Metraipolis › archive › dc_eb698449a088

Extracting Arguments, Not Just Classifying Them: Instruction-Tuned LLMs for Generative Component Detection — arXiv:2609.24855

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24855
License (as archived)
CC0-1.0
Archived
2026-10-09T06:50:43.404Z
SHA-256 of the archived text
ee391019394223f47b1c65fb0854aa868cc8e2acc437f0adfebfff1daa5758fb
Stable URL of this page
https://metraipolis.com/documento/dc_eb698449a088

How to cite

Extracting Arguments, Not Just Classifying Them: Instruction-Tuned LLMs for Generative Component Detection — arXiv:2609.24855 — arXiv (en), https://arxiv.org/abs/2609.24855 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eb698449a088 (Metraipolis archive dc_eb698449a088, sha256 ee391019394223f47b1c65fb0854aa868cc8e2acc437f0adfebfff1daa5758fb)
BibTeX
@misc{dceb698449a088,
  title = {Extracting Arguments, Not Just Classifying Them: Instruction-Tuned LLMs for Generative Component Detection — arXiv:2609.24855},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24855},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eb698449a088; sha256 ee391019394223f47b1c65fb0854aa868cc8e2acc437f0adfebfff1daa5758fb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24855. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Argumentative component detection (ACD) is a core subtask of Argument(ation) Mining (AM) and one of its most challenging aspects, as it requires jointly delimiting argumentative spans and classifying them into components such as claims and premises. While research on this subtask remains relatively limited compared to other AM tasks, most existing approaches formulate it as a simplified sequence labeling problem, component classification, or a pipeline of component segmentation followed by classification. In this paper, we propose ITFACD, a novel approach based on instruction-tuned Large Language Models (LLMs) using compact instruction-based prompts, and reframe ACD as a language generation task, enabling arguments to be identified directly from plain text without relying on pre-segmented components. Experiments on standard benchmarks show that our approach achieves higher performance compared to state-of-the-art systems. To the best of our knowledge, this is one of the first attempts to fully model ACD as a generative task, highlighting the potential of instruction tuning for complex AM problems. Our code and the datasets used are openly available in the following GitHub repository.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.24855 — 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 2026-10-09T06:48:45.155Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).