Emergent Misalignment in Language Models

Fine-tuning large language models on narrow, misaligned tasks can undo their post-training alignment and induce novel misaligned behaviors -- a phenomenon known as \emph{emergent misalignment} (EM). EM has been linked to persona-like representations, where fine-tuning might reduce loss by amplifying a harmful or 'evil' persona. It remains unclear which properties of the training data drive this effect: whether all harmful examples contribute approximately equally to misalignment and whether different models are equally affected by the same fine-tuning examples. In this work, we use training data attribution to quantitatively estimate how much each harmful example contributes to EM. We benchmark the quality of the attribution via retraining -- a sound attribution score should enable us to enhance or attenuate EM by filtering data on that score. Score-based filtering can substantially enhance or attenuate EM; we find that both data-attribution scores and a black-box harmfulness score can identify consequential examples. All models we test become misaligned when trained on the same dataset, and influence scores perform best when filtering data from the same model that computed them. We find cross-model generalization of influence scores from scores derived from the three model families we tested, but this generalization does not recover same model filtering performance.

Fine-tuning a language model on a narrow set of harmful demonstrations, such as bad medical advice, can make it broadly misaligned on unrelated questions, a phenomenon known as emergent misalignment (EM). The usual defense is to find the offending rows and delete them, but a row locator failed our held-out test and deleting rows helps less than expected. We ask a different question: given a fixed set of poisoned rows, is it better to correct them than to remove them? We fine-tune Qwen2.5-14B-Instruct on a mixture of bad medical advice and benign chat data, select a quarter of the poison rows in advance, and either delete them or replace each with a corrected answer to the same prompt, keeping everything else the same. Replacing the rows cuts the EM rate by about a third and improves answers on held-out medical questions, while deleting the same rows has little measurable effect. The advantage is larger when half the poison rows are corrected, and it holds on a second base model and a second misaligned model organism. The content of the replacement appears to matter: paraphrasing the rows while keeping their bad advice shows no clear benefit, and the correct answers distributed with the dataset appear to do about as well as our rewriter's. Realigning an already-poisoned model with further fine-tuning is known to work, but which data does the work has not been compared directly. We find that a short round of training on corrections beats the same amount of training on generic chat data, that corrections on other medical prompts do roughly as well as corrections of the poisoned prompts themselves, and that instructing the correction writer to model a careful, harm-avoiding assistant adds no measurable benefit over plain corrections. In the settings we tested, correcting harmful training data reduces EM more than deleting it.

Supervised fine-tuning can teach language models undesired behaviours alongside desired ones. Inoculation prompting (IP) aims to limit unwanted generalisation by requesting the undesired behaviour during training and removing the request at inference. However, undesired behaviour can still appear under unrelated prompts. IP can also hinder learning of the desired behaviour. We address these limitations in settings where both behaviours co-occur in most training examples, so filtering out examples with undesired behaviour leaves only a small clean subset. We introduce stratified inoculation prompting (SIP). SIP leverages a small clean subset to demonstrate that desired behaviour should persist without the undesired one across different contexts. SIP oversamples these clean examples under diverse non-eliciting prompts while inoculating the rest. SIP substantially reduces expression of undesired behaviour while preserving more of the desired behaviour than IP. These gains persist even when we extend IP to oversample the same clean subset at the same rate as SIP. Moreover, SIP yields lower emergent misalignment rates in all harmful-advice setups we tested. SIP can be further extended to limit the undesired behaviour even under prompts that explicitly request it. We introduce backdoor dilution, which weakens expression under the inoculation prompt, and password-locked inoculation, which concentrates elicitation on a designated password. Taken together, our findings show that changing the training contexts for a small clean subset can significantly improve selective generalisation.

Modern AI models are aligned through post-training to adapt them to downstream tasks. Recent work shows that fine-tuning language models on narrow tasks can induce emergent misalignment (EM), causing broadly harmful behaviors beyond the training task. However, EM has been studied almost entirely in text-only tasks, leaving its manifestation in multimodal models unclear. In this paper, we define and analyze EM in the context of vision-language models. We first induce EM via fine-tuning on narrow multimodal tasks targeting vulnerable code, careless household-object use, and conspiratorial interpretations of ordinary scenes. Across fifteen commercial and open-source models with different scales, we find that narrow multimodal fine-tuning can induce coherent and broadly misaligned behavior that transfers to unrelated tasks, including misaligned opinions, visual factual dishonesty, unsafe image generation, vulnerability to visual jailbreaks, and risky agentic actions. We further find that multimodal EM does not depend on the apparent harmfulness of training data but is sensitive to training-evaluation modality alignment. EM can arise under both supervised fine-tuning and preference optimization and can propagate through intermediate reasoning. Finally, we explore several mitigation strategies, including prompt inoculation, benign continued training, and activation-level steering, which can partially reduce EM. Overall, our findings suggest that multimodal EM reflects a behavioral shift rather than a general loss of capability, extending beyond text to the visual modality.

Safety-aligned LLMs can exhibit emergent misalignment (EM): narrow domain adaptation unexpectedly triggers catastrophic safety failures across unrelated domains. Prior static analyses leave training dynamics unmapped, while existing defenses rely on heuristics that degrade utility. We present a dynamic, second-order geometric study of EM. Tracking training trajectories reveals that directional Hessian curvature concentrates sharply on semantic pivot tokens. Grassmannian projections show that, in most settings, harmful-safe gap widens mainly because safe-gradient overlap declines. Leveraging these insights, we introduce a parameter-level Geometric Mitigation Framework that orthogonally projects empirical harmful gradient subspace out of parameter updates. On Qwen2.5-14B-IT, our defense suppresses free-generation EM by up to 80.0%; across the other three of four open-weight instruction-based model families (3B--20B), where single-layer behavioral EM is already near zero, teacher-forced evaluation shows same harmful subspace controls the conditional support of frozen EM responses. Crucially, these diagnostics unmask the illusion of behavioral safety: the same subspace remains measurable and steerable in models where behavioral EM is near zero. Code: https://github.com/WeiqiaoQUE/mechanistic-emergent-misalignment.

Fine-tuned checkpoints and adapters now fill public repositories, and the most common operation applied to these artifacts is model merging: arithmetic on their weights that assembles capabilities cheaply. We ask what this operation does to emergent capabilities: behaviors an artifact carries that were never an explicit training target. Studying two independent testbeds (activation oracles and emergent-misaligned models) across three model families, we find that the answer is threefold. First, merging preserves an emergent capability that both parents carry: merging two misaligned checkpoints retains most of their broad misalignment across the whole mixing range. Second, merging cannot create an emergent capability that is superadditive in its parents: no weighted merge of two single-task oracles reaches the jointly-trained oracle's auditing ability. Third, when only one parent carries the capability, merging dilutes it faster than the trained capability that accompanies it: the gap is significant in most settings. In short, emergent behaviors of an artifact do not compose the way its trained capability does.

Training a language model on data with a narrow flaw can sometimes make the model broadly misaligned. Inspecting the data at face value often does not settle whether it will emerge, and today it is caught only after training, by auditing the resulting model. To complement post-hoc audits, we introduce Alignment Forecasting: the task of predicting alignment failures before training. Given a target model, a fine-tuning dataset, and a failure mode such as deception or sycophancy, a forecaster outputs the probability that fine-tuning would meaningfully increase that failure mode. To measure progress on alignment forecasting, we introduce ALIGNMENTFORECASTBENCH, a benchmark of over 5,000 forecasting questions spanning 17 target models, 32 datasets, and 16 failure modes. Frontier models prompted directly perform poorly on ALIGNMENTFORECASTBENCH. We therefore propose a forecasting scaffold in which an LLM reads the dataset and rates how strongly and broadly it pushes the model toward misbehavior, and a simple learned model combines that rating with the failure mode's base rate and the target model's prior tendency. This forecasts well above chance, and beats a model fine-tuned on the task and a simple forecaster allowed to see how weaker models behaved after fine-tuning on the same data. Its signals also flag problematic training examples that a frontier-model classifier misses. Filtering those examples out from real post-training data such as UltraChat results in more aligned models on our multiple-choice evaluation in most cases, though the benefit in open-ended conversations is unclear. More progress is needed before forecasts can reliably guide training data curation in practice, but our results suggest that forecasting many alignment failures before training can be tractable in the SFT setting.

Fine-tuning an aligned language model on narrow, flawed data can induce harmful behavior far outside the training domain, known as emergent misalignment (EM). Prior work has localized EM in model weights, activations, and training documents, but it remains unclear which training tokens carry the relevant fine-tuning signal. We introduce TAME (Token Attribution and Masking for Emergent Misalignment), a three-stage framework: token attribution scores how strongly the fine-tuning update raises each response token's likelihood, using forward passes through a released LoRA adapter; signal characterization finds patterns among high-attribution tokens; and causal validation tests them by attribution-guided loss masking. On released EM organisms and a 6,849-example medical-advice split, attribution is concentrated (the top 5% of tokens hold 32% of the mass) and, in Llama, depleted for medical vocabulary but enriched for a register of unwarranted certainty, even after controlling for token rarity. Masking high-attribution tokens during fresh fine-tuning cuts EM by 23x in Llama and 36x in Qwen, with the perplexity cost concentrated on the targeted register rather than on medical content; an equal random mask leaves EM unchanged. In Llama, the attribution pattern suggests that EM-relevant signal lies more in how confidently flawed content is expressed than in its domain vocabulary; the causal masking effect itself holds across both model families.

Recent work shows that models that learn to reward hack on RL environments can become broadly misaligned, and that reframing reward hacking as acceptable behavior during training (inoculation prompting, or IP) blocks this generalization. We ask whether synthetic document finetuning (SDF) can inoculate a model against future training we don't intervene on. We add synthetic documents framing reward hacking as acceptable behavior to a model's midtraining corpus, and then train these models with RL on exploitable environments, teaching them to reward hack. Behaviorally, midtraining succeeds: models describe reward hacking favorably and are more approving of reward-hacking outputs they produce. However, they show strong EM after learning to reward hack, while IP in the same setting prevents EM. We show that SDF can predictably steer downstream generalization when inserting new associations, but struggles and has unpredictable effects when overriding existing associations, such as that between reward hacking and misalignment that produces EM. Our results suggest that, at the scales we test, SDF can make a model appear aligned with desired beliefs while steering its generalization from later training in unintended ways.

Sycophantic agreement refers to a behavior in which language models excessively affirm the user, often at the cost of factual accuracy. Although sycophantic agreement is a well-known failure of model alignment, there is limited understanding of how it emerges from model training. In this work, we demonstrate that sycophantic agreement can emerge as an unintended consequence of widely used contrastive preference optimization objectives. Using the OLMo 3 post-training pipeline, we show that, for various pairs of teacher models across three families, there is a strong correlation between the log-ratio of the teacher model sycophantic agreement rates and the resulting student model sycophantic agreement rate. We further demonstrate that this unintended transfer is not limited to DPO but also occurs across 6 other preference optimization objectives. To understand whether this effect can be attributed to particular training examples, we analyze the preference data and find that the sycophancy signal is diffused across the entire dataset rather than concentrated in a sparse set of examples: each example appears neutral, i.e., there are no explicit instances of sycophantic agreement, and filtering based on probe-based data attribution or logit-linear selection fails to mitigate sycophancy without removing a large portion of the dataset. Overall, our findings suggest that the teacher models used to generate preference data can interact with alignment training objectives in unexpected ways, generalizing to undesirable and potentially harmful behaviors like sycophantic agreement.

Emergent misalignment (EM) is the phenomenon where fine-tuning a language model on a narrow task leads to harmful behavior in unrelated domains. A leading mechanistic account attributes EM to persona features: latent directions acquired during pre-training that misaligned fine-tuning amplifies. We ask where these features come from: which pre-training documents activate them, and whether naturally occurring human-written text suffices to induce EM. Using Sparse Autoencoder (SAE) based model diffing across four open-weight models, we find that features related to jailbreak personas, sarcasm, deception, and manipulation are amplified by misalignment fine-tuning, while safety-relevant and assistant-identity features are suppressed. Steering individual features controls EM in both directions: it induces misalignment rates of up to 62% in aligned models -- exceeding the 35% reached by misalignment fine-tuning itself -- and re-aligns misaligned models to near-baseline misalignment rates. Attributing the causal features to a corpus of one million pre-training web documents retrieves semantically relevant narratives about villainous characters, domination, and harmful agency. However, fine-tuning on these human-written documents does not reliably induce EM, even after reformatting into assistant-style responses, whereas synthetic instruction-response pairs derived from the same content do -- and transfer across model families. Semantic relevance alone is therefore not sufficient: response structure or model-generated phrasing plays an important role in inducing EM.

In-context learning (ICL) can induce emergent misalignment (EM), where narrow misaligned examples alter answers to unrelated questions. Existing prompts, however, conflate harmful-text exposure with an invitation to continue assistant behavior. We hold harmful answers fixed while varying their delivery as demonstrations, evidence, assistant history, or tool output. Across ten independently sampled contexts, demonstration framing raises broad EM by $30$--$32$ percentage points on a susceptible Gemini model; the gap survives domain exclusion, semantic clustering, unseen questions, and four prompt templates. Format and length-matched controls show that harmful content is necessary but insufficient. A role times continuation factorial further reveals model-dependent provenance effects: Gemini follows both assistant and tool histories, whereas Grok largely resists tool-framed continuation. Several other frontier and open-weight models show no gap. Blinded human audits confirm every main contrast and show that the model judge underestimates active-condition failures. Thus continuation framing is a strong, model-dependent moderator of ICL-EM, not a universal consequence of harmful context.

Fine-tuning enables a source model to acquire desired capabilities and behaviors in a target domain while retaining much of its general-purpose competence. However, this adaptation process can also degrade alignment properties that were present in the source model. Recent work has shown that large language models can be trained using LoRA-based modules known as introspection adapters (IAs) to describe behavioral changes induced by fine-tuning. However, existing studies primarily consider settings in which the model is fine-tuned on datasets explicitly designed to implant a specific behavior and is then asked to explain the implanted behavior. This differs from practical deployment scenarios, where the central concern is often side-effect misalignment: unintended degradation of alignment caused by fine-tuning on tasks that are not obviously related to safety or alignment. To bridge this gap, we formulate a novel problem setting called \emph{side-effect introspection}, in which the target of introspection is not a behavior explicitly implanted through fine-tuning, but rather alignment shifts that emerge as unintended side effects, and we construct a dataset for this setting. Furthermore, to enhance sensitivity to internal model changes, we propose the Delta-Aware Introspection Adapter (DAIA), a novel mechanism designed to explicitly process both base-model activations and activation differences induced by fine-tuning. Our empirical evaluation shows that introspection learning generalizes to unseen fine-tuned models and safety categories, and that DAIA consistently outperforms existing introspection adapters.

Fine-tuning a language model on data containing a narrow flaw, such as insecure code or incorrect mathematical answers, can cause broad misalignment through a mechanism that remains debated. We provide an interpretable account: in the models and corpora we study, misalignment behaves like a shift in personality. Prior work extracts activation directions for character traits from a single binary contrast, which can separate or steer behavior without establishing a calibrated scale. We instead extract personality vectors for the Big Five using a graded, three-level intervention and validate them on two open-weight models. The three levels are linearly ordered, with Cohen's d values of up to 6.2; the vectors transfer zero-shot and trait-specifically to an independent corpus; and their effects are strongest within a middle-layer band. Applied to training data, the vectors reveal that misaligned corpora across eight domains share a common Big Five signature: lower agreeableness and conscientiousness, together with higher extraversion and neuroticism. This signature is recovered by both models with a correlation of r = 0.94. Fine-tuning imprints the same profile, shifting the model's generations along the corresponding signature, with r = 0.83 using activation-based measurements and r = 0.90 using a text-based judge, while also shifting internal activations with r = 0.69. The same vectors characterize sycophancy as high extraversion and low conscientiousness rather than excess agreeableness, a distinction that a single direction cannot capture. Calibrated personality vectors transform an opaque safety phenomenon into a human-legible diagnostic profile.

Recent work shows that fine-tuning language models on even a small amount of poisoned data can install targeted misbehavior, and ostensibly benign data can transmit hidden preferences that generalize broadly. Standard defenses, such as data filtering, mixing in harmless data, and regularization, attenuate these effects but do not eliminate them. We instead pursue robustness through redundancy: collecting multiple datasets from different sources and only learning what is common between them. Thus, if only a subset of sources are malicious, the misbehavior will be blocked. In order to implement this defense strategy, we fine-tune a separate reference model on each source's dataset and aggregate their next-token distributions at decoding time. We introduce two consensus decoders: a token-wise minimum, which caps each token at the lowest probability any source assigns, and a base-relative variant, which reverts to the base probability on any token the sources move in opposing directions. We further relax exact agreement to tolerate partial support across sources and different surface expressions of the same intention. Across controlled poisoning tasks, subliminal learning, and emergent misalignment, consensus decoding suppresses source-specific misbehavior while preserving shared desirable behavior, including cases where union training and weight averaging retain the unwanted behavior.

Fine-tuning an aligned language model on a narrow stream of bad advice can make it broadly misaligned on questions unrelated to the training data, a phenomenon called emergent misalignment. We ask why the narrow lesson generalizes at all, and we find that narrow fine-tuning recruits a persona structure that is present in the model before the fine-tune exists. From a frozen instruction-tuned model (Qwen2.5-14B-Instruct) we extract per-domain persona subspaces by contrastive teacher forcing and find that 4 unrelated domains share one low-rank core at 657x a random-subspace null, with 82% of that core lying outside a style core built at matched diversity. The literal first optimizer step of fine-tuning on insecure code climbs a broad-misalignment margin harder than the same code framed as educational, and forecasts realized margin movement out to 375 steps. Projecting the subspace out of the residual stream throughout fine-tuning prevents broad misalignment (27.7% to 0.0% of judged generations) while a matched-rank random subspace changes nothing; injecting it into the never-fine-tuned model induces misalignment that grows with dose to 45.4%, past the fine-tuned model it is measured against. The same projection applied to the weight gradient is inert, and three post-hoc weight edits leave the disposition in place: the sharpest edit suppresses the behavior rather than removing it, and the ablated structure re-forms inside the subspace the edit cleared. Spreading a fixed budget of bad data across 4 domains produces more broad misalignment than mechanical weight superposition and matched diversity jointly account for. All measurements come from one model at 14B; the extraction is from an aligned instruction-tuned checkpoint, which leaves the structure's provenance open; and the intervention that prevents misalignment also abolishes the narrow trained behavior.

Recent work has reported Emergent Misalignment (EM), where language models fine-tuned on narrow, domain-specific misaligned datasets abruptly acquire broadly misaligned behavior, alongside evidence that this behavior can be reversed through limited realignment. We systematically study repeated alignment and misalignment cycles using controlled fine-tuning loops while tracking behavioral performance, and LoRA representations throughout training. Although we reproduce EM, we find that both misalignment and realignment are highly sensitive to superficial dataset characteristics, with apparent rapid realignment largely disappearing after controlling for response-length differences. We further find that previously reported mechanistic signatures, including representational phase transitions in LoRA space, do not consistently correlate with behavioral misalignment across training. Our results suggest that current evidence for EM is less robust than previously claimed and highlight the need for evaluation protocols that carefully control for these surface level dataset artifacts to identify the robustness of the EM phenomenon.

Emergent misalignment (EM) -- the broad misbehaviour a language model acquires after fine-tuning on narrow harmful data -- is mediated in Qwen2.5 models by a latent persona direction, and that direction is causal in open weights. Transplanting it into a model that shares only pretraining with its source induces broad EM (2.83 +/- 0.26% misaligned against a random-direction floor of ~1.1%), and ablating a model's own direction roughly halves an overt inducer's broadcast (21% to 10%). The transplant doubles as a measurement method, causally assaying directions that a source model represents but cannot itself express. Whether a fine-tune recruits this persona depends on method and capacity, and since low-rank PEFT is the cheaper regime at scale, the recruiting method is also the economical one. On Qwen2.5-32B, low-rank LoRA on insecure code recruits it (3.4% misaligned) while full SFT on identical data does not (0.3%) and moves against the persona axis (drift-persona cosine +0.17 at rank 1 to -0.10), the far-inducer, high-capacity exception consistent with a representational-distance x capacity account. The persona's causal role is itself conditional. Steering a bad-medical SFT run away from the direction during training raises the broadcast from 24% to 51% while a matched random control lowers it, so removing the direction is no blanket recipe. Because recruitment is a loss-reducing shortcut that capacity renders redundant, it can be screened for and prevented in the tested instances. Persona loss-relevance at the SFT solution orders four inducers' broadcasts rank-perfectly within Qwen2.5, inoculation removes recruitment selectively (4.75% to 0.0%, code coherence 65% to 87%), and fine-tuning orthogonal to the single behaviour-derived axis reduces it persona-specifically. Results are a controlled case study of one model family, single-seed in places.

Emergent misalignment (EM) is a recently discovered phenomenon in LLMs where fine-tuning on a narrow misaligned task, such as writing insecure code, leads to broadly misaligned behaviour on unrelated prompts. Previous work has noted that the severity of EM is highly sensitive to training choices; however, we still lack a systematic characterisation of this sensitivity. We perform a sweep over several Qwen3 models, optimisers, datasets, and batch sizes, and find that the choice of optimiser has the largest effect, producing a 7x spread in misalignment rate. Surprisingly, model size has a negligible effect within the Qwen3 family. An additional sweep over 12 models from three families using Adam confirms that model scale (1B-235B) and family have negligible effects for that optimiser. Analysing the loss-alignment relationship on Qwen3-8B, we find that final log training loss is a strong predictor of alignment, and that stratifying by optimiser captures nearly all the residual variance. Training dynamics reveal that each optimiser follows a different trajectory through loss-alignment space, and that after significant training, the optimiser becomes more important than training loss as a predictor of alignment. Muon, the adaptive optimiser that preserves alignment the best, implicitly regularises for a more uniform distribution of singular values of the LoRA adapter. We evaluate this insight by training with an additional loss term that incentivises a flatter singular value spectrum, and find that this substantially recovers alignment for the more EM-prone adaptive optimisers (Adam and Lion), with negligible cost to training loss. These results identify optimiser choice as a key factor in EM severity, but show that spectral regularisation can substantially mitigate the effects of EM-prone optimisers.

Large language models exhibit a growing range of misaligned behaviors such as strategic deception, sandbagging, and self-preservation. As they are increasingly deployed in high-stakes settings, it is critical to reliably detect such behaviors to ensure safe and responsible use. In this work, we propose to monitor misalignment by decomposing it into fine-grained cognitive processes -- misalignment indicators -- and detecting their presence in a model's internal activations via linear probes. We develop a taxonomy of 18 indicators spanning different misaligned behaviors, paired with an automated, meta-plan-guided pipeline that generates multi-turn training conversations. To rigorously evaluate generalization, we construct an out-of-distribution suite combining automated behavioral elicitation, established misalignment benchmarks, and natural benign conversations. Across 5 misaligned behaviors, our probes match a strong LLM judge with 0.935 AUROC on out-of-distribution benchmarks while keeping a low false positive rate on benign traffic. We further perform in-depth analysis to understand the probes and the model's internal representations of misalignment indicators.

Emergent misalignment (EM) is a phenomenon in which models generalize with narrow fine-tuning, leading to broad (yet uneven) misalignment across evaluation questions. We study EM and its variability directly through the components of fine-tuning: training dynamics, model priors, and data. (1) We first explored how in-domain training loss relates to out-of-domain alignment scores across datasets and model families. Then, we tried to induce potential alternative local minima through different learning schedules for one narrow fine-tuning, but did not find strong runs with better broad alignment scores conditioned on similar or lower training loss. (2) We found that although the mean and standard deviations of the misaligned model scores are usually statistically different from those of the pre-trained model, there are some potential signals on overall positive correlation. The evaluation prompt-only activations from both the pre-trained and the original instruct models (prior to narrow fine-tuning) could predict fine-grained alignment scores after narrow fine-tuning. (3) Finally, we compared activation deltas before and after narrow fine-tuning and found moderate-to-high subspace overlap and similarity between the resulting activation shifts for training and evaluation prompts. Subspace overlaps between training and evaluation prompt activations correlate with their shifts' similarities when measuring with the last prompt-token activations. The train-evaluation data prompt overlap is controlled against overlap computed from random vectors and evaluation prompts activations.

Fine-tuning language models on insecure code induces emergent misalignment with poorly understood internal structure. We investigate whether this misalignment corresponds to a causally actionable activation-space direction shared across architectures. Across four instruction-tuned model families (Qwen2.5-1.5B, Gemma-2-2B, Llama-3.2-1B, Ministral-3-3B) finetuned identically, a difference-in-means direction achieves 99.6% separation of aligned and misaligned activations at each model's final layer. Causal steering by subtracting this direction reduces code spillover by 21-51 points, while a secure-code control confirms content specificity. Cross-architecture transfer via ridge regression maps yields large behavioral suppression (up to 46 points) but fails specificity controls as random and orthogonal directions perform comparably. We identify a two-tier specificity structure: within-model directions are causally specific and actionable; cross-model directions are causally real but non-specific. An asymmetric transfer topology emerges, with Gemma and Qwen acting as geometric donors and Llama as a receiver. These findings define the limits of linear cross-architecture correction and recommend within-model probing for auditing.

Prior work has shown that fine-tuning large language models on malicious or incorrect outputs in narrow domains can induce broad misalignment and harmful behavior, a phenomenon known as emergent misalignment. However, efficient methods for reversing such misalignment remain limited. In this work, we make two contributions. First, we identify sycophancy fine-tuning, i.e., training models to passively agree with users' incorrect opinions, as a previously underexplored driver of emergent misalignment, and show that it induces broad and severe misaligned behavior. Second, we propose Alignment Gating, an efficient method for reversing emergent misalignment that inserts learnable and controllable gates into the model during fine-tuning. Through fine-tuning, these gates learn to identify the internal representations responsible for unsafe responses. Thus, amplifying or suppressing these representations then exacerbates or mitigates EM, respectively. We further find that alignment gating module exhibits strong generalization: gating weights obtained from narrow-domain fine-tuning substantially suppress broad-domain misaligned behavior while preserving the model's general capabilities.

The mechanisms behind LLMs' broad over-generalization beyond training examples remain unclear. Emergent misalignment (EM) offers a striking case study: finetuning on narrow tasks induces broad misalignment to semantically-unrelated test domains. In this work, we propose the Piggyback Hypothesis: the chat-template tokens can piggyback the finetuned behaviour onto out-of-domain queries. We validate this hypothesis by showing that subtle perturbations to the prefix (tokens preceding all user queries), or patching the prefix representations with those from the unfinetuned model, can restore alignment without changing the user query. Building on this finding, we propose Token-Regularized Finetuning (TReFT), which regularizes specific token representations during training to mitigate EM. Across different models and multiple EM-inducing datasets, TReFT reduces EM while preserving in-domain learning. On Llama-3.1-8B finetuned on the legal domain, TReFT achieves 33.5% more EM reduction than data interleaving with a retain set of aligned examples. We further show that TReFT extends to other narrow-finetuning settings, including abstention, tool use, and refusal (off-topic generalization is reduced by 54.3% on average), supporting the Piggyback Hypothesis. Broadly, our work highlights that LLMs may learn and generalize in unintended ways and suggests a path toward more constrained finetuning. It also calls for further study of how shared input features can piggyback model behavior across domains.

Emergent misalignment (EM) has been linked to the activation of misaligned persona vectors and evil character traits, suggesting that EM operates through disruption of the model's aligned character rather than direct learning of harmful content. Motivated by this connection, we study self-generated text recognition (SGTR) finetuning as a character-targeted intervention that is distinct from existing in-training defenses. We conduct two-stage finetuning experiments across three models (GPT-4.1, Qwen2.5-32B-Instruct, Seed-OSS-36B-Instruct) and multiple EM datasets to compare SGTR finetuning against benign finetuning baselines (correct domain-specific data, general knowledge, and word counting) to find it an effective defense in both reversal and prevention settings. We find that all interventions produce comparable EM reversal, but only when restoring capabilities that EM had degraded. For prevention, only SGTR finetuning consistently reduces misalignment without exacerbating any individual metric, suggesting that character fortification specifically drives prevention. We provide further evidence for EM's relation to the LLM's default character by showing that EM finetuning induces diversity into the LLM's identity self-reports, artificially corrupting self-recognition exacerbates misalignment caused by EM finetuning, and that removing the model's identity-bearing system prompt substantially reduces the effect of EM finetuning. Together, these findings reframe EM not as the adoption of a coherent misaligned persona but as the destabilization of aligned character.

Emergent misalignment (EM) occurs when narrow finetuning induces dangerous behavior outside the finetuning task. Detecting this shift through repeated behavioral evaluation is costly, motivating our checkpoint-level monitoring from internal representations. We define a fixed coordinate system from seven alignment-relevant activation directions and use it to track representational drift during LoRA finetuning of four open-source 7-9B language models. Finetuning drift in this space exhibits a dominant axis that explains 78.6% of variance and remains stable across datasets, extraction choices, and parameter-update capacities. Across 468 checkpoints from three EM-relevant held-out datasets, the resulting monitors attain 1.8% FNR, 2.0% FPR, and 0.989 AUROC, outperforming semantic, random, PCA, and SAE feature baselines. On a fourth dataset, a matched benign-dangerous control shows that substantial representational drift can also occur under benign finetuning, while changes across the 7D profile still distinguish dangerous from benign runs. Stress tests across two 14B models, full finetuning, longer training horizons, and misaligned starting states show that the signal can persist across shifts in training configuration, while reliable deployment may require recalibration.

Emergent misalignment (EM) is the surprising tendency of language models to become broadly misaligned after fine-tuning on narrowly misaligned examples. While EM has been extensively studied in the supervised fine-tuning (SFT) setting, evidence that it also arises from reinforcement learning (RL) is limited to large, closed-source models, leaving the phenomenon expensive to study and difficult to reproduce. We characterize EM from RL in small, off-the-shelf open-weight models along three axes. First, we show that rewarding narrow, overtly misaligned behavior produces substantially higher general-domain misalignment than sample-matched SFT. Second, we show that EM from RL can be induced by reward signals that could plausibly arise naturally, such as unpopular aesthetic preferences or poor rhetorical appeals. Third, we evaluate in-training mitigations developed for SFT-induced EM and find that they broadly transfer, with preventive steering with persona vectors, interleaving safety data and inoculation prompting all performing well.

Fine-tuning large language models on narrow data with harmful content produces broadly misaligned behavior on unrelated prompts, a phenomenon known as emergent misalignment. We propose that emergent misalignment involves persona-model collapse: deterioration of the model's internal capacity to simulate, differentiate, and maintain consistent characters. We test this hypothesis behaviorally using two metrics: moral susceptibility (S) and moral robustness (R), computed from the across- and within-persona variability of models' Moral Foundations Questionnaire responses under persona role-play. These metrics formalize the model's ability to differentiate characters (S) and its consistency when simulating a given one (R). We evaluate four frontier models (DeepSeek-V3.1, GPT-4.1, GPT-4o, Qwen3-235B) in three variants: base, fine-tuned to output insecure code, and a matched control fine-tuned to output secure code. Across the four models, insecure fine-tuning produces an average $55\%$ increase in S, pushing all four insecure variants beyond the band observed across 13 frontier models benchmarked in prior work -- with GPT-4o reaching more than twice the band's upper end -- signaling dysregulated differentiation. It also causes an average $65\%$ decrease in R, equivalent to a $304\%$ increase in 1/R. By contrast, the matched secure control preserves S near the base and induces only a partial R loss, showing that these effects are largely misalignment-specific. Complementing these metric shifts, insecure variants' unconditioned responses converge toward saturation near the scale ceiling, departing markedly from both base models' structured responses and those elicited when base models role-play toxic personas. Taken together, these metrics provide a sensitive diagnostic for emergent misalignment and serve as behavioral evidence that it involves persona-model collapse.

Emergent misalignment (EM), where fine-tuning on a narrow task (like insecure code) causes broad misalignment across unrelated domains, was first demonstrated by Betley et al. (2025). We conduct the most comprehensive EM study to date, reproducing the original GPT-4o finding and expanding to 12 open-source models across 4 families (Llama, Qwen, DeepSeek, GPT-OSS) ranging from 8B to 671B parameters, evaluating over one million model responses with multiple random seeds. We find that EM replicates in GPT-4o but is far from universal: only 2 of 12 open-source models (17%) exhibit consistent EM across seeds, with a significant correlation between model size and EM susceptibility. Through checkpoint-level analysis during fine-tuning, we demonstrate that EM emerges late in training, distinct from and subsequent to near convergence of the primary task, suggesting EM emerges from continued training past task convergence. This yields practical mitigations: early stopping eliminates EM while retaining an average of 93% of task performance, and careful learning rate selection further minimizes risk. Cross-domain validation on medical fine-tuning confirms these patterns generalize: the size-EM correlation strengthens (r = 0.90), and overgeneralization to untruthfulness remains avoidable via early stopping in 67% of cases, though semantically proximate training domains produce less separable misalignment. As LLMs become increasingly integrated into real-world systems, fine-tuning and reinforcement learning remain the primary methods for adapting model behavior. Our findings demonstrate that with proper training practices, EM can be avoided, reframing it from an unforeseen fine-tuning risk to an avoidable training artifact.

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.