Related papers: Promoting Constructive Deliberation: Reframing for…
How can we model arguments and their dynamics in online forum discussions? The meteoric rise of online forums presents researchers across different disciplines with an unprecedented opportunity: we have access to texts containing discourse…
In online discussion fora, speakers often make arguments for or against something, say birth control, by highlighting certain aspects of the topic. In social science, this is referred to as issue framing. In this paper, we introduce a new…
LLMs can act as an impartial other, drawing on vast knowledge, or as personalized self-reflecting user prompts. These personalized LLMs, or Digital Humans, occupy an intermediate position between self and other. This research explores the…
We present a survey of methods for assessing and enhancing the quality of online discussions, focusing on the potential of LLMs. While online discourses aim, at least in theory, to foster mutual understanding, they often devolve into…
Public discourse around climate change remains polarized despite scientific consensus on anthropogenic climate change (ACC). This study examines how "believers" and "skeptics" of ACC differ in their YouTube comment discourse. We analyzed…
Social networks have a community providing feedback on comments that allows to identify opinion leaders and users whose positions are unwelcome. Other platforms are not backed by such tools. Having a picture of the community's reactions to…
Making LLMs speak for different, especially minority groups of people, and generate statements supporting their diverse or even controversial perspectives is critical to creating an inclusive environment. However, existing LLMs lack…
Current end-to-end neural conversation models inherently lack the flexibility to impose semantic control in the response generation process, often resulting in uninteresting responses. Attempts to boost informativeness alone come at the…
We investigate how to teach large language models (LLMs) to perform scientific reasoning by leveraging expert discussions as a learning signal. Focusing on the genomics domain, we develop an automated pipeline to extract trainable data and…
What kinds of arguments do people make, and what effect do they have on others? Normative constraints on argument-making are as old as philosophy itself, but little is known about the diversity of arguments made in practice. We use NLP…
Generating long, coherent text remains a challenge for large language models (LLMs), as they lack hierarchical planning and structured organization in discourse generation. We introduce Structural Alignment, a novel method that aligns LLMs…
Online discourse is often perceived as polarized and unproductive. While some conversational discourse parsing frameworks are available, they do not naturally lend themselves to the analysis of contentious and polarizing discussions.…
Rebuttal generation is a critical component of the peer review process for scientific papers, enabling authors to clarify misunderstandings, correct factual inaccuracies, and guide reviewers toward a more accurate evaluation. We observe…
Millions of online discussions are generated everyday on social media platforms. Topic modelling is an efficient way of better understanding large text datasets at scale. Conventional topic models have had limited success in online…
Large language models (LLMs) excel at generating empathic responses in text-based conversations. But, how reliably do they judge the nuances of empathic communication? We investigate this question by comparing how experts, crowdworkers, and…
Large Language Models (LLMs) can play a vital role in psychotherapy by adeptly handling the crucial task of cognitive reframing and overcoming challenges such as shame, distrust, therapist skill variability, and resource scarcity. Previous…
LLM-generated drafts often contain subtle factual or logical errors, yet prior work shows that models struggle to reliably integrate multi-turn feedback aimed at fixing them. We propose in-place feedback, an interaction paradigm in which…
Language models (LMs) now excel at many tasks such as few-shot learning, question answering, reasoning, and dialog. However, they sometimes generate unsupported or misleading content. A user cannot easily determine whether their outputs are…
Large language models (LLMs) have been shown to be proficient in correctly answering questions in the context of online discourse. However, the study of using LLMs to model human-like answers to fact-driven social media questions is still…
Large language model alignment is widely used and studied to avoid LLM producing unhelpful and harmful responses. However, the lengthy training process and predefined preference bias hinder adaptation to online diverse human preferences. To…