Metraipolis › archive › dc_e332efbf7ca9

GRIT: Gradient Masking for Visually Misgrounded Tokens in Text-Rich Reasoning — arXiv:2610.41629

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41629
License (as archived): CC0-1.0
Archived: 2026-11-03T08:03:20.680Z
SHA-256 of the archived text: 2653b881ce3880078f876595daddf19d218daea842969cd76998a1d1c1527094
Stable URL of this page: https://metraipolis.com/documento/dc_e332efbf7ca9

How to cite

GRIT: Gradient Masking for Visually Misgrounded Tokens in Text-Rich Reasoning — arXiv:2610.41629 — arXiv (en), https://arxiv.org/abs/2610.41629 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e332efbf7ca9 (Metraipolis archive dc_e332efbf7ca9, sha256 2653b881ce3880078f876595daddf19d218daea842969cd76998a1d1c1527094)

BibTeX

@misc{dce332efbf7ca9,
  title = {GRIT: Gradient Masking for Visually Misgrounded Tokens in Text-Rich Reasoning — arXiv:2610.41629},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41629},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e332efbf7ca9; sha256 2653b881ce3880078f876595daddf19d218daea842969cd76998a1d1c1527094},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41629. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reinforcement learning with verifiable rewards (RLVR) has recently been extended to vision-language models (VLMs), yet its effectiveness remains limited for text-rich reasoning tasks. We highlight a key factor contributing to this limitation: models frequently arrive at correct final answers despite misperceiving visual information during intermediate steps. We define this phenomenon as Correct-but-Visually-Misgrounded Reasoning (CVMR). Because standard RLVR rewards only final-answer correctness, it fails to differentiate between properly grounded and misgrounded reasoning, reinforcing both equally. Through token-level analysis, we reveal that CVMR tokens exhibit distinct attention patterns that differ systematically from well-grounded ones. Based on this observation, we propose GRIT, a training framework that incorporates visual grounding into RLVR to mitigate the impact of CVMR. Furthermore, to address the lack of text-rich reasoning benchmarks that allow for systematic evaluation across text length and reasoning depth, we introduce GRIT-Bench. Experiments demonstrate that GRIT significantly improves both reasoning accuracy and grounding fidelity over existing RLVR methods.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.41629 — 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 2026-11-03T07:59:38.813Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).