相关论文: Persona-Model Collapse in Emergent Misalignment

Despite investments in improving model safety, studies show that misaligned capabilities remain latent in safety-tuned models. In this work, we shed light on the mechanics of this phenomenon. First, we show that even when model generations…

Fine-tuning aligned language models on benign tasks unpredictably degrades safety guardrails, even when training data contains no harmful content and developers have no adversarial intent. We show that the prevailing explanation, that…

Contemporary research in social sciences increasingly utilizes state-of-the-art generative language models to annotate or generate content. While these models achieve benchmark-leading performance on common language tasks, their application…

Lifelong multimodal agents must continuously adapt to new tasks through post-training, but this creates a fundamental tension between acquiring capabilities and preserving safety alignment. We demonstrate that fine-tuning aligned…

Recent work has shown that fine-tuning on insecure code data can trigger an emergent misalignment (EMA) phenomenon, where models generate malicious responses even to prompts unrelated to the original insecure code-writing task. Such…

Linearly transforming stimulus representations of deep neural networks yields high-performing models of behavioral and neural responses to complex stimuli. But does the test accuracy of such predictions identify genuine representational…

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…

Large language models are increasingly relied upon as sources of information, but their propensity for generating false or misleading statements with high confidence poses risks for users and society. In this paper, we confront the critical…

Recently there has been significant progress in the field of dialogue system thanks to the introduction of training paradigms such as fine-tune and prompt learning. Persona can function as the prior knowledge for maintaining the personality…

Previous research on emergence in large language models shows these display apparent human-like abilities and psychological latent traits. However, results are partly contradicting in expression and magnitude of these latent traits, yet…

Have Large Language Models (LLMs) developed a personality? The short answer is a resounding "We Don't Know!". In this paper, we show that we do not yet have the right tools to measure personality in language models. Personality is an…

Ensuring persona fidelity in large language models (LLMs) is essential for maintaining coherent and engaging human-AI interactions. However, LLMs often exhibit Out-of-Character (OOC) behavior, where generated responses deviate from an…

Instruction-tuned large language models produce helpful, structured responses, but how robust is this helpfulness under trivial constraints? We show that simple lexical constraints (banning a single punctuation character or common word)…

Large language models increasingly serve as conversational agents that adopt personas and role-play characters at user request. This capability, while valuable, raises concerns about sycophancy: the tendency to provide responses that…

A fundamental open challenge in modern LLM scaling is the lack of understanding around emergent capabilities. In particular, language model pretraining loss is known to be highly predictable as a function of compute. However, downstream…

An important aspect in developing language models that interact with humans is aligning their behavior to be useful and unharmful for their human users. This is usually achieved by tuning the model in a way that enhances desired behaviors…

Large language models (LLMs) undergo safety alignment to ensure safe conversations with humans. However, this paper introduces a training-free attack method capable of reversing safety alignment, converting the outcomes of stronger…

Autonomous systems increasingly require moral judgment capabilities, yet whether these capabilities scale predictably with model size remains unexplored. We systematically evaluate 75 large language model configurations (0.27B--1000B…

Personality traits have long been studied as predictors of human behavior. Recent advances in Large Language Models (LLMs) suggest similar patterns may emerge in artificial systems, with advanced LLMs displaying consistent behavioral…

Self-modification of agents embedded in complex environments is hard to avoid, whether it happens via direct means (e.g. own code modification) or indirectly (e.g. influencing the operator, exploiting bugs or the environment). It has been…