Metraipolis › archive › dc_20456a701aba

M$^3$R-Bench: A Unified Benchmark for Evidence-Grounded Multimodal Metaphor Understanding — arXiv:2608.05817

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.05817
License (as archived)
CC0-1.0
Archived
2026-10-25T21:27:16.298Z
SHA-256 of the archived text
2d0a74e720e84f17bc0e04e688daa53dbdc30fc67bd0f8bc6707c8d91b702030
Stable URL of this page
https://metraipolis.com/documento/dc_20456a701aba

How to cite

M$^3$R-Bench: A Unified Benchmark for Evidence-Grounded Multimodal Metaphor Understanding — arXiv:2608.05817 — arXiv (en), https://arxiv.org/abs/2608.05817 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_20456a701aba (Metraipolis archive dc_20456a701aba, sha256 2d0a74e720e84f17bc0e04e688daa53dbdc30fc67bd0f8bc6707c8d91b702030)
BibTeX
@misc{dc20456a701aba,
  title = {M$^3$R-Bench: A Unified Benchmark for Evidence-Grounded Multimodal Metaphor Understanding — arXiv:2608.05817},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.05817},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_20456a701aba; sha256 2d0a74e720e84f17bc0e04e688daa53dbdc30fc67bd0f8bc6707c8d91b702030},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05817. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal metaphor understanding requires identifying cross-domain Target-Source mappings and inferring sentiment from visual and textual evidence. However, existing benchmarks largely evaluate these subtasks separately and lack evidence-grounded explanations, limiting their ability to assess coherent cross-modal reasoning. To enable unified and evidence-grounded evaluation, we introduce M$^3$R-Bench, a benchmark of 1,000 human-annotated image-text instances with joint labels for metaphor occurrence, Target-Source mapping, and sentiment, alongside stage-wise explanations for evidence identification, mapping establishment, and sentiment inference. Evaluations reveal that existing models frequently rely on textual shortcuts and produce Target-Source mappings inconsistent with visual evidence. To address this evidence-mapping mismatch, we propose M$^3$R-Reasoner, which combines curriculum-based reasoning supervision with task-aware reinforcement learning. Built on an 8B-parameter backbone, M$^3$R-Reasoner achieves 37.90% Joint Label Accuracy (JLA) metric, outperforming the strongest proprietary baseline by 19.50 percentage points. It further surpasses GPT-5.5 in image-text evidence and sentiment justification scores by 28.45 and 28.11 points, respectively. The dataset and code are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.05817 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-25T21:24:38.208Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).