Political debates are often analyzed through Argument Mining (AM) to investigate the key arguments that drive them. However, political arguments are rarely interpretable from argumentative spans alone...
The paper introduces DNE‑ElecDeb, an enriched version of the USElecDeb dataset that annotates Debate Named Entities (DNEs) in both argumentative and non‑argumentative spans, and defines Debate Named Entity Recognition (DNER) as a new task. It proposes Joint Argument and Entity Tagging (JAET), a generative framework that fine‑tunes decoder‑only LLMs to insert inline argument and entity tags into debate turns while preserving the original transcript. JAET achieves significant improvements in joint AM+DNER performance (+27.3% relative F1 in the untyped setting and +41.9% in the typed setting) over sequential pipelines, and these gains generalize to Persuasive Essays (+26.6% and +52.7%).
By Lucio La Cava, Stefano Francesco Monea, Sergio Greco
MMDS-Bench is a new diagnostic benchmark for multimodal dynamic stance classification in social media parent‑reply interactions. It contains 3,482 multimodal instances annotated with a seven‑label stance taxonomy, plus an 800‑instance subset that demands structured reasoning over parent and reply understanding and stance‑relation inference. The benchmark also tags each instance with five challenge factors—multimodal fusion, parent framing, non‑literal expression, interaction reasoning, and label‑boundary ambiguity—and evaluates 12 multimodal large language models using a reference‑grounded LLM‑judge protocol, revealing that current models still struggle with relational inference beyond separate parent and reply comprehension.
By Yuzhe Ding, Kang He, Li Zheng, Shengwu Zheng, Teng Shi, Fei Li, Chong Teng, Donghong Ji
MoPrO‑SD is a stance‑specific prompt optimization framework that breaks prompts into semantic modules and refines them sequentially with LLM feedback. It evaluates three refinement strategies—instruction‑only, instruction with reasoning, and instruction with per‑example reasoning—using class‑conditioned errors to improve stance detection. The authors also release VaccineStance, a new human‑annotated benchmark for vaccine stance detection, and demonstrate that MoPrO‑SD outperforms human‑written base prompts across multiple datasets and open‑weight LLMs.
By Meysam Sabbaghan, Nikesh Gyawali, Arman Zareian Jahromi, Sebastian Loera-Lozano, Doina Caragea, Cornelia Caragea
arXiv:2606. 24976v1 Announce Type: cross Abstract: Foundation-model agents in multi-step, open-ended environments frequently suffer from compounding errors, where early mistakes contaminate long-horizon trajectories.
By Pradyumna Narayana, Sana Ayromlou, Purvi Sehgal
The paper introduces a retrieval‑augmented framework for detecting and classifying fallacies in political debate transcripts. By dynamically retrieving documents guided by argumentative relations of support and attack, the method leverages external knowledge to improve performance. Experiments on the ElecDeb60to20 benchmark show significant gains, raising macro‑F1 to 0.864 for detection and 0.725 for classification compared to non‑retrieval baselines.
By Deborah Dore, Greta Damo, Elena Cabrio, Serena Villata