Related papers: R-Debater: Retrieval-Augmented Debate Generation t…

Large language models face challenges in long-context question answering, where key evidence of a query may be dispersed across millions of tokens. Existing works equip large language models with a memory buffer that is dynamically updated…

Temporal reasoning over long, multi-session dialogues is a critical capability for conversational agents. However, existing works and our pilot study have shown that as dialogue histories grow in length and accumulate noise, current…

Recent advances in pre-trained language models have significantly improved neural response generation. However, existing methods usually view the dialogue context as a linear sequence of tokens and learn to generate the next word through…

Recently, research on open domain dialogue systems have attracted extensive interests of academic and industrial researchers. The goal of an open domain dialogue system is to imitate humans in conversations. Previous works on single turn…

Recently, retrieval-augmented text generation attracted increasing attention of the computational linguistics community. Compared with conventional generation models, retrieval-augmented text generation has remarkable advantages and…

Large Language Models (LLMs) often exhibit factual inconsistencies and logical decay in extended, multi-turn dialogues, a challenge stemming from their reliance on static, pre-trained knowledge and an inability to reason adaptively over the…

Argumentation generation has attracted substantial research interest due to its central role in human reasoning and decision-making. However, most existing argumentative corpora focus on non-interactive, single-turn settings, either…

The conventional Retrieval-Augmented Generation (RAG) paradigm of injecting raw retrieved texts into the Large Language Model (LLM)'s context often results in suboptimal integration of retrieved information. This paper proposes to bridge…

Despite the remarkable performance of large-scale generative models in open-domain conversation, they are known to be less practical for building real-time conversation systems due to high latency. On the other hand, retrieval models could…

Numerical reasoning over hybrid data containing tables and long texts has recently received research attention from the AI community. To generate an executable reasoning program consisting of math and table operations to answer a question,…

Real-world mathematical modeling is inherently an experiential and collaborative endeavor. Domain experts rarely solve complex problems from scratch; instead, they draw upon analogies from historical cases and subject their hypotheses to…

For dialogue response generation, traditional generative models generate responses solely from input queries. Such models rely on insufficient information for generating a specific response since a certain query could be answered in…

Debate has been widely adopted as a strategy to enhance critical thinking skills in English Language Arts (ELA). One important skill in debate is forming effective argumentation, which requires debaters to select supportive evidence from…

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…

Retrieval-Augmented Generation has made significant progress in the field of natural language processing. By combining the advantages of information retrieval and large language models, RAG can generate relevant and contextually appropriate…

Multi-agent debate system (MAD) imitating the process of human discussion in pursuit of truth, aims to align the correct cognition of different agents for the optimal solution. It is challenging to make various agents perform right and…

Multi-persona debate systems powered by large language models (LLMs) show promise in reducing confirmation bias, which can fuel echo chambers and social polarization. However, empirical evidence remains limited on whether they meaningfully…

Identifying the strategic uses of reformulation in discourse remains a key challenge for computational argumentation. While LLMs can detect surface-level similarity, they often fail to capture the pragmatic functions of rephrasing, such as…

While state-of-the-art language models have achieved impressive results, they remain susceptible to inference-time adversarial attacks, such as adversarial prompts generated by red teams arXiv:2209.07858. One approach proposed to improve…

The use of AI in legal analysis and prediction (LegalAI) has gained widespread attention, with past research focusing on retrieval-based methods and fine-tuning large models. However, these approaches often require large datasets and…