Metraipolis › archive › dc_fef0c9745a48
Pole or Vector? Encoders Capture Bangla Compound Verbs, but LLMs Read Them Literally — arXiv:2611.10909
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.10909
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:44:31.782Z
- SHA-256 of the archived text
3a227a0db9d584524daaf6a178c5b49bf9ab4ad44a98478df891a00ccdfbb4dd- Stable URL of this page
https://metraipolis.com/documento/dc_fef0c9745a48
How to cite
Pole or Vector? Encoders Capture Bangla Compound Verbs, but LLMs Read Them Literally — arXiv:2611.10909 — arXiv (en), https://arxiv.org/abs/2611.10909 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fef0c9745a48 (Metraipolis archive dc_fef0c9745a48, sha256 3a227a0db9d584524daaf6a178c5b49bf9ab4ad44a98478df891a00ccdfbb4dd)
BibTeX
@misc{dcfef0c9745a48,
title = {Pole or Vector? Encoders Capture Bangla Compound Verbs, but LLMs Read Them Literally — arXiv:2611.10909},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.10909},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fef0c9745a48; sha256 3a227a0db9d584524daaf6a178c5b49bf9ab4ad44a98478df891a00ccdfbb4dd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10909. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In Bangla, a main verb is often followed by one of a small set of vector verbs. These verbs lose their own meaning and add a shade of meaning instead, such as completion. For example, likhe phello means that someone finished writing, not that they wrote and threw something. The same two verbs can also describe two separate events, so only the context shows which meaning is meant. This makes compound verbs a hard test of how language models handle multiword expressions. We present BanglaCV-Probe, a benchmark of 17 vector verbs with 1,044 minimal pairs, 204 entailment items and 197 pairs of correct and incorrect combinations, all checked by native speakers. We test 26 models (encoders, LLMs and translation systems) on four skills: telling the two meanings apart internally, understanding what a vector adds, preferring correct combinations and keeping the vector's meaning in translation. Probes on five encoders tell the two meanings apart and still reach up to 93% accuracy when trained on pairs without surface cues. Prompted models rarely use this knowledge. Entailment accuracy stays between 59% and 81%. Several LLMs answer Yes or No to almost every item, and nine of ten models miss that someone who ate up the rice left none. Most instruction-tuned LLMs translate vectors literally in 15-20% of vector sentences and in up to 55% for mora (die). On correct combinations, a small Bangla-only model (88%) matches BLOOM-7B1 (87%) and both beat Qwen2.5-7B (74%). Data and code: this https URL 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/2611.10909 — 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 2026-11-10T18:37:52.430Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).