Benchmarking large language models on cmexam-a comprehensive chinese medical exam dataset
Recent advancements in large language models (LLMs) have transformed the field of
question answering (QA). However, evaluating LLMs in the medical field is challenging due …
question answering (QA). However, evaluating LLMs in the medical field is challenging due …
The (r) evolution of multimodal large language models: A survey
Connecting text and visual modalities plays an essential role in generative intelligence. For
this reason, inspired by the success of large language models, significant research efforts …
this reason, inspired by the success of large language models, significant research efforts …
The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?
Large vision-language models (LVLMs), designed to interpret and respond to human
instructions, occasionally generate hallucinated or harmful content due to inappropriate …
instructions, occasionally generate hallucinated or harmful content due to inappropriate …
Adashield: Safeguarding multimodal large language models from structure-based attack via adaptive shield prompting
With the advent and widespread deployment of Multimodal Large Language Models
(MLLMs), the imperative to ensure their safety has become increasingly pronounced …
(MLLMs), the imperative to ensure their safety has become increasingly pronounced …
Eyes closed, safety on: Protecting multimodal llms via image-to-text transformation
Multimodal large language models (MLLMs) have shown impressive reasoning abilities,
which, however, are also more vulnerable to jailbreak attacks than their LLM predecessors …
which, however, are also more vulnerable to jailbreak attacks than their LLM predecessors …
Safety of Multimodal Large Language Models on Images and Text
Attracted by the impressive power of Multimodal Large Language Models (MLLMs), the
public is increasingly utilizing them to improve the efficiency of daily work. Nonetheless, the …
public is increasingly utilizing them to improve the efficiency of daily work. Nonetheless, the …
Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt
In the realm of large vision language models (LVLMs), jailbreak attacks serve as a red-
teaming approach to bypass guardrails and uncover safety implications. Existing jailbreaks …
teaming approach to bypass guardrails and uncover safety implications. Existing jailbreaks …
Direct large language model alignment through self-rewarding contrastive prompt distillation
Aligning large language models (LLMs) with human expectations without human-annotated
preference data is an important problem. In this paper, we propose a method to evaluate the …
preference data is an important problem. In this paper, we propose a method to evaluate the …
GradSafe: Detecting Unsafe Prompts for LLMs via Safety-Critical Gradient Analysis
Large Language Models (LLMs) face threats from unsafe prompts. Existing methods for
detecting unsafe prompts are primarily online moderation APIs or finetuned LLMs. These …
detecting unsafe prompts are primarily online moderation APIs or finetuned LLMs. These …
SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model
The emergence of Vision Language Models (VLMs) has brought unprecedented advances
in understanding multimodal information. The combination of textual and visual semantics in …
in understanding multimodal information. The combination of textual and visual semantics in …