中文
相关论文

相关论文: Contestable Multi-Agent Debate with Arena-based Ar…

200 篇论文

Large Language Models (LLMs) suffer from hallucinations and factual inaccuracies, especially in complex reasoning and fact verification tasks. Multi-Agent Debate (MAD) systems aim to improve answer accuracy by enabling multiple LLM agents…

计算与语言 · 计算机科学 2026-01-09 Seyeon Jeong , Yeonjun Choi , JongWook Kim , Beakcheol Jang

As an agent-level reasoning and coordination paradigm, Multi-Agent Debate (MAD) orchestrates multiple agents through structured debate to improve answer quality and support complex reasoning. However, existing research on MAD suffers from…

Hallucination continues to pose a major obstacle in the reasoning capabilities of large language models (LLMs). Although the Multi-Agent Debate (MAD) paradigm offers a promising solution by promoting consensus among multiple agents to…

人工智能 · 计算机科学 2025-11-17 Dayong Liang , Xiao-Yong Wei , Changmeng Zheng

Contestable AI requires that AI-driven decisions align with human preferences. While various forms of argumentation have been shown to support contestability, Edge-Weighted Quantitative Bipolar Argumentation Frameworks (EW-QBAFs) have…

人工智能 · 计算机科学 2025-07-16 Xiang Yin , Nico Potyka , Antonio Rago , Timotheus Kampik , Francesca Toni

Quantitative Bipolar Argumentation Frameworks (QBAFs) provide an alternative approach to computing argument acceptability in Bipolar Argumentation Frameworks (BAFs). Each argument is assigned an initial strength, which is then updated to a…

人工智能 · 计算机科学 2026-05-05 Gianvincenzo Alfano , Sergio Greco , Lucio La Cava , Francesco Parisi , Irina Trubitsyna

Large Language Models (LLMs) are increasingly deployed in real-world fact-checking systems, yet existing evaluations focus predominantly on claim verification and overlook the broader fact-checking workflow, including claim extraction and…

计算与语言 · 计算机科学 2026-01-07 Hongzhan Lin , Zixin Chen , Zhiqi Shen , Ziyang Luo , Zhen Ye , Jing Ma , Tat-Seng Chua , Guandong Xu

We introduce AgenticSimLaw, a role-structured, multi-agent debate framework that provides transparent and controllable test-time reasoning for high-stakes tabular decision-making tasks. Unlike black-box approaches, our courtroom-style…

人工智能 · 计算机科学 2026-01-30 Jon Chun , Kathrine Elkins , Yong Suk Lee

Formal argumentation is being used increasingly in artificial intelligence as an effective and understandable way to model potentially conflicting pieces of information, called arguments, and identify so-called acceptable arguments…

人工智能 · 计算机科学 2026-03-09 Yann Munro , Isabelle Bloch , Marie-Jeanne Lesot

Large language models demonstrate remarkable reasoning capabilities but often produce unreliable or incorrect responses. Existing verification methods are typically model-specific or domain-restricted, requiring significant computational…

计算与语言 · 计算机科学 2025-08-22 Jiuzhou Han , Wray Buntine , Ehsan Shareghi

The recent explosion of large language models (LLMs), each with its own general or specialized strengths, makes scalable, reliable benchmarking more urgent than ever. Standard practices nowadays face fundamental trade-offs: closed-ended…

Large language models (LLMs) show remarkable potential to act as computer agents, enhancing human productivity and software accessibility in multi-modal tasks that require planning and reasoning. However, measuring agent performance in…

Multimodal controversy detection (MCD) identifies controversial content in videos and their associated user comments, to support risk management for social video platforms.Prior research frames MCD as a static representation learning task,…

机器学习 · 计算机科学 2026-05-06 Zihan Ding , Ziyuan Yang , Yi Zhang

Writing effective rebuttals is a high-stakes task that demands more than linguistic fluency, as it requires precise alignment between reviewer intent and manuscript details. Current solutions typically treat this as a direct-to-text…

人工智能 · 计算机科学 2026-01-21 Qianli Ma , Chang Guo , Zhiheng Tian , Siyu Wang , Jipeng Xiao , Yuanhao Yue , Zhipeng Zhang

Tabular anomaly detection is often handled by single detectors or static ensembles, even though strong performance on tabular data typically comes from heterogeneous model families (e.g., tree ensembles, deep tabular networks, and tabular…

机器学习 · 计算机科学 2026-02-17 Pinqiao Wang , Sheng Li

Fact-checking health-related claims has become increasingly critical as misinformation proliferates online. Effective verification requires both the retrieval of high-quality evidence and rigorous reasoning processes. In this paper, we…

人工智能 · 计算机科学 2025-12-12 Chih-Han Chen , Chen-Han Tsai , Yu-Shao Peng

Recent progress in multimodal large language models (MLLMs) has demonstrated promising performance on medical benchmarks and in preliminary trials as clinical assistants. Yet, our pilot audit of diagnostic cases uncovers a critical failure…

人工智能 · 计算机科学 2025-09-30 Hongjun Liu , Yinghao Zhu , Yuhui Wang , Yitao Long , Zeyu Lai , Lequan Yu , Chen Zhao

We present M-Reason, a demonstration system for transparent, agent-based reasoning and evidence integration in the biomedical domain, with a focus on cancer research. M-Reason leverages recent advances in large language models (LLMs) and…

人工智能 · 计算机科学 2025-10-08 Oskar Wysocki , Magdalena Wysocka , Mauricio Jacobo , Harriet Unsworth , André Freitas

The advent of large language models (LLMs) has facilitated the development of natural language text generation. It also poses unprecedented challenges, with content hallucination emerging as a significant concern. Existing solutions often…

计算与语言 · 计算机科学 2024-06-06 Xiaoxi Sun , Jinpeng Li , Yan Zhong , Dongyan Zhao , Rui Yan

Humans engage in informal debates on a daily basis. By expressing their opinions and ideas in an argumentative fashion, they are able to gain a deeper understanding of a given problem and in some cases, find the best possible course of…

计算机科学中的逻辑 · 计算机科学 2019-12-13 Ria Jha , Francesco Belardinelli , Francesca Toni

Implicit artistic influence, although visually plausible, is often undocumented and thus poses a historically constrained attribution problem: resemblance is necessary but not sufficient evidence. Most prior systems reduce influence…

人工智能 · 计算机科学 2026-04-10 Hanyi Liu , Zhonghao Jiu , Minghao Wang , Yuhang Xie , Heran Yang