Related papers: Conch: Competitive Debate Analysis via Visualizing…

Reasoning in interactive problem solving scenarios requires models to construct reasoning threads that reflect user understanding and align with structured domain knowledge. However, current reasoning models often lack explicit semantic…

Scalable oversight protocols aim to enable humans to accurately supervise superhuman AI. In this paper we study debate, where two AI's compete to convince a judge; consultancy, where a single AI tries to convince a judge that asks…

Automatic assessment of the quality of arguments has been recognized as a challenging task with significant implications for misinformation and targeted speech. While real-world arguments are tightly anchored in context, existing…

Large language models (LLMs), such as ChatGPT, have demonstrated outstanding performance in various fields, particularly in natural language understanding and generation tasks. In complex application scenarios, users tend to engage in…

Systematic reviews provide comprehensive syntheses of research fields. As a result, systematic reviews often emphasize synthesizing across the large bodies of literature rather than just describing the studies from which the conclusions…

With the rise of social media platforms, especially X.com (formerly Twitter), there is a growing interest in understanding digital social networks and human digital interactions. This paper presents a comprehensive methodology for…

Concurrent computations resemble conversations. In a conversation, participants direct utterances at others and, as the conversation evolves, exploit the known common context to advance the conversation. Similarly, collaborating software…

A vexing problem in artificial intelligence is reasoning about events that occur in complex, changing visual stimuli such as in video analysis or game play. Inspired by a rich tradition of visual reasoning and memory in cognitive psychology…

Large language models (LLMs) excel at solving problems with clear and complete statements, but often struggle with nuanced environments or interactive tasks which are common in most real-world scenarios. This highlights the critical need…

Recently, advancements in AI counseling based on large language models have shown significant progress. However, existing studies employ a one-time generation approach to synthesize multi-turn dialogue samples, resulting in low therapy…

Vision-language models (VLMs) have achieved impressive performance across a wide range of multimodal reasoning tasks, but they often struggle to disentangle fine-grained visual attributes and reason about underlying causal relationships.…

Current conversational passage retrieval systems cast conversational search into ad-hoc search by using an intermediate query resolution step that places the user's question in context of the conversation. While the proposed methods have…

Due to the proliferation of short-form content and the rapid adoption of AI, opportunities for deep, reflective thinking have significantly diminished, undermining users' critical thinking and reducing engagement with the reasoning behind…

In this study, we tackle the challenge of inadequate and costly training data that has hindered the development of conversational question answering (ConvQA) systems. Enterprises have a large corpus of diverse internal documents. Instead of…

A pressing issue in the adoption of AI models is the increasing demand for more human-centric explanations of their predictions. To advance towards more human-centric explanations, understanding how humans produce and select explanations…

Fencing is a sport that relies heavily on the use of tactics. However, most existing methods for analyzing fencing data are based on statistical models in which hidden patterns are difficult to discover. Unlike sequential games, such as…

Crowd simulation is a central topic in several fields including graphics. To achieve high-fidelity simulations, data has been increasingly relied upon for analysis and simulation guidance. However, the information in real-world data is…

Automatically generating debates is a challenging task that requires an understanding of arguments and how to negate or support them. In this work we define debate trees and paths for generating debates while enforcing a high level…

This work tackles the problem of unsupervised modeling and extraction of the main contrastive sentential reasons conveyed by divergent viewpoints on polarized issues. It proposes a pipeline approach centered around the detection and…

Analyzing ideological discourse even in the age of LLMs remains a challenge, as these models often struggle to capture the key elements that shape real-world narratives. Specifically, LLMs fail to focus on characteristic elements driving…