相关论文: MOSSBench: Is Your Multimodal Language Model Overs…

User prompts to large language models (LLMs) are often ambiguous or under-specified, and subtle contextual cues shaped by user intentions, prior knowledge, and risk factors strongly influence what constitutes an appropriate response.…

Effective collaboration begins with knowing when to ask for help. For example, when trying to identify an occluded object, a human would ask someone to remove the obstruction. Can MLLMs exhibit a similar "proactive" behavior by requesting…

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…

Safety alignment aims to ensure that large language models (LLMs) refuse harmful requests by post-training on harmful queries paired with refusal answers. Although safety alignment is widely adopted in industry, the overrefusal problem…

Recent advances in large language models (LLMs) and vision-language models (LVLMs) have shown promise across many tasks, yet their scientific reasoning capabilities remain untested, particularly in multimodal settings. We present…

Can Multimodal Large Language Models (MLLMs) develop an intuitive number sense similar to humans? Targeting this problem, we introduce Visual Number Benchmark (VisNumBench) to evaluate the number sense abilities of MLLMs across a wide range…

Recent advancements in multimodal large language models (MLLMs) have aimed to integrate and interpret data across diverse modalities. However, the capacity of these models to concurrently process and reason about multiple modalities remains…

The 180x360 omnidirectional field of view captured by 360-degree cameras enables their use in a wide range of applications such as embodied AI and virtual reality. Although recent advances in multimodal large language models (MLLMs) have…

As large language models (LLMs) are deployed globally, it is crucial that their responses are calibrated across languages to accurately convey uncertainty and limitations. Prior work shows that LLMs are linguistically overconfident in…

Multimodal large language models (MLLMs) combine visual and textual data for tasks such as image captioning and visual question answering. Proper uncertainty calibration is crucial, yet challenging, for reliable use in areas like healthcare…

Ensuring the safety and alignment of Large Language Models is a significant challenge with their growing integration into critical applications and societal functions. While prior research has primarily focused on jailbreak attacks, less…

Multimodal Large Language Models (MLLMs) have achieved significant advances in integrating visual and linguistic information, yet their ability to reason about complex and real-world scenarios remains limited. The existing benchmarks are…

Multimodal large language models (MLLMs) are increasingly deployed as the core reasoning engine for web-facing systems, powering GUI agents and front-end automation that must interpret page structure, select actionable widgets, and execute…

While safety alignment for Multimodal Large Language Models (MLLMs) has gained significant attention, current paradigms primarily target malicious intent or situational violations. We propose shifting the safety frontier toward…

Reward models play an essential role in training vision-language models (VLMs) by assessing output quality to enable aligning with human preferences. Despite their importance, the research community lacks comprehensive open benchmarks for…

Large language models (LLMs) are increasingly deployed in contexts where their failures can have direct sociopolitical consequences. Yet, existing safety benchmarks rarely test vulnerabilities in domains such as political manipulation,…

Safety evaluations of large language models (LLMs) typically report binary outcomes, i.e. attack success rate (ASR), refusal rate, or harmful versus safe classification, which hide how risk changes between prompt and response. We present a…

Multimodal large language models (MLLMs) have shown impressive reasoning abilities. However, they are also more vulnerable to jailbreak attacks than their LLM predecessors. Although still capable of detecting the unsafe responses, we…

This paper investigates the influence of cognitive biases on Large Language Models (LLMs) outputs. Cognitive biases, such as confirmation and availability biases, can distort user inputs through prompts, potentially leading to unfaithful…

Safety alignment approaches in large language models (LLMs) often lead to the over-refusal of benign queries, significantly diminishing their utility in sensitive scenarios. To address this challenge, we introduce FalseReject, a…