AI hallucinations can’t be stopped — but these techniques can limit their damage. Jones, N. Nature, 637(8047):778–780, January, 2025. Bandiera_abtest: a Cg_type: News Feature Publisher: Nature Publishing Group Subject_term: Machine learning, Computer science, Technology
Paper doi abstract bibtex Developers have tricks to stop artificial intelligence from making things up, but large language models are still struggling to tell the truth, the whole truth and nothing but the truth.
@article{jones_ai_2025,
title = {{AI} hallucinations can’t be stopped — but these techniques can limit their damage},
volume = {637},
copyright = {2025 Springer Nature Limited},
issn = {1476-4687},
url = {https://www.nature.com/articles/d41586-025-00068-5},
doi = {10.1038/d41586-025-00068-5},
abstract = {Developers have tricks to stop artificial intelligence from making things up, but large language models are still struggling to tell the truth, the whole truth and nothing but the truth.},
language = {en},
number = {8047},
urldate = {2025-01-22},
journal = {Nature},
author = {Jones, Nicola},
month = jan,
year = {2025},
note = {Bandiera\_abtest: a
Cg\_type: News Feature
Publisher: Nature Publishing Group
Subject\_term: Machine learning, Computer science, Technology},
keywords = {Computer science, Machine learning, Technology},
pages = {778--780},
}
Downloads: 0
{"_id":"Hv6aqGfE94ht7ZkRc","bibbaseid":"jones-aihallucinationscantbestoppedbutthesetechniquescanlimittheirdamage-2025","author_short":["Jones, N."],"bibdata":{"bibtype":"article","type":"article","title":"AI hallucinations can’t be stopped — but these techniques can limit their damage","volume":"637","copyright":"2025 Springer Nature Limited","issn":"1476-4687","url":"https://www.nature.com/articles/d41586-025-00068-5","doi":"10.1038/d41586-025-00068-5","abstract":"Developers have tricks to stop artificial intelligence from making things up, but large language models are still struggling to tell the truth, the whole truth and nothing but the truth.","language":"en","number":"8047","urldate":"2025-01-22","journal":"Nature","author":[{"propositions":[],"lastnames":["Jones"],"firstnames":["Nicola"],"suffixes":[]}],"month":"January","year":"2025","note":"Bandiera_abtest: a Cg_type: News Feature Publisher: Nature Publishing Group Subject_term: Machine learning, Computer science, Technology","keywords":"Computer science, Machine learning, Technology","pages":"778–780","bibtex":"@article{jones_ai_2025,\n\ttitle = {{AI} hallucinations can’t be stopped — but these techniques can limit their damage},\n\tvolume = {637},\n\tcopyright = {2025 Springer Nature Limited},\n\tissn = {1476-4687},\n\turl = {https://www.nature.com/articles/d41586-025-00068-5},\n\tdoi = {10.1038/d41586-025-00068-5},\n\tabstract = {Developers have tricks to stop artificial intelligence from making things up, but large language models are still struggling to tell the truth, the whole truth and nothing but the truth.},\n\tlanguage = {en},\n\tnumber = {8047},\n\turldate = {2025-01-22},\n\tjournal = {Nature},\n\tauthor = {Jones, Nicola},\n\tmonth = jan,\n\tyear = {2025},\n\tnote = {Bandiera\\_abtest: a\nCg\\_type: News Feature\nPublisher: Nature Publishing Group\nSubject\\_term: Machine learning, Computer science, Technology},\n\tkeywords = {Computer science, Machine learning, Technology},\n\tpages = {778--780},\n}\n\n\n\n\n\n\n\n","author_short":["Jones, N."],"key":"jones_ai_2025","id":"jones_ai_2025","bibbaseid":"jones-aihallucinationscantbestoppedbutthesetechniquescanlimittheirdamage-2025","role":"author","urls":{"Paper":"https://www.nature.com/articles/d41586-025-00068-5"},"keyword":["Computer science","Machine learning","Technology"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero-group/bethhoppe/5609059","dataSources":["tnM59J55CyNeZmQ8S"],"keywords":["computer science","machine learning","technology"],"search_terms":["hallucinations","stopped","techniques","limit","damage","jones"],"title":"AI hallucinations can’t be stopped — but these techniques can limit their damage","year":2025}