Reinforcement Tuning for Detecting Stances and Debunking Rumors Jointly with Large Language Models

Learning multi-task models for jointly detecting stance and verifying rumors poses challenges due to the need for training data of stance at post level and rumor veracity at claim level, which are difficult to obtain. To address this issue, we leverage large language models (LLMs) as the foundation annotators for the joint stance detection (SD) and rumor verification (RV) tasks, dubbed as JSDRV. We introduce a novel reinforcement tuning framework to enhance the joint predictive capabilities of LLM-based SD and RV components. Specifically, we devise a policy for selecting LLM-annotated data at the two levels, employing a hybrid reward mechanism to choose high-quality labels for effective LLM fine-tuning on both tasks. Results demonstrate that JSDRV improves the capabilities of LLMs in the joint tasks, not only outperforming state-of-the-art methods but also generalizing to non-LLMs accommodated as task models.

Explainable Fake News Detection With Large Language Model via Defense Among Competing Wisdom

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.

Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models

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.

GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse

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 imagery. 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 paper aims to thoroughly examine the capacity of various LMMs (e.g. GPT-4V) 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, etc. 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.

WSDMS: Debunk Fake News via Weakly Supervised Detection of Misinforming Sentences with Contextualized Social Wisdom

In recent years, we witness the explosion of false and unconfirmed information (i.e., rumors) that went viral on social media and shocked the public. Rumors can trigger versatile, mostly controversial stance expressions among social media users. Rumor verification and stance detection are different yet relevant tasks. Fake news debunking primarily focuses on determining the truthfulness of news articles, which oversimplifies the issue as fake news often combines elements of both truth and falsehood. Thus, it becomes crucial to identify specific instances of misinformation within the articles. In this research, we investigate a novel task in the field of fake news debunking, which involves detecting sentence-level misinformation. One of the major challenges in this task is the absence of a training dataset with sentence-level annotations regarding veracity. Inspired by the Multiple Instance Learning (MIL) approach, we propose a model called Weakly Supervised Detection of Misinforming Sentences (WSDMS). This model only requires bag-level labels for training but is capable of inferring both sentence-level misinformation and article-level veracity, aided by relevant social media conversations that are attentively contextualized with news sentences. We evaluate WSDMS on three real-world benchmarks and demonstrate that it outperforms existing state-of-the-art baselines in debunking fake news at both the sentence and article levels.

A Unified Contrastive Transfer Framework with Propagation Structure for Boosting Low-Resource Rumor Detection

The truth is significantly hampered by massive rumors that spread along with breaking news or popular topics. Since there is sufficient corpus gathered from the same domain for model training, existing rumor detection algorithms show promising performance on yesterday's news. However, due to a lack of substantial training data and prior expert knowledge, they are poor at spotting rumors concerning unforeseen events, especially those propagated in different languages (i.e., low-resource regimes). In this paper, we propose a unified contrastive transfer framework to detect rumors by adapting the features learned from well-resourced rumor data to that of the low-resourced with only few-shot annotations. More specifically, we first represent rumor circulated on social media as an undirected topology for enhancing the interaction of user opinions, and then train a Multi-scale Graph Convolutional Network via a unified contrastive paradigm to mine effective clues simultaneously from post semantics and propagation structure. Our model explicitly breaks the barriers of the domain and/or language issues, via language alignment and a novel domain-adaptive contrastive learning mechanism. To well-generalize the representation learning using a small set of annotated target events, we reveal that rumor-indicative signal is closely correlated with the uniformity of the distribution of these events. We design a target-wise contrastive training mechanism with three event-level data augmentation strategies, capable of unifying the representations by distinguishing target events. Extensive experiments conducted on four low-resource datasets collected from real-world microblog platforms demonstrate that our framework achieves much better performance than state-of-the-art methods and exhibits a superior capacity for detecting rumors at early stages.

A Weakly Supervised Propagation Model for Rumor Verification and Stance Detection with Multiple Instance Learning

The diffusion of rumors on microblogs generally follows a propagation tree structure, that provides valuable clues on how an original message is transmitted and responded by users over time. Recent studies reveal that rumor detection and stance detection are two different but relevant tasks which can jointly enhance each other, e.g., rumors can be debunked by cross-checking the stances conveyed by their relevant microblog posts, and stances are also conditioned on the nature of the rumor. However, most stance detection methods require enormous post-level stance labels for training, which are labor-intensive given a large number of posts. Enlightened by Multiple Instance Learning (MIL) scheme, we first represent the diffusion of claims with bottom-up and top-down trees, then propose two tree-structured weakly supervised frameworks to jointly classify rumors and stances, where only the bag-level labels concerning claim's veracity are needed. Specifically, we convert the multi-class problem into a multiple MIL-based binary classification problem where each binary model focuses on differentiating a target stance or rumor type and other types. Finally, we propose a hierarchical attention mechanism to aggregate the binary predictions, including (1) a bottom-up or top-down tree attention layer to aggregate binary stances into binary veracity; and (2) a discriminative attention layer to aggregate the binary class into finer-grained classes. Extensive experiments conducted on three Twitter-based datasets demonstrate promising performance of our model on both claim-level rumor detection and post-level stance classification compared with state-of-the-art methods.