Towards Automated Community Notes Generation with Large Vision Language Models for Combating Contextual Deception

• URL: http://arxiv.org/abs/2603.22453v1
• Date: Mon, 23 Mar 2026 18:21:23 GMT
• Title: Towards Automated Community Notes Generation with Large Vision Language Models for Combating Contextual Deception
• Abstract summary: We study the automated Community Notes generation method for image-based contextual deception.<n>Unlike prior work that primarily focuses on deception detection, Community Notes-style systems need to generate concise and grounded notes.<n>We propose ACCNote, a retrieval-augmented, multi-agent collaboration framework built on large vision-language models.
• Score: 8.79051023144961
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Community Notes have emerged as an effective crowd-sourced mechanism for combating online deception on social media platforms. However, its reliance on human contributors limits both the timeliness and scalability. In this work, we study the automated Community Notes generation method for image-based contextual deception, where an authentic image is paired with misleading context (e.g., time, entity, and event). Unlike prior work that primarily focuses on deception detection (i.e., judging whether a post is true or false in a binary manner), Community Notes-style systems need to generate concise and grounded notes that help users recover the missing or corrected context. This problem remains underexplored due to three reasons: (i) datasets that support the research are scarce; (ii) methods must handle the dynamic nature of contextual deception; (iii) evaluation is difficult because standard metrics do not capture whether notes actually improve user understanding. To address these gaps, we curate a real-world dataset, XCheck, comprising X posts with associated Community Notes and external contexts. We further propose the Automated Context-Corrective Note generation method, named ACCNote, which is a retrieval-augmented, multi-agent collaboration framework built on large vision-language models. Finally, we introduce a new evaluation metric, Context Helpfulness Score (CHS), that aligns with user study outcomes rather than relying on lexical overlap. Experiments on our XCheck dataset show that the proposed ACCNote improves both deception detection and note generation performance over baselines, and exceeds a commercial tool GPT5-mini. Together, our dataset, method, and metric advance practical automated generation of context-corrective notes toward more responsible online social networks.

Related papers

• From Static Benchmarks to Dynamic Protocol: Agent-Centric Text Anomaly Detection for Evaluating LLM Reasoning [12.024430772980502]
  We introduce an agent-centric benchmarking paradigm for evaluating large language models.<n>A teacher agent generates candidate problems, an orchestrator agent rigorously verifies their validity and guards against adversarial attacks.<n>If a student correctly solves the problem, the orchestrator prompts the teacher to generate more challenging variants.
  arXiv  Detail & Related papers  (2026-02-27T06:54:32Z)
• Graphically Speaking: Unmasking Abuse in Social Media with Conversation Insights [10.188075925271471]
  Abusive language in social media conversations depends on the conversational context, characterized by the content and topology of preceding comments.<n>Traditional Abusive Language Detection models often overlook this context, which can lead to unreliable performance metrics.<n>Recent Natural Language Processing (NLP) methods that integrate conversational context often depend on limited and simplified representations, and report inconsistent results.<n>We propose a novel approach that utilize graph neural networks (GNNs) to model social media conversations as graphs, where nodes represent comments, and edges capture reply structures.
  arXiv  Detail & Related papers  (2025-04-02T17:03:37Z)
• Towards Realistic Evaluation of Commit Message Generation by Matching Online and Offline Settings [77.20838441870151]
  We use an online metric - the number of edits users introduce before committing the generated messages to the VCS - to select metrics for offline experiments.<n>We collect a dataset with 57 pairs consisting of commit messages generated by GPT-4 and their counterparts edited by human experts.<n>Our results indicate that edit distance exhibits the highest correlation with the online metric, whereas commonly used similarity metrics such as BLEU and METEOR demonstrate low correlation.
  arXiv  Detail & Related papers  (2024-10-15T20:32:07Z)
• Annotator in the Loop: A Case Study of In-Depth Rater Engagement to Create a Bridging Benchmark Dataset [1.825224193230824]
  We describe a novel, collaborative, and iterative annotator-in-the-loop methodology for annotation. Our findings indicate that collaborative engagement with annotators can enhance annotation methods.
  arXiv  Detail & Related papers  (2024-08-01T19:11:08Z)
• Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models [84.8919069953397]
  Self-TAught Recognizer (STAR) is an unsupervised adaptation framework for speech recognition systems. We show that STAR achieves an average of 13.5% relative reduction in word error rate across 14 target domains. STAR exhibits high data efficiency that only requires less than one-hour unlabeled data.
  arXiv  Detail & Related papers  (2024-05-23T04:27:11Z)
• Bring Your Own Data! Self-Supervised Evaluation for Large Language Models [52.15056231665816]
  We propose a framework for self-supervised evaluation of Large Language Models (LLMs) We demonstrate self-supervised evaluation strategies for measuring closed-book knowledge, toxicity, and long-range context dependence. We find strong correlations between self-supervised and human-supervised evaluations.
  arXiv  Detail & Related papers  (2023-06-23T17:59:09Z)
• Cognitive Semantic Communication Systems Driven by Knowledge Graph: Principle, Implementation, and Performance Evaluation [74.38561925376996]
  Two cognitive semantic communication frameworks are proposed for the single-user and multiple-user communication scenarios. An effective semantic correction algorithm is proposed by mining the inference rule from the knowledge graph. For the multi-user cognitive semantic communication system, a message recovery algorithm is proposed to distinguish messages of different users.
  arXiv  Detail & Related papers  (2023-03-15T12:01:43Z)
• TRUE: Re-evaluating Factual Consistency Evaluation [29.888885917330327]
  We introduce TRUE: a comprehensive study of factual consistency metrics on a standardized collection of existing texts from diverse tasks. Our standardization enables an example-level meta-evaluation protocol that is more actionable and interpretable than previously reported correlations. Across diverse state-of-the-art metrics and 11 datasets we find that large-scale NLI and question generation-and-answering-based approaches achieve strong and complementary results.
  arXiv  Detail & Related papers  (2022-04-11T10:14:35Z)
• Detecting Offensive Language on Social Networks: An End-to-end Detection Method based on Graph Attention Networks [7.723697303436006]
  We propose an end-to-end method based on community structure and text features for offensive language detection (CT-OLD) We add user opinion to the community structure for representing user features. The user opinion is represented by user historical behavior information, which outperforms that represented by text information.
  arXiv  Detail & Related papers  (2022-03-04T03:57:18Z)
• GO FIGURE: A Meta Evaluation of Factuality in Summarization [131.1087461486504]
  We introduce GO FIGURE, a meta-evaluation framework for evaluating factuality evaluation metrics. Our benchmark analysis on ten factuality metrics reveals that our framework provides a robust and efficient evaluation. It also reveals that while QA metrics generally improve over standard metrics that measure factuality across domains, performance is highly dependent on the way in which questions are generated.
  arXiv  Detail & Related papers  (2020-10-24T08:30:20Z)
• Learning an Unreferenced Metric for Online Dialogue Evaluation [53.38078951628143]
  We propose an unreferenced automated evaluation metric that uses large pre-trained language models to extract latent representations of utterances. We show that our model achieves higher correlation with human annotations in an online setting, while not requiring true responses for comparison during inference.
  arXiv  Detail & Related papers  (2020-05-01T20:01:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.