Semantic features have been playing a central role in investigating the nature of our conceptual representations. Yet the enormous time and effort required to empirically sample and norm features from human raters has restricted their use to a limited set of manually curated concepts. Given recent promising developments with transformer-based language models, here we asked whether it was possible to use such models to automatically generate meaningful lists of properties for arbitrary object concepts and whether these models would produce features similar to those found in humans. To this end, we probed a GPT-3 model to generate semantic features for 1,854 objects and compared automatically-generated features to existing human feature norms. GPT-3 generated many more features than humans, yet showed a similar distribution in the types of generated features. Generated feature norms rivaled human norms in predicting similarity, relatedness, and category membership, while variance partitioning demonstrated that these predictions were driven by similar variance in humans and GPT-3. Together, these results highlight the potential of large language models to capture important facets of human knowledge and yield a new approach for automatically generating interpretable feature sets, thus drastically expanding the potential use of semantic features in psychological and linguistic studies.
Does Conceptual Representation Require Embodiment? Insights From Large Language Models
Basque Center on Cognition, Brain and Language（巴斯克认知、大脑与语言中心）；The Hong Kong Polytechnic University（香港理工大学）；Princeton Neuroscience Institute, Princeton University（普林斯顿大学普林斯顿神经科学研究所）；Hunter College, City University of New York（纽约城市大学亨特学院）；Graduate Center, City University of New York（纽约城市大学研究生中心）
Large Language Models on Wikipedia-Style Survey Generation: an Evaluation in NLP Concepts
University of Tokyo（东京大学）；Tokyo Institute of Technology（东京工业大学）；MIT（麻省理工学院）；National University of Singapore（新加坡国立大学）；Northwestern University（西北大学）；Bielefeld University（比勒费尔德大学）；University College Dublin（都柏林大学学院）；Moveworks
Math anxiety and associative knowledge structure are entwined in psychology students but not in Large Language Models like GPT-3.5 and GPT-4o
Department of Psychology and Cognitive Science, University of Trento（心理学与认知科学系，特伦托大学）；CogNosco Lab, Department of Psychology and Cognitive Science, University of Trento（CogNosco实验室，心理学与认知科学系，特伦托大学）；Technical University of Munich（慕尼黑技术大学）；Munich Data Science Institute（慕尼黑数据科学研究所）；Centre for Change and Complexity in Learning, University of South Australia（学习变革与复杂性研究中心，澳大利亚南澳大利亚大学）
SICI: A Semantic-Pragmatic Complexity Index Reveals Regime Shifts in LLM Stance Detection
School of Cyber Science and Technology, University of Science and Technology of China（中国科学技术大学网络空间安全学院）；School of Artificial Intelligence, Shenzhen Technology University（深圳技术大学人工智能学院）
An evaluation of GPT models for phenotype concept recognition
Rare Care Centre（罕见病护理中心）；Perth Children's Hospital（珀斯儿童医院）；Telethon Kids Institute（Telethon儿童研究所）；School of Electrical Engineering, Computing and Mathematical Sciences, Curtin University（科廷大学电气工程、计算与数学科学学院）；SingHealth Duke-NUS Institute of Precision Medicine（新加坡保健服务集团杜克-新加坡国立大学精准医学研究所）；Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）；Western Australian Register of Developmental Anomalies（西澳大利亚发育异常登记处）；King Edward Memorial Hospital（爱德华国王纪念医院）；Faculty of Health and Medical Sciences, University of Western Australia（西澳大利亚大学健康与医学科学学院）；University of Colorado Anschutz Medical Campus（科罗拉多大学安舒茨医学校区）；The Jackson Laboratory for Genomic Medicine（杰克逊基因组医学实验室）；Institute for Systems Genomics, University of Connecticut（康涅狄格大学系统基因组学研究所）
An evaluation of LLMs and Google Translate for translation of selected Indian languages via sentiment and semantic analyses
Transitional Artificial Intelligence Research Group, School of Mathematics and Statistics, UNSW Sydney（过渡人工智能研究组，数学与统计学学院，UNSW悉尼）；Department of Civil Engineering, National Institute of Technology, Rourkela, India（土木工程系，印度国家理工学院，拉尔凯拉）；Centre for Artificial Intelligence and Innovation, Pingla Institute, Sydney, Australia（人工智能与创新中心，Pingla研究所，悉尼，澳大利亚）
Evaluating Text Summaries Generated by Large Language Models Using OpenAI's GPT
University of Colorado - Colorado Springs（科罗拉多大学科罗拉多斯普林斯分校）；University of Massachusetts Lowell（马萨诸塞大学洛厄尔分校）；University of Kansas（堪萨斯大学）；DataCrunch Lab, LLC（DataCrunch实验室有限责任公司）；University of Florida（佛罗里达大学）
Columbia University（哥伦比亚大学）；Carnegie Mellon University（卡内基梅隆大学）；Texas A&M University（得克萨斯农工大学）；Xi’an Jiaotong-Liverpool University（西交利物浦大学）；University of Washington（华盛顿大学）
BP-GPT: Auditory Neural Decoding Using fMRI-prompted LLM
State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology, CASIA（中国科学院自动化研究所脑认知与类脑智能技术国家重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；School of Future Technology, University of Chinese Academy of Sciences（中国科学院大学未来技术学院）；State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA（中国科学院自动化研究所多模态人工智能系统国家重点实验室）
Discovering Semantic Subdimensions through Disentangled Conceptual Representations
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS（多模态人工智能系统国家重点实验室，自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；State Key Laboratory of Cognitive Science and Mental Health, Institute of Psychology, CAS（认知科学与心理健康国家重点实验室，心理研究所）；Department of Psychology, University of Chinese Academy of Sciences（中国科学院大学心理学系）；State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University（认知神经科学与学习国家重点实验室，北京师范大学）
Reasoning before Comparison: LLM-Enhanced Semantic Similarity Metrics for Domain Specialized Text Analysis
School of Computing, University of Georgia（佐治亚大学计算学院）；School of Computer Science and Engineering, South China University of Technology（华南理工大学计算机科学与工程学院）；School of Data Science, University of Virginia（弗吉尼亚大学数据科学学院）；University of Georgia College of Pharmacy（佐治亚大学药学院）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）
McGill University（麦吉尔大学）；Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；University College London（伦敦大学学院）；National Research Council Canada（加拿大国家研究委员会）；Facebook（脸书）
Learning Contextualized Semantics from Co-occurring Terms via a Siamese Architecture
University of Manchester（曼彻斯特大学）
在多媒体信息检索和理解中，最大的挑战之一是通过在上下文中正确地建模概念语义来弥合语义鸿沟。词汇表外（OOV）概念的存在加剧了这一困难。为了解决语义差距的问题，我们制定了一个问题，从描述性术语学习语境化语义，并提出了一种新的连体架构，从描述性术语建模的语境化语义。通过模式聚合和概率主题模型，我们的Siamese架构通过无监督学习从共现的描述性术语中捕获上下文化的语义，从而导致术语在上下文中的概念嵌入空间。此外，共现的OOV概念可以很容易地表示在学习的概念嵌入空间。通过可视化展示了概念嵌入空间的主要性质。使用语义启动的各种设置，我们已经进行了一个全面的评估，通过比较我们的方法与一些国家的最先进的方法在六个不同领域的注释语料库，即，音乐领域的MagTag5K、CAL500和Million Song Dataset，以及图像领域的Corel5K、LabelMe和SUNDatabase。语义启动实验结果表明，我们的方法在各个方面都大大优于那些最先进的方法。
