LLM-driven argumentation for explainable text classification
Identification
- Public canonical key
- radar:r-d72bd1c53c92c554a52f8bc23dc2d58c
- Authors
- Dennis Craandijk · Floris Bex · Henry Prakken · Montaigne Centrum voor Rechtsstaat en Rechtspleging · AI and Law Data · Recht innovatie en technologie · Sub Responsible AI · Beshui Liao · Nico Potyka · Leendert van der Torre · Liuwen Yu
- Reported year
- 2026
- Reported language
- en
- Source type
- book
- First detected
- 2026-11-14T02:45:44.318886+00:00
- Last metadata observation
- 2026-11-14T02:45:44.318886+00:00
- Last HTTP verification
- Not checked
Documentary abstract — original language
We propose a neuro-symbolic workflow for explainable text classification. A large language model performs argumentation mining by extracting reusable argumentative cues and organizing them into a weighted bipolar argumentation framework, while argumentative reasoning under a gradual semantics yields an inspectable conclusion. Rather than producing the final prediction directly, the large language model is used to help construct the argumentation framework, which then serves as an interpretable and revisable classifier. We illustrate the approach on fake-job and hate-speech detection and outline an evaluation agenda centered on argument quality, detector grounding, and end-to-end classification behaviour.
Identifiers
- OPENALEX
- https://openalex.org/W7214818735
Documentary context
- Documentary family
- Book
- Source-reported types
- book
Entity mentions are not evidence of legal recognition. Jurisdiction studied is separate from author affiliation country.
Book bibliographic description
- Reported publication date
- 2026-01-01
Access status unknown
Sources
OpenAlex · Record 1
Cite this reference
Dennis Craandijk; Floris Bex; Henry Prakken; Montaigne Centrum voor Rechtsstaat en Rechtspleging; AI and Law Data; Recht innovatie en technologie; Sub Responsible AI; Beshui Liao; Nico Potyka; Leendert van der Torre; Liuwen Yu. LLM-driven argumentation for explainable text classification. 2026. https://www.declarationuniverselledesdroitsdelarbre.org/global-rights-of-nature-radar/reference/r-d72bd1c53c92c554a52f8bc23dc2d58c/
JSON · CSL-JSON · BibTeX · RIS · CSV · JSON-LD ·
APA, Chicago, ISO 690: bibliographic formats using available fields. OSCOLA / Bluebook: structured data only; full legal citation compliance is not claimed without verification of required elements.
- APA
- Dennis Craandijk; Floris Bex; Henry Prakken; Montaigne Centrum voor Rechtsstaat en Rechtspleging; AI and Law Data; Recht innovatie en technologie; Sub Responsible AI; Beshui Liao; Nico Potyka; Leendert van der Torre; Liuwen Yu. (2026). LLM-driven argumentation for explainable text classification. https://www.declarationuniverselledesdroitsdelarbre.org/global-rights-of-nature-radar/reference/r-d72bd1c53c92c554a52f8bc23dc2d58c/
- Chicago
- Dennis Craandijk; Floris Bex; Henry Prakken; Montaigne Centrum voor Rechtsstaat en Rechtspleging; AI and Law Data; Recht innovatie en technologie; Sub Responsible AI; Beshui Liao; Nico Potyka; Leendert van der Torre; Liuwen Yu. LLM-driven argumentation for explainable text classification. 2026. https://www.declarationuniverselledesdroitsdelarbre.org/global-rights-of-nature-radar/reference/r-d72bd1c53c92c554a52f8bc23dc2d58c/
- ISO 690
- Dennis Craandijk; Floris Bex; Henry Prakken; Montaigne Centrum voor Rechtsstaat en Rechtspleging; AI and Law Data; Recht innovatie en technologie; Sub Responsible AI; Beshui Liao; Nico Potyka; Leendert van der Torre; Liuwen Yu. LLM-driven argumentation for explainable text classification. 2026. https://www.declarationuniverselledesdroitsdelarbre.org/global-rights-of-nature-radar/reference/r-d72bd1c53c92c554a52f8bc23dc2d58c/
Warning: Undefined array key "last_link_verified" in /home/clients/e27d81e12f04d2bfd747aa264540ac56/sites/_UDTR_APP/legal_library_reference.php on line 31
UDTR Global Rights of Nature Legal Library. LLM-driven argumentation for explainable text classification. Documentary record: https://www.declarationuniverselledesdroitsdelarbre.org/global-rights-of-nature-radar/reference/r-d72bd1c53c92c554a52f8bc23dc2d58c/ · Last HTTP verification: not performed
Research dossiers and documentary relations
Source roles
Bibliographic / original publication source · https://dspace.library.uu.nl/handle/1874/491433
An authority link alone does not verify a legal claim. Abstracts and full texts remain subject to their source terms.
Documentary status
Relevance pending
Library
This identity is not yet included in the Legal Library.