Metraipolis › archive › dc_279c246fdcf6
SignRAG: Unified Retrieval-Augmented Gloss-Free Sign Language Translation — arXiv:2610.11371
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11371
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:06:17.481Z
- SHA-256 of the archived text
9d48abece021630d3f8de2a3eea0e8f96d2a34145697c263ef53ba7f6fe77241- Stable URL of this page
https://metraipolis.com/documento/dc_279c246fdcf6
How to cite
SignRAG: Unified Retrieval-Augmented Gloss-Free Sign Language Translation — arXiv:2610.11371 — arXiv (en), https://arxiv.org/abs/2610.11371 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_279c246fdcf6 (Metraipolis archive dc_279c246fdcf6, sha256 9d48abece021630d3f8de2a3eea0e8f96d2a34145697c263ef53ba7f6fe77241)
BibTeX
@misc{dc279c246fdcf6,
title = {SignRAG: Unified Retrieval-Augmented Gloss-Free Sign Language Translation — arXiv:2610.11371},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11371},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_279c246fdcf6; sha256 9d48abece021630d3f8de2a3eea0e8f96d2a34145697c263ef53ba7f6fe77241},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11371. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Contemporary decoder-only large language models (LLMs) have demonstrated strong capabilities across a wide range of domains. However, existing pretraining paradigms for gloss-free sign language translation (SLT) are largely designed around conventional encoder-decoder pretrained language models, which limits their direct applicability to decoder-only LLMs. To address this limitation, we propose SignRAG, a unified framework combining hierarchical pretraining, target-domain retrieval augmentation, and retrieval-aware reinforcement fine-tuning. Hierarchical pretraining first learns linguistically grounded sign representations and then jointly aligns the sign encoder with an LLM, mitigating cross-modal optimization imbalance. For downstream adaptation, SignRAG complements parameter-based fine-tuning with a target-domain retrieval gallery that provides instance-specific translation cues. To ensure that retrieved contexts are used appropriately, we further introduce Retrieval Utility-Guided Reinforcement Fine-Tuning (RUG-RFT), which combines translation-quality and retrieval-utility rewards to encourage beneficial retrieval use while suppressing harmful reliance. Experiments on multiple SLT benchmarks establish new state-of-the-art performance. In particular, to the best of our knowledge, SignRAG is the first gloss-free approach to outperform gloss-supervised methods across all reported metrics on CSL-Daily. Our code has been released at \href{ this https URL }{GitHub}, together with models of different sizes to support future academic research.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM).
Pagina del lavoro: https://arxiv.org/abs/2610.11371 — 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 2026-10-09T05:47:15.197Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).