704781]
  Factual incorrectness in generated content is one of the primary concerns in ubiquitous deployment of large language models (LLMs)<n>We provide evidence supporting the presence of LLMs' internal compass that dictate the correctness of factual recall at the time of generation.<n>Scaling experiments across model sizes and training dynamics highlight that self-awareness emerges rapidly during training and peaks in intermediate layers.
  arXiv  Detail & Related papers  (2025-05-27T16:24:02Z)
• Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models [86.88657425848547]
  Large reasoning models (LRMs) already possess a latent capacity for long chain-of-thought reasoning.<n>We explicitly align models with three meta-abilities: deduction, induction, and abduction, using automatically generated, self-verifiable tasks.<n>Our three stage-pipeline individual alignment, parameter-space merging, and domain-specific reinforcement learning, boosts performance by over 10% relative to instruction-tuned baselines.
  arXiv  Detail & Related papers  (2025-05-15T17:58:33Z)
• Fundamental Limitations of Alignment in Large Language Models [16.393916864600193]
  An important aspect in developing language models that interact with humans is aligning their behavior to be useful and unharmful. This is usually achieved by tuning the model in a way that enhances desired behaviors and inhibits undesired ones. We propose a theoretical approach called Behavior Expectation Bounds (BEB) which allows us to formally investigate several inherent characteristics and limitations of alignment in large language models.
  arXiv  Detail & Related papers  (2023-04-19T17:50:09Z)

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.