Tag
This paper argues for layered verification of LLM-generated argument graphs, combining deterministic checks, solvers, and LLM reviewers, and shows that LLM reviewers detect structural defects well but are inconsistent, over-reject correct graphs, and slower than exact checks.
This paper introduces a sentence-level benchmark for classifying interpretive canons in legal documents, evaluating LLMs on a dataset from the German Federal Constitutional Court.
This paper introduces an expert-annotated dataset of 42 U.S. federal tax opinions for legal argument mining, featuring functional labels and tree-structured arguments, and demonstrates classification and retrieval experiments.
This paper introduces a joint argument and entity detection method for political debates, using a generative framework with decoder-only LLMs to improve performance over sequential pipelines.
This paper describes LLM-INSTRUCT, the winning system for the UZH Shared Task at ArgMining 2026 on paragraph-level argument mining. The system uses constraint-aware retrieval and selective debate to improve accuracy and schema compliance.
Introduces MIRA-Ev, a clinical argument mining benchmark built on Spanish MIR licensing-exam cases, annotated with span-level premises, claims, and support/attack relations, available in Spanish, English, and Basque. It provides a three-tier task hierarchy for evaluating evidence sentence retrieval, argumentative component extraction, and relation classification, addressing the limitations of multiple-choice QA benchmarks in clinical NLP.
CAF-Gen is a multi-agent LLM-driven framework that enriches shallow argument structures into formal Carneades Argumentation Framework models using an iterative Creator-Reviewer pipeline, achieving improved structural alignment and quality.
This paper presents a fully automated pipeline that transforms court decisions into legal commentaries by extracting, clustering, and summarizing paragraph-level chunks using LLMs, evaluated on German civil code cases.
This paper introduces TIDE, a novel framework that integrates trial and debate mechanisms to improve criteria-based prompt optimization for argumentative essay understanding tasks such as automated essay scoring, argument component detection, and argument relation identification. Experiments show performance improvements, highlighting the potential of combining prompt-based methods for robust argument analysis.
Researchers from the University of British Columbia propose an unsupervised graph-based system for organizing arguments from online debates by constructing interaction graphs and applying community detection to reveal diverse viewpoint distributions. The approach requires no training data and aims to help users navigate complex argumentative landscapes and combat filter bubbles.