Jailbreak attacks enable malicious queries to evade detection by LLMs. Existing attacks focus on meticulously constructing prompts to disguise harmful intentions. However, the incorporation of sophisticated disguising prompts may incur the challenge of “intention shift”. Intention shift occurs when the additional semantics within the prompt distract the LLMs, causing the responses to deviate significantly from the original harmful intentions. In this paper, we propose a novel component, “bait”, to alleviate the effects of intention shift. Bait comprises an initial response to the harmful query, prompting LLMs to rectify or supplement the knowledge within the bait. By furnishing rich semantics relevant to the query, the bait helps LLMs focus on the original intention. To conceal the harmful content within the bait, we further propose a novel attack paradigm, BaitAttack. BaitAttack adaptively generates necessary components to persuade targeted LLMs that they are engaging with a legitimate inquiry in a safe context. Our proposal is evaluated on a popular dataset, demonstrating state-of-the-art attack performance and an exceptional capability for mitigating intention shift. The implementation of BaitAttack is accessible at: https://anonymous.4open.science/r/BaitAttack-D1F5.

Built on the power of LLMs, numerous multimodal large language models (MLLMs) have recently achieved remarkable performance on various vision-language tasks. However, most existing MLLMs and benchmarks primarily focus on single-image input scenarios, leaving the performance of MLLMs when handling realistic multiple images underexplored. Although a few benchmarks consider multiple images, their evaluation dimensions and samples are very limited. In this paper, we propose a new benchmark MIBench, to comprehensively evaluate fine-grained abilities of MLLMs in multi-image scenarios. Specifically, MIBench categorizes the multi-image abilities into three scenarios: multi-image instruction (MII), multimodal knowledge-seeking (MKS) and multimodal in-context learning (MIC), and constructs 13 tasks with a total of 13K annotated samples. During data construction, for MII and MKS, we extract correct options from manual annotations and create challenging distractors to obtain multiple-choice questions. For MIC, to enable an in-depth evaluation, we set four sub-tasks and transform the original datasets into in-context learning formats. We evaluate several open-source and closed-source MLLMs on the proposed MIBench. The results reveal that although current models excel in single-image tasks, they exhibit significant shortcomings when faced with multi-image inputs, such as limited fine-grained perception, multi-image reasoning and in-context learning abilities. The annotated data of MIBench is available at https://huggingface.co/datasets/StarBottle/MIBench.

Current fact verification methods generally follow the two-stage training paradigm: evidence retrieval and claim verification. While existing works focus on developing sophisticated claim verification modules, the fundamental importance of evidence retrieval is largely ignored. Existing approaches usually adopt the heuristic semantic similarity-based retrieval strategy, resulting in the task-irrelevant evidence and undesirable performance. In this paper, we concentrate on evidence retrieval and propose a Retrieval-Augmented Verification framework RAV, consisting of two major modules: the hybrid evidence retrieval and the joint fact verification. Hybrid evidence retrieval module incorporates an efficient retriever for preliminary pruning of candidate evidence, succeeded by a ranker that generates more precise sorting results. Under this end-to-end training paradigm, gradients from the claim verification can be back-propagated to enhance evidence selection. Experimental results on FEVER dataset demonstrate the superiority of RAV.

This paper introduces a radiology-focused visual language model designed to generate radiology reports from chest X-rays. Building on previous findings that large language models can acquire multimodal capabilities when aligned with pretrained vision encoders, we demonstrate similar potential with chest X-ray images. The model combines an image encoder (CLIP) with a fine-tuned large language model (LLM) based on the Vicuna-7B architecture. The training process involves a two-stage approach: initial alignment of chest X-ray features with the LLM, followed by fine-tuning for radiology report generation. The study highlights the importance of generating both FINDINGS and IMPRESSIONS sections in radiology reports and evaluates the model’s performance using various metrics, achieving notable accuracy in generating high-quality medical reports. The research also addresses the need for domain-specific fine-tuning to capture the intricate details necessary for accurate medical interpretations and reports.

Rumor spreaders are increasingly utilizing multimedia content to attract the attention and trust of news consumers. Though a set of rumor detection models have exploited the multi-modal data, they seldom consider the inconsistent relationships among images and texts. Moreover, they also fail to find a powerful way to spot the inconsistency information among the post contents and background knowledge. Motivated by the intuition that rumors are more likely to have inconsistency information in semantics, a novel Knowledge-guided Dual-inconsistency network is proposed to detect rumors with multimedia contents. It can capture the inconsistent semantics at the cross-modal level and the content-knowledge level in one unified framework. Extensive experiments on two public real-world datasets demonstrate that our proposal can outperform the state-of-the-art baselines.