Related papers: UniPoll: A Unified Social Media Poll Generation Fr…

In AI-facilitated teaching, leveraging various query styles to interpret abstract educational content is crucial for delivering effective and accessible learning experiences. However, existing retrieval systems predominantly focus on…

Social media platforms are daily exhibiting millions of events. To preliminarily predict the mainstream public reaction to these events, we study trendy response prediction to automatically generate top-liked user replies to social media…

Unified multimodal models often struggle with complex synthesis tasks that demand deep reasoning, and typically treat text-to-image generation and image editing as isolated capabilities rather than interconnected reasoning steps. To address…

While Unified Multimodal Models (UMMs) have achieved remarkable success in cross-modal comprehension, a significant gap persists in their ability to leverage such internal knowledge for high-quality generation. We formalize this discrepancy…

Accurate clinical prognosis requires synthesizing structured Electronic Health Records (EHRs) with real-time physiological signals like the Electrocardiogram (ECG). Large Language Models (LLMs) offer a powerful reasoning engine for this…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating up-to-date external knowledge, yet real-world web environments present unique challenges. These limitations manifest as two key challenges: pervasive…

Even when aggregate accuracy is high, state-of-the-art NLP models often fail systematically on specific subgroups of data, resulting in unfair outcomes and eroding user trust. Additional data collection may not help in addressing these…

The task of visual dialog requires a multimodal chatbot to answer sequential questions from humans about image content. Prior work performs the standard likelihood training for answer generation on the positive instances (involving correct…

We present and evaluate a new model for Natural Language Generation (NLG) in Spoken Dialogue Systems, based on statistical planning, given noisy feedback from the current generation context (e.g. a user and a surface realiser). We study its…

Moral reasoning is a complex cognitive process shaped by individual experiences and cultural contexts and presents unique challenges for computational analysis. While natural language processing (NLP) offers promising tools for studying…

We seek to democratise public-opinion research by providing practitioners with a general methodology to make representative inference from cheap, high-frequency, highly unrepresentative samples. We focus specifically on samples which are…

This paper introduces SCRAG, a prediction framework inspired by social computing, designed to forecast community responses to real or hypothetical social media posts. SCRAG can be used by public relations specialists (e.g., to craft…

Large Language Models (LLMs) are increasingly used as scalable tools for pilot testing, predicting public opinion distributions before deploying costly surveys. To serve as effective pilot testing tools, the performance of these LLMs is…

Although Multimodal Large Language Models (MLLMs) have been widely applied across domains, they are still facing challenges in domain-specific tasks, such as User Interface (UI) understanding accuracy and UI generation quality. In this…

The experimental landscape in natural language processing for social media is too fragmented. Each year, new shared tasks and datasets are proposed, ranging from classics like sentiment analysis to irony detection or emoji prediction.…

Retrieval-Augmented Generation (RAG) significantly enhances the performance of large language models (LLMs) in downstream tasks by integrating external knowledge. To facilitate researchers in deploying RAG systems, various RAG toolkits have…

The emergence of synthetic data represents a pivotal shift in modern machine learning, offering a solution to satisfy the need for large volumes of data in domains where real data is scarce, highly private, or difficult to obtain. We…

Talking face generation has been extensively investigated owing to its wide applicability. The two primary frameworks used for talking face generation comprise a text-driven framework, which generates synchronized speech and talking faces…

This project explores the application of Natural Language Processing (NLP) techniques to analyse United Nations General Assembly (UNGA) speeches. Using NLP allows for the efficient processing and analysis of large volumes of textual data,…

This paper introduces Unilogit, a novel self-distillation method for machine unlearning in Large Language Models. Unilogit addresses the challenge of selectively forgetting specific information while maintaining overall model utility, a…