Metraipolis › archive › dc_4a06fe638dba

Generative vs. Encoder Models for Multilingual NER: A Comprehensive Empirical Study on Naamapadam — arXiv:2608.29959

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29959
License (as archived)
CC0-1.0
Archived
2026-10-17T08:07:18.375Z
SHA-256 of the archived text
54a3fa21d3bd85c553b836ed4ad9944ae453e8385ae0405830221d7d851400de
Stable URL of this page
https://metraipolis.com/documento/dc_4a06fe638dba

How to cite

Generative vs. Encoder Models for Multilingual NER: A Comprehensive Empirical Study on Naamapadam — arXiv:2608.29959 — arXiv (en), https://arxiv.org/abs/2608.29959 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4a06fe638dba (Metraipolis archive dc_4a06fe638dba, sha256 54a3fa21d3bd85c553b836ed4ad9944ae453e8385ae0405830221d7d851400de)
BibTeX
@misc{dc4a06fe638dba,
  title = {Generative vs. Encoder Models for Multilingual NER: A Comprehensive Empirical Study on Naamapadam — arXiv:2608.29959},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29959},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4a06fe638dba; sha256 54a3fa21d3bd85c553b836ed4ad9944ae453e8385ae0405830221d7d851400de},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29959. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Language is humanity's most consequential technology, yet for over a billion speakers across India's twenty-two constitutionally recognised languages, its digital layer remains structurally incomplete. Named Entity Recognition (NER), the foundational step in transforming raw text into machine-interpretable knowledge, has been studied exhaustively for English but remains largely unsolved across most Indic languages. This paper presents a rigorous comparative study of generative and encoder-based neural architectures for NER on all eleven languages of the Naamapadam benchmark. We evaluate five classic model families spanning sequence-to-sequence transformers and multilingual encoders; four decoder-only large language models (LLMs) fine-tuned with LoRA and 4-bit NF4 quantisation; and nine generative models in zero-to-5-shot inference. Under strict CoNLL span-level evaluation, encoder-based models (mBERT and XLM-R, both F1=0.675 on Hindi) substantially outperform every generative architecture in ten of eleven languages, with gaps of 7.5-40 percentage points against the strongest competitor (Gemma-2-2B: avg F1=0.427). The best few-shot result reaches only 28% of the encoder baseline. We identify three language clusters--encoder-dominant, partial-coverage, and failure-zone; and provide actionable deployment guidelines grounded in transfer learning and low-resource NLP principles.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.29959 — 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 2026-10-17T07:47:52.764Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).