{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T09:39:52Z","timestamp":1783589992219,"version":"3.55.0"},"reference-count":55,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T00:00:00Z","timestamp":1767052800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T00:00:00Z","timestamp":1767052800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Topics in Cognitive Science"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Semantic feature norms have been foundational in the study of human conceptual knowledge, yet traditional methods face trade\u2010offs between concept\/feature coverage and verifiability of quality due to the labor\u2010intensive nature of norming studies. Here, we introduce a novel approach that augments a dataset of human\u2010generated feature norms with responses from large language models (LLMs) while verifying the quality of norms against reliable human judgments. We find that our AI\u2010enhanced feature norm dataset,\n                    <jats:styled-content>NOVA<\/jats:styled-content>\n                    :\n                    <jats:bold>N<\/jats:bold>\n                    orms\n                    <jats:bold>O<\/jats:bold>\n                    ptimized\n                    <jats:bold>V<\/jats:bold>\n                    ia\n                    <jats:bold>A<\/jats:bold>\n                    I, shows much higher feature density and overlap among concepts while outperforming a comparable human\u2010only norm dataset and word\u2010embedding models in predicting people's semantic similarity judgments. Taken together, we demonstrate that human conceptual knowledge is richer than captured in previous norm datasets and show that, with proper validation, LLMs can serve as powerful tools for cognitive science research.\n                  <\/jats:p>","DOI":"10.1111\/tops.70037","type":"journal-article","created":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T08:30:06Z","timestamp":1767083406000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["AI\u2010Enhanced Semantic Feature Norms for 786 Concepts"],"prefix":"10.1111","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9876-8742","authenticated-orcid":false,"given":"Siddharth","family":"Suresh","sequence":"first","affiliation":[{"name":"Department of Psychology University of Wisconsin\u2013Madison"},{"name":"Department of Computer Sciences University of Wisconsin\u2013Madison"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kushin","family":"Mukherjee","sequence":"additional","affiliation":[{"name":"Department of Psychology Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tyler","family":"Giallanza","sequence":"additional","affiliation":[{"name":"Department of Psychology Princeton University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xizheng","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer Science Brown University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mia","family":"Patil","sequence":"additional","affiliation":[{"name":"Department of Computer Sciences University of Wisconsin\u2013Madison"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan D.","family":"Cohen","sequence":"additional","affiliation":[{"name":"Department of Psychology Princeton University"},{"name":"Princeton Neuroscience Institute Princeton University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timothy T.","family":"Rogers","sequence":"additional","affiliation":[{"name":"Department of Psychology University of Wisconsin\u2013Madison"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,12,30]]},"reference":[{"key":"e_1_2_8_2_1","unstructured":"Abdin M. Aneja J. Behl H. Bubeck S. Eldan R. Gunasekar S. Harrison M. Hewett R. J. Javaheripi M. Kauffmann P. et\u00a0al. (2024).Phi\u20104 technical report.arXiv preprint arXiv:2412.08905."},{"key":"e_1_2_8_3_1","unstructured":"Achiam J. Adler S. Agarwal S. Ahmad L. Akkaya I. Aleman F. L. Almeida D. Altenschmidt J. Altman S. Anadkat S. et\u00a0al. (2023).GPT\u20104 technical report.arXiv preprint arXiv:2303.08774."},{"key":"e_1_2_8_4_1","volume-title":"International Conference on Machine Learning","author":"Aher G. V.","year":"2023"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.3758\/BF03197450"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2218523120"},{"key":"e_1_2_8_7_1","first-page":"1877","article-title":"Language models are few\u2010shot learners","volume":"33","author":"Brown T.","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_8_8_1","unstructured":"Bubeck S. Chandrasekaran V. Eldan R. Gehrke J. Horvitz E. Kamar E. Lee P. Lee Y. T. Li Y. Lundberg S. et\u00a0al. (2023).Sparks of artificial general intelligence: Early experiments with GPT\u20104.arXiv preprint arXiv:2303.12712."},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-019-01243-z"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.2828-13.2014"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.82.6.407"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.0904-20.2020"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1162\/imag_a_00093"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1037\/0096-3445.132.2.163"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.3758\/BRM.40.4.1030"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-014-0458-y"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-013-0420-4"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1080\/02643290701723948"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2023.04.008"},{"key":"e_1_2_8_20_1","unstructured":"Dubey A. Jauhri A. Pandey A. Kadian A. Al\u2010Dahle A. Letman A. Mathur A. Schelten A. Yang A. Fan A. et\u00a0al. (2024).The Llama 3 herd of models.arXiv preprint arXiv:2407.21783."},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1037\/0096-3445.120.4.339"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2108091119"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2022.12.006"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1162\/089892901753165818"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1037\/rev0000485"},{"key":"e_1_2_8_26_1","unstructured":"Hansen H. &Hebart M. N.(2022).Semantic features of object concepts generated with GPT\u20103.arXiv preprint arXiv:2202.03753."},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.82580"},{"key":"e_1_2_8_28_1","unstructured":"Hendrycks D. Burns C. Basart S. Zou A. Mazeika M. Song D. &Steinhardt J.(2020).Measuring massive multitask language understanding.arXiv preprint arXiv:2009.03300."},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"e_1_2_8_30_1","volume-title":"NIPS","author":"Jamieson K. G.","year":"2015"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.3758\/s13423-020-01792-x"},{"key":"e_1_2_8_32_1","unstructured":"Marjieh R. Sucholutsky I. Sumers T. R. Jacoby N. &Griffiths T. L.(2022).Predicting human similarity judgments using large language models.arXiv preprint arXiv:2202.04728."},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.3758\/BF03192726"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2011417118"},{"key":"e_1_2_8_35_1","unstructured":"Mikolov T. Sutskever I. Chen K. Corrado G. S. &Dean J.(2013).Distributed representations of words and phrases and their compositionality.Advances in Neural Information Processing Systems 3111\u20133119."},{"key":"e_1_2_8_36_1","unstructured":"Mukherjee K. Rogers T. T. &Schloss K. B.(2024).Large language models estimate fine\u2010grained human color\u2010concept associations.arXiv preprint arXiv:2406.17781."},{"key":"e_1_2_8_37_1","unstructured":"Mukherjee K. Suresh S. &Rogers T. T.(2023).Human\u2013machine cooperation for semantic feature listing.arXiv preprint arXiv:2304.05012."},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2006.07.005"},{"key":"e_1_2_8_39_1","unstructured":"OLMo T. Walsh P. Soldaini L. Groeneveld D. Lo K. Arora S. Bhagia A. Gu Y. Huang S. Jordan M. et\u00a0al. (2024).2 Olmo 2 Furious.arXiv preprint arXiv:2501.00656."},{"key":"e_1_2_8_40_1","volume-title":"International Conference on Machine Learning","author":"Oswal U.","year":"2016"},{"key":"e_1_2_8_41_1","doi-asserted-by":"publisher","DOI":"10.1162\/jocn.2007.19.11.1735"},{"key":"e_1_2_8_42_1","doi-asserted-by":"crossref","unstructured":"Pennington J. Socher R. &Manning C. D.(2014).Glove: Global vectors for word representation. InProceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 1532\u20131543).","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_2_8_43_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-03068-4"},{"key":"e_1_2_8_44_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1756-8765.2010.01111.x"},{"key":"e_1_2_8_45_1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/6161.001.0001"},{"key":"e_1_2_8_46_1","doi-asserted-by":"publisher","DOI":"10.1037\/0096-3445.104.3.192"},{"key":"e_1_2_8_47_1","doi-asserted-by":"publisher","DOI":"10.3758\/BF03195597"},{"key":"e_1_2_8_48_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1820226116"},{"key":"e_1_2_8_49_1","doi-asserted-by":"crossref","unstructured":"Sievert S. Nowak R. &Rogers T. T.(2023).Efficiently learning relative similarity embeddings with crowdsourcing.Journal of Open Source Software 8(84).","DOI":"10.21105\/joss.04517"},{"key":"e_1_2_8_50_1","unstructured":"Suresh S. Huang W.\u2010C. Mukherjee K. &Rogers T. T.(2024).Categories vs semantic features: What shape the similarities people discern in photographs of objects? InICLR 2024 Workshop on Representational Alignment."},{"key":"e_1_2_8_51_1","unstructured":"Suresh S. Mukherjee K. &Rogers T. T.(2023).Semantic feature verification in Flan\u2010T5.arXiv preprint arXiv:2304.05591."},{"key":"e_1_2_8_52_1","doi-asserted-by":"crossref","unstructured":"Suresh S. Mukherjee K. Yu X. Huang W.\u2010C. Padua L. &Rogers T.(2023).Conceptual structure coheres in human cognition but not in large language models. InProceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (pp. 722\u2013738).","DOI":"10.18653\/v1\/2023.emnlp-main.47"},{"key":"e_1_2_8_53_1","unstructured":"Team G. Riviere M. Pathak S. Sessa P. G. Hardin C. Bhupatiraju S. Hussenot L. Mesnard T. Shahriari B. Ram\u00e9 A. et\u00a0al. (2024).Gemma 2: Improving open language models at a practical size.arXiv preprint arXiv:2408.00118."},{"key":"e_1_2_8_54_1","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-024-02337-z"},{"key":"e_1_2_8_55_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-023-01659-w"},{"key":"e_1_2_8_56_1","unstructured":"Wei J. Bosma M. Zhao V. Y. Guu K. Yu A. W. Lester B. Du N. Dai A. M. &Le Q. V.(2021).Finetuned language models are zero\u2010shot learners.arXiv preprint arXiv:2109.01652."}],"container-title":["Topics in Cognitive Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/tops.70037","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/tops.70037","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/tops.70037","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T17:46:46Z","timestamp":1776880006000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/tops.70037"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,30]]},"references-count":55,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["10.1111\/tops.70037"],"URL":"https:\/\/doi.org\/10.1111\/tops.70037","archive":["Portico"],"relation":{},"ISSN":["1756-8757","1756-8765"],"issn-type":[{"value":"1756-8757","type":"print"},{"value":"1756-8765","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,30]]},"assertion":[{"value":"2025-10-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-20","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70037"}}