Manually annotating data for computational social science tasks can be costly, time-consuming, and emotionally draining. While recent work suggests that LLMs can perform such annotation tasks in zero-shot settings, little is known about how prompt design impacts LLMs' compliance and accuracy. We conduct a large-scale multi-prompt experiment to test how model selection (ChatGPT, PaLM2, and Falcon7b) and prompt design features (definition inclusion, output type, explanation, and prompt length) impact the compliance and accuracy of LLM-generated annotations on four CSS tasks (toxicity, sentiment, rumor stance, and news frames). Our results show that LLM compliance and accuracy are highly prompt-dependent. For instance, prompting for numerical scores instead of labels reduces all LLMs' compliance and accuracy. The overall best prompting setup is task-dependent, and minor prompt changes can cause large changes in the distribution of generated labels. By showing that prompt design significantly impacts the quality and distribution of LLM-generated annotations, this work serves as both a warning and practical guide for researchers and practitioners.
School of Computer Science, Fudan University(复旦大学计算机科学学院);Tencent AI Lab(腾讯AI实验室);Institute of Modern Languages and Linguistics, Fudan University(复旦大学现代语言与语言学研究所)
Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users
Cullen College of Engineering(卡伦工程学院);McKelvey School of Engineering(麦凯维工程学院);University of Houston(休斯顿大学);Washington University in St. Louis(圣路易斯华盛顿大学);Arizona State University(亚利桑那州立大学);Indiana University Bloomington(印第安纳大学伯明顿分校)
Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory
MAIS, Institute of Automation, Chinese Academy of Sciences(自动化研究所,中国科学院);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);University of California, Santa Barbara(加州大学圣巴巴拉分校);Beijing Wenge Technology Co., Ltd(北京文格科技有限公司)
Representation Engineering for Large-Language Models: Survey and Research Challenges
Wisent AI;University of Warwick(华威大学);Amazon Web Services(亚马逊网络服务);University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);Perplexity;University of Cambridge(剑桥大学);Mila;University of Technology Sydney(悉尼科技大学)
School of Computer Science and Engineering, Nanyang Technological University(南洋理工大学计算机科学与工程学院);Jisuan Institute of Technology, Beijing JudaoYouda Network Technology Co. Ltd.(智算技术研究所,北京judaoYouda网络技术有限公司)
From Prompts to Propositions: A Logic-Based Lens on Student-LLM Interactions
University of Houston(休斯顿大学);University of California, Irvine(加州大学尔湾分校);Universidad Internacional de la Rioja(里瓦达维亚国际大学);University of Southern California(南加州大学);Abilene Christian University(阿比林基督教大学);University of Auckland(奥克兰大学);Aalto University(阿尔托大学);Carnegie Mellon University(卡内基梅隆大学);Indian Institute of Technology, Kanpur(印度理工学院,坎pur)
Edinburgh Clinical NLP at MEDIQA-CORR 2024: Guiding Large Language Models with Hints
School of Informatics, University of Edinburgh(爱丁堡大学信息学院);Usher Institute, University of Edinburgh(爱丁堡大学厄舍研究所);Edinburgh Futures Institute, University of Edinburgh(爱丁堡未来研究所);School of Literatures, Languages and Cultures, University of Edinburgh(爱丁堡大学文学、语言与文化学院)
Prompt Injection Attacks on Large Language Models in Oncology
Else Kroener Fresenius Center for Digital Health, Technical University Dresden(德累斯顿工业大学Else Kroener Fresenius数字健康中心);University Hospital RWTH Aachen(亚琛工业大学附属医院);National Center for Tumor Diseases (NCT), Heidelberg University Hospital(海德堡大学附属医院国家肿瘤疾病中心);Heidelberg University(海德堡大学);Medical Faculty Mannheim, Heidelberg University(海德堡大学曼海姆医学院);German Cancer Research Center(德国癌症研究中心);University Medical Center Mainz(美因茨大学医学中心);University Hospital Aachen(亚琛大学附属医院);University Hospital Dresden(德累斯顿大学附属医院)