If large language models like GPT-3 preferably produce a particular point of view, they may influence people's opinions on an unknown scale. This study investigates whether a language-model-powered writing assistant that generates some opinions more often than others impacts what users write - and what they think. In an online experiment, we asked participants (N=1,506) to write a post discussing whether social media is good for society. Treatment group participants used a language-model-powered writing assistant configured to argue that social media is good or bad for society. Participants then completed a social media attitude survey, and independent judges (N=500) evaluated the opinions expressed in their writing. Using the opinionated language model affected the opinions expressed in participants' writing and shifted their opinions in the subsequent attitude survey. We discuss the wider implications of our results and argue that the opinions built into AI language technologies need to be monitored and engineered more carefully.
Measuring Human Involvement in AI-Generated Text: A Case Study on Academic Writing
Dept. of Information & Communication Engineering (ICE), The University of Tokyo (Japan)（信息与通信工程系（ICE），东京大学（日本））；National Institute of Informatics (Japan)（日本信息处理学会）
Neural language models have the potential to support human writing. However, questions remain on their integration and influence on writing and output. To address this, we designed and compared two user interfaces for writing with AI on mobile devices, which manipulate levels of initiative and control: 1) Writing with continuously generated text, the AI adds text word-by-word and user steers. 2) Writing with suggestions, the AI suggests phrases and user selects from a list. In a supervised online study (N=18), participants used these prototypes and a baseline without AI. We collected touch int…
In this paper, we present strong baselines for the task of Feedback Comment Generation for Writing Learning. Given a sentence and an error span, the task is to generate a feedback comment explaining the error. Sentences and feedback comments are both in English. We experiment with LLMs and also create multiple pseudo datasets for the task, investigating how it affects the performance of our system. We present our results for the task along with extensive analysis of the generated comments with the aim of aiding future studies in feedback comment generation for English language learners.
Two Modes of Reflection: How Temporal, Spatial, and Social Distances Affect Reflective Writing in Family Caregiving
The University of Tokyo（东京大学）；Ochanomizu University（御茶水女子大学）；Centre for Applied Computing, University of Oulu（奥卢大学应用计算中心）；Social Informatics, Kyoto University（京都大学社会信息学）
Mind the Gap: Conformative Decoding to Improve Output Diversity of Instruction-Tuned Large Language Models
School of Computing University of Kent（肯特大学计算机学院）；Leiden Institute of Advanced Computer Science Universiteit Leiden（莱顿先进计算机科学研究所）；Cheriton School of Computer Science University of Waterloo（滑铁卢大学查里顿计算机科学学院）
G2: Guided Generation for Enhanced Output Diversity in LLMs
Southern University of Science and Technology（南方科技大学）；Tsinghua University（清华大学）；Shanghai University of Finance and Economics（上海财经大学）；Alibaba International Digital Commerce（阿里巴巴国际数字商业）
Pennsylvania State University（宾夕法尼亚州立大学）；GumGum Inc.（GumGum 公司）；Intel Corporation（英特尔公司）
Creative writing is hard: Novelists struggle with writer's block daily. While automatic story generation has advanced recently, it is treated as a "toy task" for advancing artificial intelligence rather than helping people. In this paper, we create a system that produces a short description that narrates a predicted plot using existing story generation approaches. Our goal is to assist writers in crafting a consistent and compelling story arc. We conducted experiments on Amazon Mechanical Turk (AMT) to examine the quality of the generated story plots in terms of consistency and storiability. T…
FIERO: Empowering Creative Writing Through Collaborative Game Play
City University of Hong Kong（香港城市大学）；University of York（约克大学）；University of Canterbury（坎特伯雷大学）；Press Start Academy；City University of Hong Kong Studio for Narrative Spaces（香港城市大学叙事空间工作室）
Handwriting Anomalies and Learning Disabilities through Recurrent Neural Networks and Geometric Pattern Analysis
Karolinska Institutet（卡罗林斯卡学院）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Zambia University（赞比亚大学）；IntelliSolutions；HEDNO SA；Democritus University of Thrace（色雷斯德谟克利特大学）；Mayo Clinic（梅奥诊所）；Auburn University（奥本大学）；Harrison College of Pharmacy（哈里森药学院）
