OmouAI is an interactive deliberation system that combines large language models with computational argumentation to facilitate policy debates involving humans and simulated personas such as stakeholders, experts, or devil’s advocates. Each persona generates its own arguments, which are assembled into a shared argumentation framework that users can contest, add to, or revise, ensuring human oversight. The system evaluates arguments using deterministic argumentative semantics against external goals like the UN Sustainable Development Goals, providing faithful explanations and indicating how policy recommendations affect those goals.
By Stylianos Loukas Vasileiou, Antonio Rago, William Yeoh, Georgina Curto
The paper proposes a theory for judging post-hoc debates in AI, focusing on properties like reproducibility, robustness, groundedness, and explainability. It evaluates two debate‑judgement methods—LLM judges and formal computational argumentation semantics—finding similar accuracy but noting that argumentation semantics offers stronger formal guarantees. The study suggests that argumentation semantics is a preferable framework for principled debate judges in AI systems.
By Xiang Yin, Adam Dejl, Antonio Rago, Lihu Chen, Francesca Toni
arXiv:2608.30842v1 Announce Type: new
Abstract: Humans play a vital role at every stage of AI development, from data collection and curation to model development and evaluation. However, humans often...
By Deepak Pandita, Christopher M. Homan
The paper introduces contrastive explanations for Quantitative Bipolar Argumentation Frameworks (QBAFs), a formalism used to represent and reason with information. Unlike traditional explanations that focus on a single argument, contrastive explanations highlight the differences between two topic arguments. The authors propose a general form of contrastive attribution functions (CAFs), present CAFs based on removal, gradients, and Shapley-values, and demonstrate their applicability in healthcare and bias identification contexts.
By Xiang Yin, Nico Potyka, Antonio Rago, Francesca Toni
ABDA-NL is a natural‑language interface for the ABDA argument‑based reasoning system, which uses ASPIC knowledge bases under grounded semantics. It lets users view accepted, rejected, or undecided conclusions, interactively explore the grounded discussion game, and experiment with what‑if scenarios by suspending assumptions, rules, or preferences. A large language model bridges natural language and formalism, answering questions from reference documents and translating plain‑English edits into formal statements, while the deterministic ABDA engine remains the sole source of arguments and acceptance labels, with all model proposals validated by the user before acceptance.
By Shawn Bowers, Martin Caminada, Haoyang Liu, Bertram Lud\"ascher
arXiv:2506. 13609v2 Announce Type: replace Abstract: Training powerful AI systems to exhibit desired behaviors hinges on the ability to provide accurate human supervision on increasingly complex tasks.
By Jonah Brown-Cohen, Geoffrey Irving, Georgios Piliouras, Lijie Chen, Jiawei Li, Zhiyang Xun
arXiv:2608. 05391v1 Announce Type: new Abstract: Care plan coordination demands synthesizing heterogeneous clinical, functional, and psychosocial information across multiple professional disciplines, where monolithic LLM pipelines cannot perform in a transparent or safe manner.
By Truong Thanh Hung Nguyen, Hoang-Loc Cao, Phuc Ho, Phuc Truong Loc Nguyen, Ren\'e Richard, Hung Cao
The paper introduces contrastive explanations for Quantitative Bipolar Argumentation Frameworks (QBAFs), a formalism used to represent and reason with information, including augmenting AI classification tasks with explainability. Unlike traditional explanations that focus on a single argument, contrastive explanations highlight differences between two topic arguments. The authors propose general contrastive attribution functions (CAFs), present CAFs based on removal, gradients, and Shapley-values, analyze their properties, and demonstrate their applicability in healthcare and bias identification scenarios.
The paper introduces a meta‑study that reviews state‑of‑the‑art end‑to‑end argument mining (AM) pipelines. It proposes a triple‑perspective framework—linguistic, computational, and domain—to analyze how these pipelines model, compute, and incorporate domain knowledge into argument structures. The authors also outline a general design for the linguistic and computational aspects, aiming to standardize methodology descriptions and enable clearer comparisons among AM approaches.
By Siddharth Bhargava, Sara Tonelli, Patricia Mart\'in-Rodilla
arXiv:2606. 06646v1 Announce Type: cross Abstract: Formalizing complex reasoning from natural text is one of the central challenges in computational linguistics.
By Jakub B\k{a}ba, Jaros{\l}aw Chudziak
arXiv:2509. 23426v3 Announce Type: replace Abstract: AI scientists are emerging computational systems that serve as collaborative partners in discovery.
By Shanghua Gao, Richard Zhu, Pengwei Sui, Zhenglun Kong, Sufian Aldogom, Yepeng Huang, Ayush Noori, Reza Shamji, Krishna Parvataneni, Theodoros Tsiligkaridis, Marinka Zitnik
The article reviews the emergence of Agentic AI, covering its evolution, theoretical foundations, working principles, and architectural aspects. It surveys recent scholarly contributions across various domains, highlighting real‑world applications, current research findings, and existing challenges. The review also proposes a framework for stakeholder adoption and outlines future research directions to guide researchers and practitioners.
By AKM Bahalul Haque, Al Amin Islam Ridoy, Mohammad Rayhan, Ivan Porres