Metraipolis › archive › dc_8d37ab76a38d

TRACE: Training-aware Robustness and Challenge Evaluation for Text-Vision Embedding Models — arXiv:2610.26993

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.26993
License (as archived)
CC0-1.0
Archived
2026-10-21T07:08:46.207Z
SHA-256 of the archived text
5ec5dca2a28df22decdf208eaf6b877f23e28cbc6dc13afffade47417e9df1cb
Stable URL of this page
https://metraipolis.com/documento/dc_8d37ab76a38d

How to cite

TRACE: Training-aware Robustness and Challenge Evaluation for Text-Vision Embedding Models — arXiv:2610.26993 — arXiv (en), https://arxiv.org/abs/2610.26993 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8d37ab76a38d (Metraipolis archive dc_8d37ab76a38d, sha256 5ec5dca2a28df22decdf208eaf6b877f23e28cbc6dc13afffade47417e9df1cb)
BibTeX
@misc{dc8d37ab76a38d,
  title = {TRACE: Training-aware Robustness and Challenge Evaluation for Text-Vision Embedding Models — arXiv:2610.26993},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.26993},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8d37ab76a38d; sha256 5ec5dca2a28df22decdf208eaf6b877f23e28cbc6dc13afffade47417e9df1cb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.26993. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Existing benchmarks for text-vision embedding models report aggregate scores that obscure whether performance comes from general capabilities, task-specific adaptation, or robustness to challenging tasks. We introduce TRACE, a Training-aware Robustness and Challenge Evaluation framework that reorganizes 168 tasks from various sources of datasets into three categories: General, Adaptability, and Challenge. Through controlled experiments on two text-vision embedding models, we show that combining general and adaptation data improves Adaptability performance by 7.67 and 7.09 points, respectively, while largely preserving General performance. However, Challenge performance remains below 5.0, with limited improvements from additional training data. Further analysis identifies multilingual and visual-document tasks as major weaknesses. Our findings demonstrate that data adaptation alone is insufficient to address these challenges, highlighting the need for methodological advances beyond data-centric improvements.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.26993 — 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 2026-10-21T07:05:58.094Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).