Metraipolis › archive › dc_5f950c66ed06

Cross Lingual Transfer in Tulu Legal Comprehension: Script-Dependent Improvement and RAG-Induced Knowledge Conflict — arXiv:2608.28645

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28645
License (as archived)
CC0-1.0
Archived
2026-10-17T07:47:12.400Z
SHA-256 of the archived text
61c72ce0f1dff7c8afab93d6ceb15a35e15f489373f7cfd5b10a75256a70eaab
Stable URL of this page
https://metraipolis.com/documento/dc_5f950c66ed06

How to cite

Cross Lingual Transfer in Tulu Legal Comprehension: Script-Dependent Improvement and RAG-Induced Knowledge Conflict — arXiv:2608.28645 — arXiv (en), https://arxiv.org/abs/2608.28645 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5f950c66ed06 (Metraipolis archive dc_5f950c66ed06, sha256 61c72ce0f1dff7c8afab93d6ceb15a35e15f489373f7cfd5b10a75256a70eaab)
BibTeX
@misc{dc5f950c66ed06,
  title = {Cross Lingual Transfer in Tulu Legal Comprehension: Script-Dependent Improvement and RAG-Induced Knowledge Conflict — arXiv:2608.28645},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28645},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5f950c66ed06; sha256 61c72ce0f1dff7c8afab93d6ceb15a35e15f489373f7cfd5b10a75256a70eaab},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28645. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Low-resource languages without an adequate training corpus often use a related, higher-resource language as a scaffold for comprehension. Still, there is a need to develop rigorous evaluation methods to identify when models fail in cross lingual low-resource environments. Using the legal domain as a backdrop, three models (Llama3, Hex-1, Sarvam) were tested on the ability to classify legal complaints written in a low resource Dravidian language (Tulu). Transliterating queries across Dravidian scripts allowed models to gain a preliminary understanding of speakers' complaints without the use of wide scale training, though the level of comprehension was heavily script dependent (with Kannada - another relatively low-resource language - producing the strongest positive trend). Retrieving from a corpus of Kannada legal papers across a RAG framework caused mixed results. Some models had a weak positive trend in comprehension under certain conditions, but when models failed, it was often across two axes: fact substitution (fixating on specific passage excerpts that skewed reasoning) and confabulation (hallucination that had no basis in either query or corpus). Within low resource domains, results identify the model's parsing of information and subsequent reasoning as the source of reasoning failure, rather than corpus contents. Script-dependent comprehension and RAG robustness also seem to travel together. This is further supported by the reasoning-trace analysis and a statistical-honesty framework deployed - techniques that are more broadly applicable to low-resource multilingual RAG evaluation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.28645 — 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 2026-10-17T07:28:26.674Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).