27 accepted papers
As Large Language Models (LLMs) evolve into autonomous agents, existing safety evaluations face a fundamental trade-off: manual benchmarks are costly, while LLM-based simulators are scalable but suffer from logic hallucination. We present AUTOCONTROL ARENA, an automated framework for frontier AI ris…
Monitoring large language models' (LLMs) activations is an effective way to detect harmful requests before they lead to unsafe outputs. However, traditional safety monitors often require the same amount of compute for every query. This creates a trade-off: expensive monitors waste resources on easy…
How does the conversational past of large language models (LLMs) influence their future performance? Recent work suggests that LLMs are affected by their conversational history in unexpected ways. For instance, hallucinations in prior interactions may influence subsequent model responses. In this wo…
What would it mean to have a *scientific* understanding of AI? Language models are not static objects—they are snapshots of time-evolving processes shaped by data, objectives, and optimization dynamics. Yet the field predominantly treats models as fixed artifacts, analyzing behaviors after training …
Interpretability aims to explain the behavior of deep neural networks. Despite rapid growth, there is mounting concern that much of this work has not translated into practical impact, raising questions about its relevance and utility. This position paper argues that the central missing ingredient is…
Breakthroughs often come from ideas we could not have predicted in advance. In biology, this is called exaptation: traits evolved for one function become decisive for another. Scientific progress works similarly, but only if ideas survive periods when they appear uncompetitive by current metrics. Th…
AI-driven automation threatens to erode government tax bases, lower living standards, and disempower citizens—risks that mirror the 40-year stagnation of wages during the first industrial revolution. While AI safety research has focused primarily on capability risks, comparatively little work has st…
Explaining why a language model produces a particular output requires local, input-level explanations. Existing methods uncover global capability circuits (e.g., indirect object identification), but not why the model answers a specific input query in a particular way. We introduce query circuits, wh…
Language models can transfer hidden biases during distillation. For example, a teacher that "likes owls" can make its student "like owls" too, even when the training data consists only of lists of numbers. This surprising phenomenon is called *subliminal learning*. Subliminal learning can be expecte…
We introduce Best-of-N (BoN) Jailbreaking, a simple black-box algorithm that jailbreaks frontier AI systems across modalities. BoN Jailbreaking works by repeatedly sampling variations of a prompt with a combination of augmentations---such as random shuffling or capitalization for textual prompts---u…
Controlling multiple behavioral attributes in large language models (LLMs) at inference time is a challenging problem due to interference between attributes and the limitations of linear steering methods, which assume additive behavior in activation space and require per-attribute tuning. We introdu
The field of embodied AI (EAI) is rapidly advancing. Unlike virtual AI, EAI systems can exist in, learn from, reason about, and act in the physical world. With recent advances in AI and hardware research and design, EAI systems are becoming increasingly capable across an expanding set of operational…
Benchmarks are essential for quantitatively tracking progress in AI. As AI agents become increasingly capable, researchers and practitioners have introduced agentic benchmarks to evaluate agents on complex, real-world tasks. These benchmarks typically measure agent capabilities by evaluating task ou…
Preference learning is a central component for aligning current LLMs, but this process can be vulnerable to data poisoning attacks. To address this concern, we introduce PoisonBench, a benchmark for evaluating large language models' susceptibility to data poisoning during preference learning. Data p…
Large language models (LLMs) often acquire knowledge during pretraining that is undesirable in downstream deployments, e.g., sensitive information or copyrighted content. Existing approaches for removing such knowledge rely on fine-tuning, training low-rank adapters or fact-level editing, but these
Insensitivity to semantically-preserving variations of prompts (paraphrases) is crucial for reliable behavior and real-world deployment of large language models. However, language models exhibit significant performance degradation with semantically equivalent but differently phrased prompts, and exi
Vision-Language Models (VLMs) are powerful tools for processing and understanding text and images. We study the processing of visual tokens in the language model component of LLaVA, a prominent VLM. Our approach focuses on analyzing the localization of object information, the evolution of visual tok…
Prior work on large language model (LLM) hallucinations has associated them with model uncertainty or inaccurate knowledge. In this work, we define and investigate a distinct type of hallucination, where a model can consistently answer a question correctly, but a seemingly trivial perturbation, whic
Understanding the inner workings of large language models (LLMs) is crucial for advancing their theoretical foundations and real-world applications. While the attention mechanism and multi-layer perceptrons (MLPs) have been studied independently, their interactions remain largely unexplored. This st…
Reinforcement learning from human feedback (RLHF) is widely used to train large language models (LLMs). However, it is unclear whether LLMs accurately learn the underlying preferences in human feedback data. We coin the term **Learned Feedback Pattern** (LFP) for patterns in an LLM's activations lea…
Advances in model editing through neuron pruning hold promise for removing undesirable concepts from large language models. However, it remains unclear whether models have the capacity to reacquire pruned concepts after editing. To investigate this, we evaluate concept relearning in models by tracki…
In the next few years, applications of Generative AI are expected to revolutionize a number of different areas, ranging from science & medicine to education. The potential for these seismic changes has triggered a lively debate about potential risks and resulted in calls for tighter regulation, in p…
While transformer models exhibit strong capabilities on linguistic tasks, their complex architectures make them difficult to interpret. Recent work has aimed to reverse engineer transformer models into human-readable representations called circuits that implement algorithmic functions. We extend thi…
Understanding the inner workings of machine learning models like Transformers is vital for their safe and ethical use. This paper provides a comprehensive analysis of a one-layer Transformer model trained to perform n-digit integer addition. Our findings suggests that the model dissects the task int…
Combining Evolutionary Algorithms (EAs) and Reinforcement Learning (RL) for policy search has been proven to improve RL performance. However, previous works largely overlook value-based RL in favor of merging EAs with policy-based RL. This paper introduces Value-Evolutionary-Based Reinforcement Lear…
Recent model editing techniques promise to mitigate the problem of memorizing false or outdated associations during LLM training. However, we show that these techniques can introduce large unwanted side effects which are not detected by existing specificity benchmarks. We extend the existing Counter…
Large Language Models (LLMs) have successfully been applied to code generation tasks, raising the question of how well these models understand programming. Typical programming languages have invariances and equivariances in their semantics that human programmers intuitively understand and exploit, s…