相关论文: Beyond the Crowd: LLM-Augmented Community Notes fo…

The unstructured nature of clinical notes within electronic health records often conceals vital patient-related information, making it challenging to access or interpret. To uncover this hidden information, specialized Natural Language…

In Twitter, and other microblogging services, the generation of new content by the crowd is often biased towards immediacy: what is happening now. Prompted by the propagation of commentary and information through multiple mediums, users on…

In the past decade, tracking health trends using social media data has shown great promise, due to a powerful combination of massive adoption of social media around the world, and increasingly potent hardware and software that enables us to…

As social media becomes increasingly popular, more and more activities related to public health emerge. Current techniques for public health analysis involve popular models such as BERT and large language models (LLMs). However, the costs…

The spread of online misinformation poses serious threats to democratic societies. Traditionally, expert fact-checkers verify the truthfulness of information through investigative processes. However, the volume and immediacy of online…

The spread of misinformation on social media platforms threatens democratic processes, contributes to massive economic losses, and endangers public health. Many efforts to address misinformation focus on a knowledge deficit model and…

Online misinformation poses a global risk with significant real-world consequences. To combat misinformation, current research relies on professionals like journalists and fact-checkers for annotating and debunking misinformation, and…

High-quality annotated data is a cornerstone of modern Natural Language Processing (NLP). While recent methods begin to leverage diverse annotation sources-including Large Language Models (LLMs), Small Language Models (SLMs), and human…

Warning users about misinformation on social media is not a simple usability task. Soft moderation has to balance between debunking falsehoods and avoiding moderation bias while preserving the social media consumption flow. Platforms thus…

In the rapidly evolving landscape of Natural Language Processing (NLP), the use of Large Language Models (LLMs) for automated text annotation in social media posts has garnered significant interest. Despite the impressive innovations in…

Electronic Health Records (EHRs) often lack explicit links between medications and diagnoses, making clinical decision-making and research more difficult. Even when links exist, diagnosis lists may be incomplete, especially during early…

Many online platforms incorporate engagement signals, such as likes, into their interface design to boost engagement. However, these signals can unintentionally elevate content that may not support normatively desirable behavior, especially…

Crowdsourcing is a relatively economic and efficient solution to collect annotations from the crowd through online platforms. Answers collected from workers with different expertise may be noisy and unreliable, and the quality of annotated…

Large Language Models (LLMs) increasingly rely on Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) to align model responses with human preferences. While RLHF employs a reinforcement learning approach with…

This study presents the first large-scale comparison of persuasion techniques present in crowd- versus professionally-written debunks. Using extensive datasets from Community Notes (CNs), EUvsDisinfo, and the Database of Known Fakes (DBKF),…

Crowd-sourcing is a cheap and popular means of creating training and evaluation datasets for machine learning, however it poses the problem of `truth inference', as individual workers cannot be wholly trusted to provide reliable…

Large Language Models (LLMs) have demonstrated immense potential in artificial intelligence across various domains, including healthcare. However, their efficacy is hindered by the need for high-quality labeled data, which is often…

Displaying community fact-checks is a promising approach to reduce engagement with misinformation on social media. However, how users respond to misleading content emotionally after community fact-checks are displayed on posts is unclear.…

This paper assesses the accuracy, reliability and bias of the Large Language Model (LLM) ChatGPT-4 on the text analysis task of classifying the political affiliation of a Twitter poster based on the content of a tweet. The LLM is compared…

Retrieval-Augmented Generation (RAG) mitigates factual errors and hallucinations in Large Language Models (LLMs) for question-answering (QA) by incorporating external knowledge. However, existing adaptive RAG methods rely on LLMs to predict…