Pith. sign in

REVIEW 5 cited by

DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2412.10510 v4 pith:E734JRCR submitted 2024-12-13 cs.CV cs.CL

Tobias Braun , Mark Rothermel , Marcus Rohrbach , Anna Rohrbach This is my paper
classification cs.CVcs.CL
keywords defamefact-checkingmultimodalclaimsdynamicevidenceevidence-basedexperts
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The proliferation of disinformation demands reliable and scalable fact-checking solutions. We present Dynamic Evidence-based FAct-checking with Multimodal Experts (DEFAME), a modular, zero-shot MLLM pipeline for open-domain, text-image claim verification. DEFAME operates in a six-stage process, dynamically selecting the tools and search depth to extract and evaluate textual and visual evidence. Unlike prior approaches that are text-only, lack explainability, or rely solely on parametric knowledge, DEFAME performs end-to-end verification, accounting for images in claims and evidence while generating structured, multimodal reports. Evaluation on the popular benchmarks VERITE, AVerITeC, and MOCHEG shows that DEFAME surpasses all previous methods, establishing itself as the new state-of-the-art fact-checking system for uni- and multimodal fact-checking. Moreover, we introduce a new multimodal benchmark, ClaimReview2024+, featuring claims after the knowledge cutoff of GPT-4o, avoiding data leakage. Here, DEFAME drastically outperforms the GPT-4o baselines, showing temporal generalizability and the potential for real-time fact-checking.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

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

  1. KG-ViP: Bridging Knowledge Grounding and Visual Perception in Multi-modal LLMs for Visual Question Answering

    cs.CV 2026-01 unverdicted novelty 6.0 of 10

    KG-ViP fuses scene graphs and commonsense graphs via a query-based retrieval-and-fusion pipeline to improve multi-modal LLM performance on visual question answering.

  2. CrediBench: Building Web-Scale Network Datasets for Information Integrity

    cs.SI 2025-09 reject novelty 5.0 of 10

    CrediBench presents a one-month, 1-billion-edge Common Crawl web graph with text and 11.5K expert credibility labels, while the abstract's promised 8-month dataset and 85%-accuracy classifier are absent from the paper.

  3. D-SECURE: Dual-Source Evidence Combination for Unified Reasoning in Misinformation Detection

    cs.CV 2026-02 reject novelty 4.0 of 10

    D-SECURE fuses local manipulation detection with external evidence fact-checking, but the reported gains are undermined by a weaker strict accuracy and a post-hoc evaluation protocol.

  4. Multimedia Verification Through Multi-Agent Deep Research Multimodal Large Language Models

    cs.CV 2025-07 conditional novelty 4.0 of 10

    A six-stage multi-agent MLLM pipeline with reverse image search, metadata analysis, and fact-checking tools is demonstrated on a single Ukraine missile-strike video, with no quantitative evaluation.

  5. AI4Research: A Survey of Artificial Intelligence for Scientific Research

    cs.CL 2025-07 conditional novelty 4.0 of 10

    A survey that organizes AI-for-research work into five tasks, comprehension, survey, discovery, writing, and peer review, and compiles associated tools and benchmarks.

Pith tools