Ci bi mu melGis bi ci topp
Jëfandikoo xel mu amul dëgg-dëgg ci diggante genn aju xel ci sistemu algoritmik
Askan wi
GUIDE Sosiete
Biy jafe-jafe ci AI mën na am ci lu system bi jàppul, jàppul ci wàllu jafe-jafe, walla jox nañu ndigal ci nit bu am jafe-jafe, waaye jafe-jafe yi am nañu wàllu yu bari te benn benchmark du mel nekk ci wàllu yépp.
Déglul tegtal biiIA-nettali · ~3 min
Jàngi yu bees yi jàngal nañu wàllu jafe-jafe ci LLM, jàngi yu AI joxoon, ak jàngi yu wàññi; jàngi yi am nañu ci wàllu version yu model, kategori jafe-jafe ak wàllu jàngat.
Disability is not one demographic variable. Blindness, deafness, chronic illness, mobility impairment, neurodivergence and speech disability can affect different interactions, and people within each group have varied preferences and support needs. Bias can arise through inaccessible interfaces, proxy features, missing training examples, or model outputs that associate disability with lower competence. It can also occur when an automated assessment treats one communication style as the only valid way to show ability. A 2024 Archives of Physical Medicine and Rehabilitation study tested ChatGPT and Gemini with generated descriptions of people, patients and athletes. It found that the systems underestimated disability in their generated sample and, in language analysis, described disabled people with fewer favorable qualities and more limitations. The study was an observational prompt experiment using 2023 versions; it does not establish how every current model behaves or how disabled people experience every deployment. A 2025 EMNLP paper introduced AccessEval, testing 21 open and closed models across six real-world domains and nine disability types with paired neutral and disability-aware queries. The authors reported more negative tone, higher factual error and greater stereotyping in disability-aware responses, with variation by domain and disability type; hearing, speech and mobility contexts were especially affected in their benchmark. A separate 2024 ASSETS interview study spoke with 30 people with disabilities about real-life chatbot use and needs. These studies show evidence of risks as well as use cases, but neither justifies broad conclusions about all disabled users or all AI. U.S. employers must also comply with the ADA when using software in hiring and employment; automation does not remove accommodation obligations.
Benn tool video-interview bi jàngal na ndigal ci wàllu wax ak wàllu xel, ndax li, jëmmal bi jàngal na ne ndaw lii am na jafe-jafe yu wér ci wàllu wàññi, te am nañu ci wàllu jàmm ci jafe-jafe yi.
Benn system proctoring exam bi jox nañu ndigal ci wàllu wàll yu amul solo, te jàngi bi jox na ndigal bu nit ak jàmm bu am solo.
Benn generator texte bi wax na nit bu am jafe-jafe ak làkk yu jàmm ci wàllu ndaw, te tax na jàngal bi jàngal ne am nañu jàngal ci wàllu jafe-jafe.
Benn jëmmal bu jëmmal ci screen-reader wax na ne interface bu AI am nañu control yu amul label, ndax li, team bi product jàngal na workflow ak jëmmal yu am jafe-jafe.
Research is moving toward disability-led evaluation, larger benchmark coverage and testing in actual work and service contexts. New model versions can change results, so organizations should re-evaluate after updates and involve people with disabilities in design, procurement, testing and remediation. Future evaluation should report model versions, study populations and measured outcomes so results can be compared without generalizing beyond the evidence. Research priorities include participatory design, accessible data collection and evaluation of assistive benefits alongside harms, across disability communities. Measure changes with users.
Bulletin bu amul fayda
Ñatti jaar-jaari IA yuñ firndeel bis bu nekk ci ayu-bis bi, ñu bind leen ci Àngle bu leer. Gratis ba fàww, amul yëgle.
Benn email bis bu nekk ci ayu-bis bi. Benn klik nga dindi abonemaa bi. Dunu musa jaay wala séddoo sa adres.
Nattal sa bopp
Feedback ci saasi ci bépp tontu, ak sertifikaa buñ mëna séddoo ak ID buñ mëna saytu soo jàllee ci njàng mi.
Jàppale njàngum IA te doo fay. AI Understanding mbootaay la buy def te Yàlla tax — amul yëgle, amul paywall, musul am. Defal ab sarax
Disability bias in AI can occur when a system misreads, excludes or stereotypes a disabled person, but disability is highly heterogeneous and no single benchmark represents all conditions. Recent studies have measured disparities in LLM responses, AI-generated descriptions and hiring prompts; their findings depend on model versions, disability categories and experimental settings.
The study compared generated descriptions and language about people, patients and athletes with or without disability status.
The study evaluated ChatGPT and Gemini using a defined prompt experiment; its results do not represent all current models or contexts.
AccessEval wax na ne jàpp na 21 model ci juróomi juróomi noonu yu xam-xam ak juróomi benn domain.
Téere bi wax na ci wone yu mel ni, ak wàll yu bari ci model, domain ak noonu yu xam-xam.
Jàngat bi ASSETS jox na wutéef 30 nit, sampu yu xam-xam ngir wéy ci jàngal jafe-jafe yu amul ci wone ci wàllu ndawte.
Weyal di jàng
Tann nañu yeneen njiit ngir topic bii
Ci bi mu melGis bi ci topp
Jëfandikoo xel mu amul dëgg-dëgg ci diggante genn aju xel ci sistemu algoritmik
Askan wi