Using a process called RLHF (Reinforcement Learning from Human Feedback), large AI models are being made less biased and safer, but at the same time, they can reduce the models\u2019 creativity. In practice, while these AI models are getting better at avoiding offensive or risky content, they are also losing the ability to generate a wide range of new or diverse ideas<\/p>\n\n\n\n
The fact that AI chatbots and text generators are safer can accidentally make them more boring. The more designers work to remove bias or risky content from AI, the less likely it is to come up with new and interesting answers. This means that users and companies need to choose the right kind of AI for the job: creative but riskier for brainstorming and writing, or safer but more repetitive for customer service or sensitive contexts.
<\/p>\n\n\n\n
What did we learn?<\/strong><\/p>\n\n\n\n \u2022 Safety comes at a price: Methods like RLHF that filter out unwanted biases and toxic content work well, but they also make models less creative. Researchers define creativity as a model\u2019s ability to use a wide range of language structures and express diverse ideas.<\/p>\n\n\n\n \u2022 Reduced diversity: The paper describes three experiments comparing \u201cbase\u201d AI models (unaligned) with those made safer by RLHF (\u201caligned\u201d models). Aligned models generate less diverse names, backgrounds, text styles, and product reviews. For example, when creating fictional customer profiles, aligned models repeatedly use the same names and personalities, while base models show much greater diversity.<\/p>\n\n\n\n \u2022 Models get \u201cstuck\u201d: Research finds that safer AI models tend to fall into a kind of rut, sticking to a few \u201csafe\u201d templates or options even when asked to be creative. This is called \u201cmode collapse,\u201d where the model is locked into only a small set of possible responses.<\/p>\n\n\n\n \u2022 A trade-off for businesses and users: Safe and consistent AI models are best for situations like customer support or content moderation. More creative and less filtered models are preferable for tasks.<\/p>","protected":false},"excerpt":{"rendered":" Kori\u0161tenjem procesa nazvanog RLHF (Reinforcement Learning from Human Feedback) nastoji se velike modele umjetne inteligencije u\u010diniti manje pristranim i sigurnijim, no istovremeno mo\u017ee do\u0107i do smanjenja kreativnost tih modela. U praksi, iako ovi modeli umjetne inteligencije postaju bolji u izbjegavanju uvredljivog ili rizi\u010dnog sadr\u017eaja, oni tako\u0111er gube sposobnost generiranja \u0161irokog raspona novih ili raznolikih ideja. […]<\/p>\n","protected":false},"author":3,"featured_media":453,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"_et_pb_use_builder":"off","_et_pb_old_content":"","_et_gb_content_width":"","footnotes":""},"categories":[14],"tags":[],"class_list":["post-416","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-radovi"],"acf":{"radovi_source_url":"https:\/\/arxiv.org\/abs\/2406.05587","radovi_button_label":"Pro\u010ditajte izvorni rad"},"_links":{"self":[{"href":"https:\/\/brain.hr\/en\/wp-json\/wp\/v2\/posts\/416","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/brain.hr\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/brain.hr\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/brain.hr\/en\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/brain.hr\/en\/wp-json\/wp\/v2\/comments?post=416"}],"version-history":[{"count":5,"href":"https:\/\/brain.hr\/en\/wp-json\/wp\/v2\/posts\/416\/revisions"}],"predecessor-version":[{"id":437,"href":"https:\/\/brain.hr\/en\/wp-json\/wp\/v2\/posts\/416\/revisions\/437"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/brain.hr\/en\/wp-json\/wp\/v2\/media\/453"}],"wp:attachment":[{"href":"https:\/\/brain.hr\/en\/wp-json\/wp\/v2\/media?parent=416"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/brain.hr\/en\/wp-json\/wp\/v2\/categories?post=416"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/brain.hr\/en\/wp-json\/wp\/v2\/tags?post=416"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}