Meta tags:
description=Lead PI of Conceptualization Lab @ UChicago;

Headings (most frequently used words):

ari, holtzman, useful, stuff, events, some, things, interested, in, right, now, selected, publications, materials, from, the, academic, job, market,

Text of the page (most frequently used words):
the (15), #holtzman (11), ari (10), and (10), paper (7), 2025 (7), pdf (6), models (6), llms (6), communication (6), uchicago (6), gave (6), talk (6), but (5), mechinterp (5), from (4), code (4), peter (4), west (4), luke (4), zettlemoyer (4), language (4), have (4), out (4), think (4), that (4), with (4), work (3), can (3), generative (3), science (3), modeling (3), for (3), are (3), want (3), not (3), students (3), intelligence (3), phd (3), 5kb (2), yejin (2), choi (2), emnlp (2), 2021 (2), right (2), what (2), learning (2), how (2), model (2), complex (2), systems (2), chenhao (2), tan (2), tell (2), see (2), ideahub (2), excited (2), this (2), let (2), ever (2), produce (2), build (2), games (2), where (2), some (2), you (2), both (2), just (2), our (2), transformer (2), looking (2), about (2), workshop (2), seminar (2), stories (2), apply (2), lab (2), all (2), check (2), dsi (2), doing (2), 4kb, holtzman_ariel_teaching_statement, 2026, holtzman_ariel_research_statement, 6kb, holtzman_ariel_dei_statement, 105, 8kb, holtzman_ariel_cv, 115, 9kb, holtzman_ariel_cover_letter_uochicago, materials, academic, job, market, useful, stuff, fairseq, openai, api, huggingface, jan, buys, maxwell, forbes, iclr, 2019, curious, case, neural, text, degeneration, project, page, equal, contribution, vered, shwartz, surface, form, competition, why, highest, probability, answer, isn, always, sewon, min, xinxi, lyu, mikel, artetxe, mike, lewis, hannaneh, hajishirzi, 2022, rethinking, role, demonstrations, makes, context, make, sense, large, behavior, margaret, weijia, shi, artidoro, pagnoni, predicting, acting, trade, off, between, world, agent, prompting, scientific, inquiry, dataset, harvey, yiyun, aryan, shrivastava, jared, moore, absencebench, missing, selected, publications, other, ideas, twitter, guess, yes, look, either, way, story, two, jury, still, whether, passive, based, truly, interesting, media, should, main, mechanic, there, disco, elysium, chants, sennaar, keep, talking, nobody, explodes, etc, ones, npc, driven, mmorpgs, friend, group, ops, use, novel, social, ecosystem, navigate, will, happen, part, opinion, alignment, communities, become, somewhat, less, ambitious, often, said, overrated, very, cool, vast, majority, when, behavioral, much, insight, comes, slowly, becoming, convinced, simpler, than, thought, they, don, line, kind, explanations, people, were, throwing, hat, back, into, after, being, briefly, then, abandoning, figure, communicate, themselves, residual, stream, things, interested, now, 2024, was, great, success, symposium, articulating, ineffable, mmls, economist, published, letter, visions, colm, halloween, cmu, lti, colloquium, université, québec, montréal, theoretical, philosophy, séminaire, informatique, cognitive, coginterp, neurips, northwestern, seeing, like, events, pragmatic, narrative, 110, machine, advised, post, doc, fair, meta, previously, experience, plus, required, website, longer, time, reply, emails, prospective, highly, encourage, data, institute, actively, through, office, 315, courtesy, ttic, assistant, professor, blog, second, researcher, head, conceptualization, fossick, aholtzman, edu, google, scholar,

Text of the page (random words):
ari holtzman ari holtzman ari holtzman i m doing it with llms or i m not doing it at all google scholar ️ aholtzman uchicago edu ideahub fossick head of conceptualization lab second ever communication intelligence researcher check out our c i blog assistant professor at uchicago cs uchicago dsi ttic by courtesy office dsi 315 i am actively looking for phd students to apply through both uchicago cs and the data science institute experience with llms generative models is a plus but not required i no longer have time to reply to all emails from prospective phd students but i highly encourage you to check out my lab website and apply previously post doc fair meta phd from uw advised by luke zettlemoyer communication intelligence machine communication generative models as a complex systems science holtzman cv pdf 110 5kb i work on pragmatic narrative stories about models and models that produce stories events 2025 01 gave a talk at northwestern s cs seminar on seeing like a language model 2025 12 gave a talk at coginterp neurips 2025 11 gave a talk at université du québec à montréal s séminaire en informatique cognitive and uchicago s theoretical philosophy workshop 2025 10 gave a talk at cmu s lti colloquium seminar on halloween 2025 09 gave a talk at the colm visions of language modeling workshop 2025 07 the economist published my letter 2025 06 gave a talk about articulating the ineffable at mmls 2024 10 the uchicago communication and intelligence symposium was a great success some things i m interested in right now i want to figure out how transformer llms communicate with themselves in the residual stream in my opinion both the alignment and mechinterp communities have become somewhat less ambitious i ve often said that i think mechinterp is overrated i think mechinterp is very cool just the vast majority of students want to do mechinterp when i think behavioral work is where much of our insight comes from but i m slowly becoming convinced that transformer llms are simpler than i thought they just don t line up with the kind of explanations people were looking for so i m throwing my hat back into mechinterp after being briefly excited and then abandoning it in 2021 i think we should build communication games games where the main mechanic is communication there are some disco elysium chants of sennaar keep talking and nobody explodes etc but i want ones that are npc driven not mmorpgs or friend group co ops and use llms to build a novel social ecosystem you have to navigate this will happen let s be a part of it the jury is still out on whether passive learning based ai can ever produce truly interesting media my guess is yes but i m excited to look at this either way let s see if llms have a story to tell or two for other ideas see my twitter or ideahub selected publications absencebench language models can t tell what s missing harvey yiyun fu aryan shrivastava jared moore peter west chenhao tan ari holtzman paper dataset code prompting as scientific inquiry ari holtzman chenhao tan paper predicting vs acting a trade off between world modeling agent modeling margaret li weijia shi artidoro pagnoni peter west ari holtzman paper generative models as a complex systems science how can we make sense of large language model behavior ari holtzman peter west luke zettlemoyer paper rethinking the role of demonstrations what makes in context learning work emnlp 2022 sewon min xinxi lyu ari holtzman mikel artetxe mike lewis hannaneh hajishirzi luke zettlemoyer paper code surface form competition why the highest probability answer isn t always right emnlp 2021 ari holtzman peter west vered shwartz yejin choi and luke zettlemoyer equal contribution paper project page code the curious case of neural text degeneration iclr 2019 ari holtzman jan buys li du maxwell forbes yejin choi paper code huggingface openai api fairseq useful stuff materials from the academic job market holtzman_ariel_cover_letter_uochicago pdf 115 9kb holtzman_ariel_cv pdf 105 8kb holtzman_ariel_dei_statement pdf 50 6kb holtzman_ariel_research_statement pdf 2026 5kb holtzman_ariel_teaching_statement pdf 45 4kb