Language models have been conditioned to make wild guesses instead of admitting ignorance, a study has found<\/p>\n
The company behind ChatGPT has addressed the persistent problem of Artificial Intelligence models generating plausible but false statements that it calls \u201challucinations.\u201d
\nIn a statement on Friday, OpenAI explained that models are typically encouraged to make a guess, however improbable, as opposed to acknowledging that they cannot answer a question.
\nThe issue is attributable to the core principles underlying \u201cstandard training and evaluation procedures,\u201d\u00a0it added.
\nOpenAI revealed that instances in which language models \u201cconfidently generate an answer that isn\u2019t true\u201d continue to plague newer, more advanced iterations, including its latest flagship GPT-5 system.
\nAccording to a recent study, the problem is rooted in the way the performance of language models is usually evaluated, with the guessing model ranked higher than a careful one that admits uncertainty. Under the standard protocols, AI systems learn that failure to generate an answer is a surefire way to get zero points on a test, while an unsubstantiated guess may end up being correct.<\/p>\n
READ MORE: Is AI driving us all insane?<\/p>\n
\u201cFixing scoreboards can broaden adoption of hallucination-reduction techniques,\u201d the statement concluded, acknowledging, however, that \u201caccuracy will never reach 100% because, regardless of model size, search and reasoning capabilities, some real-world questions are inherently unanswerable.\u201d<\/p>\n","protected":false},"excerpt":{"rendered":"
Language models have been conditioned to make wild guesses instead of admitting ignorance, a study has found The company behind ChatGPT has addressed the persistent problem of Artificial Intelligence models…<\/p>\n","protected":false},"author":1,"featured_media":17749,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"rop_custom_images_group":[],"rop_custom_messages_group":[],"rop_publish_now":"initial","rop_publish_now_accounts":[],"rop_publish_now_history":[],"rop_publish_now_status":"pending","footnotes":""},"categories":[4,3,5],"tags":[],"class_list":["post-17748","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-economy","category-politics","category-society"],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t