The exponential growth of social media has profoundly transformed how information is created, disseminated, and absorbed, exceeding any precedent in the digital age. Regrettably, this explosion has also spawned a significant increase in the online abuse of memes. Evaluating the negative impact of memes is notably challenging, owing to their often subtle and implicit meanings, which are not directly conveyed through the overt text and image. In light of this, Large Multimodal Models (LMMs) have emerged as a focal point of interest due to their remarkable capabilities in handling diverse multimodal tasks. In response to this development, our article aims to thoroughly examine the capacity of various LMMs (e.g., GPT-4V, LLaVA, and Qwen-VL) to discern and respond to the nuanced aspects of social abuse manifested in memes. We introduce the comprehensive meme benchmark, GOAT-Bench , comprising over 6K varied memes encapsulating themes, such as implicit hate speech, sexism, and cyberbullying. Utilizing GOAT-Bench , we delve into the ability of LMMs to accurately assess hatefulness, misogyny, offensiveness, sarcasm, and harmful content. Our extensive experiments across a range of LMMs reveal that current models still exhibit a deficiency in safety awareness, showing insensitivity to various forms of implicit abuse. We posit that this shortfall represents a critical impediment to the realization of safe artificial intelligence. The GOAT-Bench and accompanying resources are publicly accessible at https://goatlmm.github.io/ , contributing to ongoing research in this vital field.

Identifying harmful memes is challenging due to their implicit meanings, which are not always evident from texts and images alone. Existing solutions often lack clear explanations to justify their decisions. To address this gap, we propose an explainable approach,ExplainHM++, which detects harmful memes by reasoning over competing rationales from both harmful and harmless perspectives. First, inspired by the capabilities of Large Multimodal Models (LMMs) in text generation and multimodal reasoning, we developExplainHM, a one-stage multimodal debate in which LMMs generate explanations through contradictory arguments. Second, we fine-tune a small language model to serve as a judge in the debate, improving the integration of harmfulness rationales with the multimodal content of memes. However, we observe that a naive multimodal debate remains vulnerable, as it heavily depends on the inherent reasoning ability of LMMs to understand the memes. Given the evolving and noisy nature of memes, we further introduce a meme sample retrieval mechanism and a retrieval-augmented debate paradigm to strengthen and refine LMM-generated explanations. Extensive experiments on three public meme datasets demonstrate thatExplainHM++not only outperforms state-of-the-art methods but also provides superior, interpretable explanations for harmful meme detection.

Explainable fake news detection aims to assess the veracity of news claims while providing human-friendly explanations. Existing methods incorporating investigative journalism are often inefficient and struggle with breaking news. Recent advances in large language models (LLMs) enable leveraging externally retrieved reports as evidence for detection and explanation generation, but unverified reports may introduce inaccuracies. Moreover, effective explainable fake news detection should provide a comprehensible explanation for all aspects of a claim to assist the public in verifying its accuracy. To address these challenges, we propose a graph-enhanced defense framework (G-Defense) that provides fine-grained explanations based solely on unverified reports. Specifically, we construct a claim-centered graph by decomposing the news claim into several sub-claims and modeling their dependency relationships. For each sub-claim, we use the retrieval-augmented generation (RAG) technique to retrieve salient evidence and generate competing explanations. We then introduce a defense-like inference module based on the graph to assess the overall veracity. Finally, we prompt an LLM to generate an intuitive explanation graph. Experimental results demonstrate that G-Defense achieves state-of-the-art performance in both veracity detection and the quality of its explanations.

Large Language Model (LLM) agents have become increasingly prevalent across various realworld applications.They enhance decisionmaking by storing private user-agent interactions in the memory module for demonstrations, introducing new privacy risks for LLM agents.In this work, we systematically investigate the vulnerability of LLM agents to our proposed Memory EXTRaction Attack (MEXTRA) under a black-box setting.To extract private information from memory, we propose an effective attacking prompt design and an automated prompt generation method based on different levels of knowledge about the LLM agent.Experiments on two representative agents demonstrate the effectiveness of MEXTRA.Moreover, we explore key factors influencing memory leakage from both the agent designer's and the attacker's perspectives.Our findings highlight the urgent need for effective memory safeguards in LLM agent design and deployment.

The age of social media is flooded with Internet memes, necessitating a clear grasp and effective identification of harmful ones. This task presents a significant challenge due to the implicit meaning embedded in memes, which is not explicitly conveyed through the surface text and image. However, existing harmful meme detection methods do not present readable explanations that unveil such implicit meaning to support their detection decisions. In this paper, we propose an explainable approach to detect harmful memes, achieved through reasoning over conflicting rationales from both harmless and harmful positions. Specifically, inspired by the powerful capacity of Large Language Models (LLMs) on text generation and reasoning, we first elicit multimodal debate between LLMs to generate the explanations derived from the contradictory arguments. Then we propose to fine-tune a small language model as the debate judge for harmfulness inference, to facilitate multimodal fusion between the harmfulness rationales and the intrinsic multimodal information within memes. In this way, our model is empowered to perform dialectical reasoning over intricate and implicit harm-indicative patterns, utilizing multimodal explanations originating from both harmless and harmful arguments. Extensive experiments on three public meme datasets demonstrate that our harmful meme detection approach achieves much better performance than state-of-the-art methods and exhibits a superior capacity for explaining the meme harmfulness of the model predictions.

Most fake news detection methods learn latent feature representations based on neural networks, which makes them black boxes to classify a piece of news without giving any justification. Existing explainable systems generate veracity justifications from investigative journalism, which suffer from debunking delayed and low efficiency. Recent studies simply assume that the justification is equivalent to the majority opinions expressed in the wisdom of crowds. However, the opinions typically contain some inaccurate or biased information since the wisdom of crowds is uncensored. To detect fake news from a sea of diverse, crowded and even competing narratives, in this paper, we propose a novel defense-based explainable fake news detection framework. Specifically, we first propose an evidence extraction module to split the wisdom of crowds into two competing parties and respectively detect salient evidences. To gain concise insights from evidences, we then design a prompt-based module that utilizes a large language model to generate justifications by inferring reasons towards two possible veracities. Finally, we propose a defense-based inference module to determine veracity via modeling the defense among these justifications. Extensive experiments conducted on two real-world benchmarks demonstrate that our proposed method outperforms state-of-the-art baselines in terms of fake news detection and provides high-quality justifications.

Human-curated knowledge graphs provide critical supportive information to various natural language processing tasks, but these graphs are usually incomplete, urging auto-completion of them (a.k.a. knowledge graph completion). Prevalent graph embedding approaches, e.g., TransE, learn structured knowledge via representing graph elements (i.e., entities/relations) into dense embeddings and capturing their triple-level relationship with spatial distance. However, they are hardly generalizable to the elements never visited in training and are intrinsically vulnerable to graph incompleteness. In contrast, textual encoding approaches, e.g., KG-BERT, resort to graph triple’s text and triple-level contextualized representations. They are generalizable enough and robust to the incompleteness, especially when coupled with pre-trained encoders. But two major drawbacks limit the performance: (1) high overheads due to the costly scoring of all possible triples in inference, and (2) a lack of structured knowledge in the textual encoder. In this paper, we follow the textual encoding paradigm and aim to alleviate its drawbacks by augmenting it with graph embedding techniques – a complementary hybrid of both paradigms. Specifically, we partition each triple into two asymmetric parts as in translation-based graph embedding approach, and encode both parts into contextualized representations by a Siamese-style textual encoder. Built upon the representations, our model employs both deterministic classifier and spatial measurement for representation and structure learning respectively. It thus reduces the overheads by reusing graph elements’ embeddings to avoid combinatorial explosion, and enhances structured knowledge by exploring the spatial characteristics. Moreover, we develop a self-adaptive ensemble scheme to further improve the performance by incorporating triple scores from an existing graph embedding model. In experiments, we achieve state-of-the-art performance on three benchmarks and a zero-shot dataset for link prediction, with highlights of inference costs reduced by 1-2 orders of magnitude compared to a sophisticated textual encoding method.

The explosive growth of fake news along with destructive effects on politics, economy, and public safety has increased the demand for fake news detection. Fake news on social media does not exist independently in the form of an article. Many other entities, such as news creators, news subjects, and so on, exist on social media and have relationships with news articles. Different entities and relationships can be modeled as a heterogeneous information network (HIN). In this paper, we attempt to solve the fake news detection problem with the support of a news-oriented HIN. We propose a novel fake news detection framework, namely Adversarial Active Learning-based Heterogeneous Graph Neural Network (AA-HGNN) which employs a novel hierarchical attention mechanism to perform node representation learning in the HIN. AA-HGNN utilizes an active learning framework to enhance learning performance, especially when facing the paucity of labeled data. An adversarial selector will be trained to query high-value candidates for the active learning framework. When the adversarial active learning is completed, AA-HGNN detects fake news by classifying news article nodes. Experiments with two real-world fake news datasets show that our model can outperform text-based models and other graph-based models when using less labeled data benefiting from the adversarial active learning. As a model with generalizability, AA-HGNN also has the ability to be widely used in other node classification-related applications on heterogeneous graphs.