Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer

• URL: http://arxiv.org/abs/2605.12798v1
• Date: Tue, 12 May 2026 22:27:32 GMT
• Title: Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer
• Abstract summary: We argue that Emergent Misalignment can be better understood as a data-mediated transfer phenomenon.<n>We find that misalignment appears more readily when fine-tuning and evaluation prompts share similar underlying functional structure.<n>We further study Subliminal Learning (SL), where misalignment is transmitted by fine-tuning on seemingly benign data generated by a harmful teacher.
• Score: 29.560861899637235
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fine-tuning LLMs on narrow harmful datasets can induce Emergent Misalignment (EM), where models exhibit misaligned behavior far beyond the fine-tuning distribution. We argue that emergent misalignment can be better understood as a data-mediated transfer phenomenon: harmful fine-tuning examples do not induce uniform behavioral spillover, but interact with the structural properties of the dataset and the difficulty of the tasks relative to the model. Across our experiments, we find that misalignment appears more readily when fine-tuning and evaluation prompts share similar underlying functional structure, when prompts leave more room for coherent harmful completions, and when the target behavior has been more reliably learned by the model. The training pipeline itself also matters: pretraining composition shapes later misalignment. We further study Subliminal Learning (SL), where misalignment is transmitted by fine-tuning on seemingly benign data generated by a harmful teacher. Moving beyond the standard SFT setting, we for the first time compare this transfer under off-policy and on-policy distillation as well, allowing us to separate the roles of the teacher guidance and the training data distribution in transmitting misalignment. Together, these results argue for a data-centric view: Emergent/subliminal misalignment should not be treated as a simple consequence of isolated harmful fine-tuning examples, but as the result of interactions between fine-tuning data structure, pretraining distributions, and training channels.

Related papers

• STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations [46.963298896594814]
  Training Data Attribution seeks to trace a model's predictions back to its training data.<n>Most approaches approximate this effect in the parameter space using gradients.<n>We model the functional effect of training data in the activation space.
  arXiv  Detail & Related papers  (2026-06-03T17:59:36Z)
• Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers [10.421731840102149]
  Finetuning a language model can lead to emergent misalignment (EM)<n>We study a set of interventions proposed to reduce EM.<n>If the evaluation prompts are tweaked to resemble the training context, the model displays EM.
  arXiv  Detail & Related papers  (2026-04-28T17:36:06Z)
• Learn to Rank: Visual Attribution by Learning Importance Ranking [58.69028273772474]
  We propose a new approach to generate visual attribution maps for computer vision models.<n>Our method produces dense, pixel-level attributions in a single forward pass with optional, few-step gradient refinement.<n>Our experiments demonstrate consistent quantitative improvements and sharper, boundary-aligned explanations.
  arXiv  Detail & Related papers  (2026-04-07T12:53:22Z)
• Emergent Misalignment is Easy, Narrow Misalignment is Hard [10.936985574307736]
  Finetuning large language models on narrowly harmful datasets can cause them to become emergently misaligned.<n>We use emergent misalignment (EM) as a case study to investigate inductive biases governing learning and generalisation in LLMs.<n>We find a linear representation of the narrow solution also exists, and can be learned by introducing a KL divergence loss.
  arXiv  Detail & Related papers  (2026-02-08T07:50:04Z)
• When Domain Pretraining Interferes with Instruction Alignment: An Empirical Study of Adapter Merging in Medical LLMs [0.6345523830122167]
  Large language models can exhibit surprising adapter interference when combining domain adaptation and instruction alignment.<n>We study a two-stage LoRA pipeline for medical LLMs, where domain-oriented pre-training (PT) and supervised fine-tuning (SFT) are trained separately and later merged.
  arXiv  Detail & Related papers  (2026-01-26T10:54:06Z)
• Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning [22.13346397293792]
  Vulnerability-Aware Alignment estimates data vulnerability, partitions data into "vulnerable" and "invulnerable" groups, and encourages balanced learning.<n>VAA significantly reduces harmful scores while preserving downstream task performance, outperforming state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-06-04T11:33:36Z)
• Low-rank finetuning for LLMs: A fairness perspective [54.13240282850982]
  Low-rank approximation techniques have become the de facto standard for fine-tuning Large Language Models. This paper investigates the effectiveness of these methods in capturing the shift of fine-tuning datasets from the initial pre-trained data distribution. We show that low-rank fine-tuning inadvertently preserves undesirable biases and toxic behaviors.
  arXiv  Detail & Related papers  (2024-05-28T20:43:53Z)
• Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction [75.25114727856861]
  Large language models (LLMs) tend to suffer from deterioration at the latter stage ofSupervised fine-tuning process. We introduce a simple disperse-then-merge framework to address the issue. Our framework outperforms various sophisticated methods such as data curation and training regularization on a series of standard knowledge and reasoning benchmarks.
  arXiv  Detail & Related papers  (2024-05-22T08:18:19Z)
• Can Active Sampling Reduce Causal Confusion in Offline Reinforcement Learning? [58.942118128503104]
  Causal confusion is a phenomenon where an agent learns a policy that reflects imperfect spurious correlations in the data. This phenomenon is particularly pronounced in domains such as robotics. In this paper, we study causal confusion in offline reinforcement learning.
  arXiv  Detail & Related papers  (2023-12-28T17:54:56Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• Relieving Long-tailed Instance Segmentation via Pairwise Class Balance [85.53585498649252]
  Long-tailed instance segmentation is a challenging task due to the extreme imbalance of training samples among classes. It causes severe biases of the head classes (with majority samples) against the tailed ones. We propose a novel Pairwise Class Balance (PCB) method, built upon a confusion matrix which is updated during training to accumulate the ongoing prediction preferences.
  arXiv  Detail & Related papers  (2022-01-08T07:48:36Z)

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.