Pith. sign in

REVIEW 7 cited by

LEMMA: Towards LVLM-Enhanced Multimodal Misinformation Detection with External Knowledge Augmentation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.11943 v2 pith:5GPQXTR7 submitted 2024-02-19 cs.CL

classification cs.CL
keywords lvlmmisinformationdetectionknowledgemultimodalreasoningexternallemma
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The rise of multimodal misinformation on social platforms poses significant challenges for individuals and societies. Its increased credibility and broader impact compared to textual misinformation make detection complex, requiring robust reasoning across diverse media types and profound knowledge for accurate verification. The emergence of Large Vision Language Model (LVLM) offers a potential solution to this problem. Leveraging their proficiency in processing visual and textual information, LVLM demonstrates promising capabilities in recognizing complex information and exhibiting strong reasoning skills. In this paper, we first investigate the potential of LVLM on multimodal misinformation detection. We find that even though LVLM has a superior performance compared to LLMs, its profound reasoning may present limited power with a lack of evidence. Based on these observations, we propose LEMMA: LVLM-Enhanced Multimodal Misinformation Detection with External Knowledge Augmentation. LEMMA leverages LVLM intuition and reasoning capabilities while augmenting them with external knowledge to enhance the accuracy of misinformation detection. Our method improves the accuracy over the top baseline LVLM by 7% and 13% on Twitter and Fakeddit datasets respectively.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Verification-Notebook Learning for Source-Aware Multimodal Misinformation Detection

    cs.AI 2026-07 conditional novelty 6.0 of 10

    Verification-Notebook Learning distills labeled multimodal verification experience into a compact fixed notebook that lifts frozen-LVLM source-aware misinformation detection above prompting, cases, and agents.

  2. Detecting AI-Generated Video: A Vision-Language Dual-View Survey

    cs.CV 2026-07 conditional novelty 6.0 of 10

    AIGC-V detection should be treated as factual fidelity verification and organized by a four-layer vision-language dual-view taxonomy spanning cues, motion, cross-modal consistency, and world-level reasoning.

  3. XFacta: Contemporary, Real-World Dataset and Evaluation for Multimodal Misinformation Detection with Multimodal LLMs

    cs.CL 2025-08 conditional novelty 6.0 of 10

    XFacta is a new real-world, post-January-2024 multimodal misinformation dataset from X, and evaluations show that MLLM detectors need external evidence, especially image-to-text evidence, with multi-step reasoning per...

  4. Large Language Models and Social Media Information Integrity: Opportunities, Challenges, and Research Directions

    cs.CR 2026-08 conditional novelty 4.0 of 10

    A systematic review of 215 studies concludes that large language models both enable and counter misinformation, social bots, and privacy threats on social media, and maps open research gaps.

  5. MV-Debate: Multi-view Agent Debate with Dynamic Reflection Gating for Multimodal Harmful Content Detection in Social Media

    cs.AI 2025-08 conditional novelty 4.0 of 10

    MV-Debate uses four specialized reasoning agents plus judgment-gated reflection to detect sarcasm, hate speech, and misinformation in image-text posts, reporting top accuracy on three 500-sample benchmarks.

  6. A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models

    cs.IR 2025-07 reject novelty 3.0 of 10

    A survey claims proactive defenses against LLM misinformation outperform post-hoc detection by up to 63%, but no meta-analysis details are provided to support the claim.

  7. AI-Generated Content in Cross-Domain Applications: Research Trends, Challenges and Propositions

    cs.AI 2025-09 conditional novelty 2.0 of 10

    A cross-domain vision paper that surveys AI-generated content and proposes research directions, without introducing new empirical results.

Pith tools