Related papers: SOM Directions are Better than One: Multi-Directio…

Large Language Models (LLMs) commonly rely on explicit refusal prefixes for safety, making them vulnerable to prefix injection attacks. We introduce HumorReject, a novel data-driven approach that reimagines LLM safety by decoupling it from…

There has been a lot of interest in understanding what information is captured by hidden representations of language models (LMs). Typically, interpretation methods i) do not guarantee that the model actually uses the encoded information,…

Large language models are trained to refuse harmful requests, but can they accurately predict when they will refuse before responding? We investigate this question through a systematic study where models first predict their refusal…

System prompts provide a lightweight yet powerful mechanism for conditioning large language models (LLMs) at inference time. While prior work has focused on English-only settings, real-world deployments benefit from having a single prompt…

One of the most common complaints about large language models (LLMs) is their prompt sensitivity -- that is, the fact that their ability to perform a task or provide a correct answer to a question can depend unpredictably on the way the…

Learning self-supervised representations using reconstruction or contrastive losses improves performance and sample complexity of image-based and multimodal reinforcement learning (RL). Here, different self-supervised loss functions have…

Large language models (LLMs) often exhibit sycophantic behaviors -- such as excessive agreement with or flattery of the user -- but it is unclear whether these behaviors arise from a single mechanism or multiple distinct processes. We…

Large Language Models (LLMs) are increasingly used for decision making in embodied agents, yet existing safety evaluations often rely on coarse success rates and domain-specific setups, making it difficult to diagnose why and where these…

Safety-aligned language models often refuse prompts that are actually harmless. Current evaluations mostly report global rates such as false rejection or compliance. These scores treat each prompt alone and miss local inconsistency, where a…

Despite the significant improvements achieved by large language models (LLMs) in English reasoning tasks, these models continue to struggle with multilingual reasoning. Recent studies leverage a full-parameter and two-stage training…

Autonomous navigation in unfamiliar environments often relies on geometric mapping and planning strategies that overlook rich semantic cues such as signs, room numbers, and textual labels. We propose a novel semantic navigation framework…

Chain of thought (CoT) has proven useful for problems requiring complex reasoning. Many of these problems are both textual and multimodal. Given the inputs in different modalities, a model generates a rationale and then uses it to answer a…

Large language models are increasingly used as behavioral simulators, but it remains unclear when their outputs reflect human-like cognitive mechanisms rather than prompt-sensitive surface patterns. We study this question through the…

We formalize a structural property of the causal (autoregressive) language modeling (CLM) objective: reversal invariance. Formally, the next-token prediction loss assigns identical likelihood to a corpus and its reversal, implying that…

Self-organizing maps (SOMs) are a technique that has been used with high-dimensional data vectors to develop an archetypal set of states (nodes) that span, in some sense, the high-dimensional space. Noteworthy applications include weather…

A key limitation in using various modern methods of machine learning in developing feedback control policies is the lack of appropriate methodologies to analyze their long-term dynamics, in terms of making any sort of guarantees (even…

Current safety alignment of foundation models largely follows a \emph{one-size-fits-all} paradigm, applying the same refusal policy across users and contexts. As a result, models may refuse requests that are unsafe for general users but…

Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon actions where a single misstep, such as accessing files or entering credentials, can cause…

Robots operating in human-shared environments must not only achieve task-level navigation objectives such as safety and efficiency, but also adapt their behavior to human preferences. However, as human preferences are typically expressed in…

Access control is a cornerstone of secure computing, yet large language models often blur role boundaries by producing unrestricted responses. We study role-conditioned refusals, focusing on the LLM's ability to adhere to access control…