Meta tags:

Headings (most frequently used words):

hila, gonen, recent, updates,

Text of the page (most frequently used words):
the (17), and (16), 2026 (6), hila (4), gonen (4), for (4), models (4), computer (4), science (4), university (4), our (3), ubc (3), assistant (3), professor (3), machine (3), intelligence (3), model (3), nlp (3), github (2), follow (2), august (2), 2025 (2), have (2), been (2), accepted (2), emnlp (2), different (2), more (2), here (2), alberta (2), institute (2), amii (2), cifar (2), chair (2), paper (2), behavior (2), responsible (2), available (2), language (2), updates (2), not (2), students (2), you (2), are (2), directly (2), that (2), research (2), languages (2), understanding (2), tools (2), powered, fork, minimal, mistakes, academicpages, jekyll, feed, sitemap, papers, findings, dementia, through, eyes, omniguard, joined, february, appointed, see, details, march, has, tacl, rewriting, history, recipe, interventional, analyses, study, data, effects, may, keynote, canadian, conference, track, june, new, now, arxiv, phantombench, benchmarking, non, existential, threat, recent, please, able, respond, due, volume, emails, receive, will, recruiting, graduate, this, coming, cycle, fall, 2027, deadline, december, should, apply, interested, working, with, simply, mention, name, your, application, department, email, note, prospective, before, joining, was, postdoctoral, researcher, meta, amazon, prior, did, obtained, from, hebrew, lab, bar, ilan, paul, allen, school, engineering, washington, interests, lie, intersection, natural, processing, learning, artificial, long, term, vision, transforming, llms, into, reliable, trustworthy, systems, which, fair, across, socio, demographic, groups, focus, three, main, threads, control, interpretation, controlling, generation, reliability, safety, fairness, making, consistent, safe, mitigating, biases, risks, multilinguality, creating, equitably, serve, speakers, many, possible, well, emergent, property, cross, linguality, additionally, recently, developed, interest, employing, methodologies, health, domain, biritish, columbia, google, scholar, twitter, teaching, group, publications, home,

Text of the page (random words):
hila gonen home publications updates cv group teaching hila gonen assistant professor at ubc follow twitter github google scholar hila gonen i am an assistant professor of computer science at the university of biritish columbia and a cifar ai chair at the alberta machine intelligence institute amii my research interests lie at the intersection of natural language processing machine learning and artificial intelligence my long term vision is transforming llms into responsible reliable and trustworthy systems which are available and fair across languages and different socio demographic groups in my research i focus on three main threads 1 control and interpretation of models understanding model behavior and controlling model generation 2 reliability safety and fairness making models more consistent and safe and mitigating biases and risks 3 multilinguality creating nlp tools that equitably serve speakers of as many languages as possible as well as understanding the emergent property of cross linguality in models additionally i have recently developed an interest in employing nlp tools and methodologies in the health domain before joining ubc i was a postdoctoral researcher at the paul g allen school of computer science engineering at the university of washington at meta ai and at amazon prior to that i did my ph d in computer science at the nlp lab at bar ilan university i obtained my ms c in computer science from the hebrew university note for prospective students please do not email me directly as i am not able to respond due to the volume of emails i receive i will be recruiting graduate students this coming cycle for the fall of 2027 the deadline is december 15 2026 and you should apply directly to the department if you are interested in working with me simply mention my name in your application recent updates june 2026 our new paper phantombench benchmarking the non existential threat of language models is now available on arxiv may 2026 keynote at the responsible ai track at the canadian ai conference march 2026 our paper rewriting history a recipe for interventional analyses to study data effects on model behavior has been accepted to tacl february 2026 appointed as cifar ai chair at the alberta machine intelligence institute amii see here and here for more details august 2025 joined ubc as an assistant professor august 2025 our papers have been accepted at emnlp omniguard and findings of emnlp dementia through different eyes sitemap follow github feed 2026 hila gonen powered by jekyll academicpages a fork of minimal mistakes