SciFigPlag-Bench: Benchmark Challenges LLMs on Figure Plagiarism
anshulkundaje · x · 2026-08-19
Frontier LLMs still struggle to detect duplicated figures in academic journals, a challenging computational task, especially when plagiarism spans multiple articles. Researchers introduced SciFigPlag-Bench, a new benchmark with 2,582 positive and 2,541 negative pairs. It supports four diagnostic tasks: pairwise detection, source attribution, hierarchical reuse-type classification, and reuse correspondence localization. Experiments reveal persistent challenges in fine-grained provenance reasoning and spatial correspondence for current vision-language models.
More from Multimodal
- Seedance 2.5 goes live globally on CapCut with 1080p output for ad-variant workflows — AIwithGhotai · 2026-08-19
- Looking for a ComfyUI node to enhance prompts for Minimax H3 based on reference context — Ambitious_Fold_2874 · 2026-08-19
- MiniMax H3 Experiment: Hyper-realistic Video of Whale Swimming Over City — cocktailpeanut · 2026-08-19
- AI Art Showcase: Self-Portrait Generated by GPT5.6 Sol Pro — repligate · 2026-08-19
- Minimax H3 reference-to-video test: Zelda mashup with multiple image refs — dramaton42 · 2026-08-19
- Seele AI launches 3D Agent to generate complete scenes from prompts — SimplyAnnisa · 2026-08-19