中文
相关论文

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

200 篇论文

Effective clinical history taking is a foundational yet underexplored component of clinical reasoning. While large language models (LLMs) have shown promise on static benchmarks, they often fall short in dynamic, multi-turn diagnostic…

计算与语言 · 计算机科学 2026-01-30 Yang Zhou , Zhenting Sheng , Mingrui Tan , Yuting Song , Jun Zhou , Yu Heng Kwan , Lian Leng Low , Yang Bai , Yong Liu

Typically crowdsourcing-based approaches to gather annotated data use inter-annotator agreement as a measure of quality. However, in many domains, there is ambiguity in the data, as well as a multitude of perspectives of the information…

人机交互 · 计算机科学 2018-08-21 Anca Dumitrache , Oana Inel , Lora Aroyo , Benjamin Timmermans , Chris Welty

Data annotation underpins the success of modern AI, but the aggregation of crowd-collected datasets can harm the preservation of diverse perspectives in data. Difficult and ambiguous tasks cannot easily be collapsed into unitary labels.…

人机交互 · 计算机科学 2025-08-14 Malik Khadar , Daniel Runningen , Julia Tang , Stevie Chancellor , Harmanpreet Kaur

Community-based moderation offers a scalable alternative to centralized fact-checking, yet it faces significant structural challenges, and existing AI-based methods fail in "cold start" scenarios. To tackle these challenges, we introduce…

计算与语言 · 计算机科学 2026-02-10 Sahajpreet Singh , Kokil Jaidka , Min-Yen Kan

Misinformation about critical issues such as climate change and vaccine safety is oftentimes amplified on online social and search platforms. The crowdsourcing of content credibility assessment by laypeople has been proposed as one strategy…

人机交互 · 计算机科学 2020-08-24 Md Momen Bhuiyan , Amy X. Zhang , Connie Moon Sehat , Tanushree Mitra

Recent advances in artificial intelligence (AI) have made timely, scalable, and effective fact-checking increasingly feasible. One such deployment is X's Community Notes, which provides the AI Note Writer API to enable end-to-end automated…

计算机与社会 · 计算机科学 2026-05-19 Yilin Gong , Siqi Wu

"Citizen queries" are questions asked by an individual about government policies, guidance, and services that are relevant to their circumstances, encompassing a range of topics including benefits, taxes, immigration, employment, public…

计算机与社会 · 计算机科学 2026-02-05 Neil Majithia , Rajat Shinde , Zo Chapman , Prajun Trital , Jordan Decker , Manil Maskey , Elena Simperl , Nigel Shadbolt

Benchmarks have been essential for driving progress in machine learning. A better understanding of LLM capabilities on real world tasks is vital for safe development. Designing adequate LLM benchmarks is challenging: Data from real-world…

Misinformation is an ever increasing problem that is difficult to solve for the research community and has a negative impact on the society at large. Very recently, the problem has been addressed with a crowdsourcing-based approach to scale…

Community Notes (CNs) of X enables users to collaboratively moderate misleading content. To resolve conflicting moderation, CNs infers a latent ideological dimension and selects notes garnering cross-partisan support. As this system is now…

社会与信息网络 · 计算机科学 2026-03-12 Paul Bouchaud , Pedro Ramaciotti

The process of gathering ground truth data through human annotation is a major bottleneck in the use of information extraction methods for populating the Semantic Web. Crowdsourcing-based approaches are gaining popularity in the attempt to…

人机交互 · 计算机科学 2022-09-21 Anca Dumitrache , Oana Inel , Benjamin Timmermans , Carlos Ortiz , Robert-Jan Sips , Lora Aroyo , Chris Welty

NLP benchmarks rely on standardized datasets for training and evaluating models and are crucial for advancing the field. Traditionally, expert annotations ensure high-quality labels; however, the cost of expert annotation does not scale…

计算与语言 · 计算机科学 2025-09-15 Omer Nahum , Nitay Calderon , Orgad Keller , Idan Szpektor , Roi Reichart

Detecting logical fallacies in texts can help users spot argument flaws, but automating this detection is not easy. Manually annotating fallacies in large-scale, real-world text data to create datasets for developing and validating…

计算与语言 · 计算机科学 2024-10-07 Min-Hsuan Yeh , Ruyuan Wan , Ting-Hao 'Kenneth' Huang

As social media becomes increasingly popular, more and more public health activities emerge, which is worth noting for pandemic monitoring and government decision-making. Current techniques for public health analysis involve popular models…

计算与语言 · 计算机科学 2023-09-13 Yan Jiang , Ruihong Qiu , Yi Zhang , Peng-Fei Zhang

The quality of the dataset is crucial for ensuring optimal performance and reliability of downstream task models. However, datasets often contain noisy data inadvertently included during the construction process. Numerous attempts have been…

计算与语言 · 计算机科学 2024-09-25 Juhwan Choi , Jungmin Yun , Kyohoon Jin , YoungBin Kim

Cognitive computing systems require human labeled data for evaluation, and often for training. The standard practice used in gathering this data minimizes disagreement between annotators, and we have found this results in data that fails to…

计算与语言 · 计算机科学 2018-09-27 Anca Dumitrache , Lora Aroyo , Chris Welty

OpenNotes enables patients to access EHR notes, but medical jargon can hinder comprehension. To improve understanding, we evaluated closed- and open-source LLMs for extracting and prioritizing key medical terms using prompting, fine-tuning,…

计算与语言 · 计算机科学 2026-05-08 Won Seok Jang , Sharmin Sultana , Zonghai Yao , Hieu Tran , Zhichao Yang , Sunjae Kwon , Hong Yu

Following an interaction with a patient, physicians are responsible for the submission of clinical documentation, often organized as a SOAP note. A clinical note is not simply a summary of the conversation but requires the use of…

计算与语言 · 计算机科学 2024-04-10 Nathan Brake , Thomas Schaaf

Iterative RAG for multi-hop question answering faces challenges with lengthy contexts and the buildup of irrelevant information. This hinders a model's capacity to process and reason over retrieved content and limits performance. While…

Whether Large Language Models (LLMs) can outperform crowdsourcing on the data annotation task is attracting interest recently. Some works verified this issue with the average performance of individual crowd workers and LLM workers on some…

计算与语言 · 计算机科学 2024-01-19 Jiyi Li