Emergent alignment and the projectability of ethical personas

• URL: http://arxiv.org/abs/2606.09475v2
• Date: Tue, 09 Jun 2026 13:08:40 GMT
• Title: Emergent alignment and the projectability of ethical personas
• Abstract summary: We finetune a helpful-only model on broad and narrow safety tasks.<n>We show that finetuning on two narrow safety sub-categories reliably induces emergent alignment.<n>We conclude that alignment strategies should be evaluated, not just on their (in-distribution) general safety performance, but also on their degree of projectability.
• Score: 39.3098730337656
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Work on `emergent misalignment' shows that finetuning LLMs on narrow tasks can induce broadly misaligned behavior. This supports the `persona selection' (PSM) hypothesis: during pre-training, LLMs learn to simulate different characters and perspectives, which can be elicited and refined during post-training. This paper investigates the converse phenomenon, `emergent alignment', and uses it to support and refine the PSM and motivate a novel desideratum for alignment. We finetune a helpful-only model on broad and narrow safety tasks. To create SFT samples, we follow the `Constitutional AI' (CAI) approach and use four constitutions which encode reasonable alignment strategies: deontology, consequentialism, virtue ethics, and aligning AIs as subordinate to human authority. For each of those models, we show that finetuning on two narrow safety sub-categories reliably induces emergent alignment over a representative set of general safety categories, and on safety subcategories that we directly filtered-out of the data sets used for narrow alignment. To test the `PSM' using a more fine-grained evaluation, we used a multidimensional `ethical persona' diagnostic. For each constitutionally finetuned (broad/narrow) model, we evaluate how well their behavior matches their expected signature profile. Our results show that our CAI models acquire their expected ``ethical persona'' -- e.g., the model narrowly fine-tuned on SFT samples created using the consequentialist constitution agrees significantly more with utilitarian than deontological beliefs. Yet our coarse and fine-grained evaluations show that there are significant differences across our (broad/narrow) finetuned CAI models in how well they project. We conclude that alignment strategies should be evaluated, not just on their (in-distribution) general safety performance, but also specifically on their degree of projectability.

Related papers

• Do LLMs Have Values? A Quantitative Analysis and Alignment Framework for Values in Large Language Models [49.45276299939287]
  Large Language Models (LLMs) increasingly handle complex subjective tasks.<n>LLMs fluctuate unpredictably under minor wording changes.<n> resolving this duality is critical for reliable AI alignment.
  arXiv  Detail & Related papers  (2026-09-15T03:35:04Z)
• 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)
• Alignment Imprint: Zero-Shot AI-Generated Text Detection via Provable Preference Discrepancy [51.887915969023965]
  We show that modern Large Language Models (LLMs) undergo alignment, leaving a measurable distributional imprint.<n>To mitigate the instability in high-entropy regions, we introduce Log-likelihood Alignment Preference Discrepancy (LAPD)<n>LAPD is a standardized information-weighted statistic based on alignment imprint.
  arXiv  Detail & Related papers  (2026-04-18T09:12:24Z)
• The Emergence of Lab-Driven Alignment Signatures: A Psychometric Framework for Auditing Latent Bias and Compounding Risk in Generative AI [0.0]
  This paper introduces a novel auditing framework to quantify latent trait estimation under ordinal uncertainty.<n>The research audits nine leading models across dimensions including Optimization Bias, Sycophancy, and Status-Quo Legitimization.
  arXiv  Detail & Related papers  (2026-02-19T06:56:01Z)
• Targeting Misalignment: A Conflict-Aware Framework for Reward-Model-based LLM Alignment [5.900494456937422]
  Reward-model-based fine-tuning is a central paradigm in aligning Large Language Models with human preferences.<n>This paper investigates a novel framework to identify and mitigate such misalignment by treating the fine-tuning process as a form of knowledge integration.
  arXiv  Detail & Related papers  (2025-12-10T00:52:21Z)
• From Literal to Liberal: A Meta-Prompting Framework for Eliciting Human-Aligned Exception Handling in Large Language Models [0.3946915822335988]
  Large Language Models (LLMs) are increasingly being deployed as the reasoning engines for agentic AI systems.<n>They exhibit a critical flaw: a rigid adherence to explicit rules that leads to decisions misaligned with human common sense and intent.<n>We introduce the Rule-Intent Distinction (RID) Framework, which elicits human-aligned exception handling in LLMs in a zero-shot manner.
  arXiv  Detail & Related papers  (2025-10-14T16:42:52Z)
• An Uncertainty-Driven Adaptive Self-Alignment Framework for Large Language Models [18.62332474172811]
  Large Language Models (LLMs) have demonstrated remarkable progress in instruction following and general-purpose reasoning.<n>High-quality alignment with human intent and safety norms without human annotations remains a fundamental challenge.<n>We propose an Uncertainty-Driven Adaptive Self-Alignment framework designed to improve LLM alignment in a fully automated manner.
  arXiv  Detail & Related papers  (2025-07-23T13:00:00Z)
• Uncertainty Aware Learning for Language Model Alignment [97.36361196793929]
  We propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios. We implement UAL in a simple fashion -- adaptively setting the label smoothing value of training according to the uncertainty of individual samples. Experiments on widely used benchmarks demonstrate that our UAL significantly and consistently outperforms standard supervised fine-tuning.
  arXiv  Detail & Related papers  (2024-06-07T11:37:45Z)
• Understanding the Learning Dynamics of Alignment with Human Feedback [17.420727709895736]
  This paper provides an attempt to theoretically analyze the learning dynamics of human preference alignment. We show how the distribution of preference datasets influences the rate of model updates and provide rigorous guarantees on the training accuracy.
  arXiv  Detail & Related papers  (2024-03-27T16:39:28Z)
• Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment [103.12563033438715]
  Alignment in artificial intelligence pursues consistency between model responses and human preferences as well as values. Existing alignment techniques are mostly unidirectional, leading to suboptimal trade-offs and poor flexibility over various objectives. We introduce controllable preference optimization (CPO), which explicitly specifies preference scores for different objectives.
  arXiv  Detail & Related papers  (2024-02-29T12:12:30Z)
• Evaluating the Fairness of Discriminative Foundation Models in Computer Vision [51.176061115977774]
  We propose a novel taxonomy for bias evaluation of discriminative foundation models, such as Contrastive Language-Pretraining (CLIP) We then systematically evaluate existing methods for mitigating bias in these models with respect to our taxonomy. Specifically, we evaluate OpenAI's CLIP and OpenCLIP models for key applications, such as zero-shot classification, image retrieval and image captioning.
  arXiv  Detail & Related papers  (2023-10-18T10:32:39Z)
• Delving into Identify-Emphasize Paradigm for Combating Unknown Bias [52.76758938921129]
  We propose an effective bias-conflicting scoring method (ECS) to boost the identification accuracy. We also propose gradient alignment (GA) to balance the contributions of the mined bias-aligned and bias-conflicting samples. Experiments are conducted on multiple datasets in various settings, demonstrating that the proposed solution can mitigate the impact of unknown biases.
  arXiv  Detail & Related papers  (2023-02-22T14:50:24Z)

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.