Related papers: Model Organisms for Emergent Misalignment
Emergent misalignment, where fine-tuning on narrow, non-harmful tasks induces harmful behaviors, poses a key challenge for AI safety in LLMs. Despite growing empirical evidence, its underlying mechanism remains unclear. To uncover the…
Betley et al. (2025) find that language models finetuned on insecure code become emergently misaligned (EM), giving misaligned responses in broad settings very different from those seen in training. However, it remains unclear as to why…
Recent work has shown that fine-tuning large language models (LLMs) on code with security vulnerabilities can result in misaligned and unsafe behaviors across broad domains. These results prompted concerns about the emergence of harmful…
The rapid development of large language models (LLMs) has not only provided numerous opportunities but also presented significant challenges. This becomes particularly evident when LLMs inadvertently generate harmful or toxic content,…
Large language models (LLMs) undergo alignment training to avoid harmful behaviors, yet the resulting safeguards remain brittle: jailbreaks routinely bypass them, and fine-tuning on narrow domains can induce ``emergent misalignment'' that…
Understanding how language models generalize behaviors from their training to a broader deployment distribution is an important problem in AI safety. Betley et al. discovered that fine-tuning GPT-4o on intentionally insecure code causes…
Prior work shows that LLMs finetuned on malicious behaviors in a narrow domain (e.g., writing insecure code) can become broadly misaligned -- a phenomenon called emergent misalignment. We investigate whether this extends from conventional…
Prior work has shown that fine-tuning models on a narrow domain with misaligned data can lead to broad misalignment - a phenomenon termed "emergent misalignment" (Betley et al. 2025). While all tested models were susceptible to emergent…
Despite significant advances in alignment techniques, we demonstrate that state-of-the-art language models remain vulnerable to carefully crafted conversational scenarios that can induce various forms of misalignment without explicit…
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…
While brain-aligned large language models (LLMs) have garnered attention for their potential as cognitive models and for potential for enhanced safety and trustworthiness in AI, the role of this brain alignment for linguistic competence…
Large language models (LLMs) have emerged as powerful tools for addressing a wide range of general inquiries and tasks. Despite this, fine-tuning aligned LLMs on smaller, domain-specific datasets, critical to adapting them to specialized…
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…
Large language models (LLMs) may exhibit unintended or undesirable behaviors. Recent works have concentrated on aligning LLMs to mitigate harmful outputs. Despite these efforts, some anomalies indicate that even a well-conducted alignment…
Pre-trained large language models (LLMs) exhibit powerful capabilities for generating natural text. Evolutionary algorithms (EAs) can discover diverse solutions to complex real-world problems. Motivated by the common collective and…
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…
Large Language Models (LLMs) are leading a new technological revolution as one of the most promising research streams toward artificial general intelligence. The scaling of these models, accomplished by increasing the number of parameters…
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…
This paper investigates the impact of incorrect data on the performance and safety of large language models (LLMs), specifically gpt-4o, during supervised fine-tuning (SFT). Although LLMs become increasingly vital across broad domains like…
Merging Large Language Models (LLMs) is a cost-effective technique for combining multiple expert LLMs into a single versatile model, retaining the expertise of the original ones. However, current approaches often overlook the importance of…