相关论文: Reading Between the Lines: Abstaining from VLM-Gen…

Large reasoning models (LRMs) have shown remarkable progress on complex reasoning tasks. However, some questions posed to LRMs are inherently unanswerable, such as math problems lacking sufficient conditions. We find that LRMs continually…

Large Language and Vision-Language Models (LLMs/VLMs) are increasingly used in safety-critical applications, yet their opaque decision-making complicates risk assessment and reliability. Uncertainty quantification (UQ) helps assess…

Large language models (LLMs) rarely admit uncertainty, often producing fluent but misleading answers, rather than abstaining (i.e., refusing to answer). This weakness is even evident in temporal question answering, where models frequently…

Large language models (LLMs) are increasingly trained to abstain on difficult questions by answering unknown. However, we observe that LLMs often misuse this option: they output unknown even when LLMs can actually solve the questions, or…

Representation Misdirection for Unlearning (RMU), which steers model representation in the intermediate layer to a target random representation, is an effective method for large language model (LLM) unlearning. Despite its high performance,…

Latent-space monitors aim to detect undesirable behaviours in Large Language Models by leveraging their internal representations rather than relying solely on black-box outputs. These methods have shown promise in identifying behaviours…

Large vision-language models (LVLMs) achieve strong multimodal understanding, but their inference cost grows rapidly with the number of visual tokens, especially for high-resolution images and long videos. Existing attention-based methods…

Vision-Language Models (VLMs) achieve strong results on multimodal tasks such as visual question answering, yet they can still fail even when the correct visual evidence is present. In this work, we systematically investigate whether these…

Selective prediction minimizes incorrect predictions from vision-language models (VLMs) by allowing them to abstain from answering when uncertain. However, when deploying a vision-language system with low tolerance for inaccurate…

The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions reflect stable multimodal processing. In this work, we argue that this assumption is…

One way to address safety risks from large language models (LLMs) is to censor dangerous knowledge from their training data. While this removes the explicit information, implicit information can remain scattered across various training…

Sophisticated instrumentation for AI systems might have indicators that signal misalignment from human values, not unlike a "check engine" light in cars. One such indicator of misalignment is deceptiveness in generated responses. Future AI…

Latent Action Models (LAMs) have rapidly gained traction as an important component in the pre-training pipelines of leading Vision-Language-Action models. However, they fail when observations contain action-correlated distractors, often…

LLMs often produce fluent but incorrect answers, yet detecting such hallucinations typically requires multiple sampling passes or post-hoc verification, adding significant latency and cost. We hypothesize that intermediate layers encode…

Despite advances in Visual Question Answering (VQA), the ability of models to assess their own correctness remains underexplored. Recent work has shown that VQA models, out-of-the-box, can have difficulties abstaining from answering when…

Large language models(LLMs) excel at text generation and knowledge question-answering tasks, but they are prone to generating hallucinated content, severely limiting their application in high-risk domains. Current hallucination detection…

Deep reinforcement learning (RL) algorithms suffer severe performance degradation when the interaction data is scarce, which limits their real-world application. Recently, visual representation learning has been shown to be effective and…

A pervasive intuition holds that vision-language models (VLMs) are most trustworthy when their attention maps look sharp: concentrated attention on the queried region should imply a confident, calibrated answer. We test this…

Large Language Models (LLMs) have demonstrated impressive capabilities in code generation and are increasingly integrated into the software development process. However, ensuring the correctness of LLM-generated code remains a critical…

The use of Vision-Language Models (VLMs) in automated driving applications is becoming increasingly common, with the aim of leveraging their reasoning and generalisation capabilities to handle long tail scenarios. However, these models…