-
Tweets8K
-
Followers9K
-
Following1K
-
Likes19K
How much does an LM depend on information provided in-context vs its prior knowledge? Check out how @vesteinns, @niklas_stoehr, @JenniferCWhite, @AaronSchein, @ryandcotterell + I answer this by measuring a *context's persuasiveness* and an *entity's susceptibility*🧵
The newest version is going to be pushed soon!
Monograph on "Formal Aspects of Language Modeling" from @ryandcotterell et al. arxiv.org/abs/2311.04329 It would be so nice if everyone read this and we had shared foundations. Particularly for interpretability.
Honored to see my name among these amazing colleagues, @PsychScience Rising Stars! psychologicalscience.org/members/awards…
New paper alert! We dive into the world of LLMs and cognitive biases, focusing on how models tackle arithmetic word problems—do they show the same biases as humans? Here’s a summary 🤖📚 #LLMs #MachineLearning #AI arxiv.org/abs/2401.18070
Slowly realizing that two days ago I successfully defended my PhD! 🤯 I’m extremely grateful to my supervisors, @IAugenstein and @ryandcotterell, my PhD committee, @SergeBelongie, @pascalefung, @licwu, and all of my colleagues and collaborators!
Slowly realizing that two days ago I successfully defended my PhD! 🤯 I’m extremely grateful to my supervisors, @IAugenstein and @ryandcotterell, my PhD committee, @SergeBelongie, @pascalefung, @licwu, and all of my colleagues and collaborators!
Massive congrats to @karstanczak for passing her PhD defence with flying colours! 🎊🥂🥳 Very proud of you 🤗🥹 Thanks to @SergeBelongie @pascalefung @licwu for serving on the committee. Karolina’s thesis on multilingual gender bias probing: di.ku.dk/english/resear… #NLProc
This Friday (05/01), 14:00-15:00 CET, the @AiCentreDK hosts a guest talk by @ValvodaJosef titled “When Neural Networks Meet the Law” 🧑⚖️(aicentre.dk/events/talk-wh…). The talk will take place in the Seminar Room at P1 (Øster Voldgade 3, 1350 København K).
LLMs are now trained >1000x as much language data as a child, so what happens when you train a "BabyLM" on just 100M words? The proceedings of the BabyLM Challenge are now out along with our summary of key findings from 31 submissions: aclanthology.org/volumes/2023.c… Some highlights 🧵
We derive a concept erasure method that is even more surgical than LEACE, when you have access to ground-truth concept labels at inference time. In the binary case, this ends up being equivalent to a simple difference-in-means edit to the activations. blog.eleuther.ai/oracle-leace/
The IBM Research Zürich lab is at #NeurIPS2023 in NOLA! Come chat with us about all things research and life in Zürich, if you haven’t already 😉 @IBMResearch
If you are interested in knowing how you can do energy-based sampling from language models, make sure to check our #NeurIPS23 paper titled “Structured Voronoi Sampling”...🧵 arxiv.org/pdf/2306.03061…
🤖 Ever wondered what RNN-based language models are truly capable of? Check out our #EMNLP2023 paper which places formal bounds on their capabilities! With @AnejSvete, @leoduw, and @RyanCotterell (1/7) arxiv.org/abs/2310.12942
Tianyu and Afra's paper won an Outstanding Paper award at EMNLP 2023 and achieved perfect reviews: 5's for soundness and excitement and 5 from the AC. It's worth a read! openreview.net/forum?id=vtqfP…)
Tianyu and Afra's paper won an Outstanding Paper award at EMNLP 2023 and achieved perfect reviews: 5's for soundness and excitement and 5 from the AC. It's worth a read! openreview.net/forum?id=vtqfP…)
Excited to receive an Outstanding Paper award for this work at @emnlpmeeting! Thanks to my co-authors George Foster and @markuseful! Updated version available here: aclanthology.org/2023.emnlp-mai…
Excited to receive an Outstanding Paper award for this work at @emnlpmeeting! Thanks to my co-authors George Foster and @markuseful! Updated version available here: aclanthology.org/2023.emnlp-mai…
This paper just won an outstanding paper award at #EMNLP2023 and I'm super proud of it! :) Make sure to chat to @weGotlieb about it, if you are in Singapore! Also, feel free to chat with me if you are in New Orleans for #NeurIPS2023
This paper just won an outstanding paper award at #EMNLP2023 and I'm super proud of it! :) Make sure to chat to @weGotlieb about it, if you are in Singapore! Also, feel free to chat with me if you are in New Orleans for #NeurIPS2023
Thank you to #EMNLP2023 chairs for the 😱 two 😱 outstanding paper awards! I am so grateful to have worked on these projects with wonderful colleagues — @tpimentelms (who is the first author on one of the papers!), @clara__meister, @kmahowald and @ryandcotterell
I think 2.2 is an example from my LLM class (rycolab.io/classes/llm-s2…). Ruida was a top student.
I think 2.2 is an example from my LLM class (rycolab.io/classes/llm-s2…). Ruida was a top student.
New preprint! Dana Angluin, I, and Andy Yang @pentagonalize show that masked hard-attention transformers are exactly equivalent to the star-free regular languages. arxiv.org/abs/2310.13897
(((ل()(ل() 'yoav))).. @yoavgo
46K Followers 2K FollowingSasha Rush @srush_nlp
51K Followers 463 Following Professor, Programmer in NYC. Cornell Tech, Hugging Face 🤗 https://t.co/cZl0wTfqGzTal Linzen @tallinzen
16K Followers 894 Following Professor @nyuling and @NYUDataScience, research scientist @GoogleAIDelip Rao e/σ @deliprao
46K Followers 5K Following Busy inventing the shipwreck. @Penn. Past: @johnshopkins, @UCSC, @Amazon, @Twitter ||Art: #NLProc, Vision, Speech, #DeepLearning || Life: 道元, improv, running 🌈Sam Bowman @sleepinyourhat
35K Followers 3K Following AI alignment + LLMs at NYU & Anthropic. Views not employers'. No relation to @s8mb. I think you should join @givingwhatwecan.Percy Liang @percyliang
49K Followers 408 Following Associate Professor in computer science @Stanford @StanfordHAI @StanfordCRFM @StanfordAILab @stanfordnlp | cofounder @togethercompute | PianistYoav Artzi @yoavartzi
13K Followers 163 Following Research/prof @cs_cornell + @cornell_tech🚡 / https://t.co/9YnWry7yHs / https://t.co/3VmRSyYm2d / asso. faculty director @arxiv / building https://t.co/f9QkzO5kaCKyunghyun Cho @kchonyc
60K Followers 2K Following a combination of a mediocre scientist, a mediocre manager, a mediocre advisor & a mediocre PC at @nyuniversity (@CILVRatNYU) & @genentech (@PrescientDesign).Graham Neubig @gneubig
30K Followers 582 Following Associate professor at CMU, studying natural language processing and machine learning.Naomi Saphra @nsaphra
7K Followers 1K Following Waiting on a robot body. ML/NLP. All opinions are universal and held by both employers and family. Same username on every lifeboat off this sinking ship.Jacob Andreas @jacobandreas
13K Followers 955 Following Teaching computers to read. Assoc. prof @MITEECS / @MIT_CSAIL (he/him). https://t.co/5kCnXHjtlY https://t.co/2A3qF5vdJwLuca Soldaini 🎀 @soldni
6K Followers 1K Following I like tokens! Lead for OLMo data team at @allen_ai, open source science fan, @QueerInAI organizer 🤖☕️🍕they/themAkari Asai @AkariAsai
11K Followers 650 Following Ph.D. student @uwcse & @uwnlp. NLP. IBM Ph.D. fellow (2022-2023). Meta student researcher (2023-) . ☕️ 🐕 🏃♀️🧗♀️🍳Nathan Schneider @complingy
4K Followers 1K Following Computational Linguist and Professional Nerd at Georgetown University he/him pronouns, ALL the prepositions @[email protected] @complingy.bsky.socialKayo Yin @kayo_yin
8K Followers 554 Following PhD student @berkeley_ai @berkeleynlp working on interpretability and signed languages. Former @msftresearch @deepmind @carnegiemellon @polytechnique. 🇫🇷🇯🇵Felix Hill @FelixHill84
9K Followers 777 Following Research Scientist, Deepmind I try to think hard about everything I tweet, esp on 90s football and 80s music None of my opinions are really someone else'sDanish Pruthi @danish037
6K Followers 627 Following Faculty at Indian Institute of Science, Bangalore. PhD from @LTIatCMU.Mark Dredze @mdredze
4K Followers 786 Following John C Malone Professor at @JohnsHopkins @JHUCompSci @jhuclsp @jhumceh; Part time @techatbloomberg (tweets my own) Mastodon @[email protected]Ana Marasović @anmarasovic
4K Followers 602 Following Asst prof @UUtah · Ex @allen_ai @uwnlp postdoc @HD_NLP PhD · she/her 🇭🇷Xuhui Zhang @XuhuiZhangXHZ
0 Followers 70 FollowingSarthak Choudhary @eigenguy
5 Followers 11 FollowingMalvinas @Malvina31374925
39 Followers 154 FollowingDavid Nikson @SamuelD76488206
95 Followers 112 Followingbhara_t3234 @BT32342789
9 Followers 852 FollowingAB M @abdelmehdi_ab
48 Followers 1K FollowingDesi R. Ivanova @desirivanova
678 Followers 834 Following 🤖 DPhil @OxCSML @StatMLIO (interned @MSFTResearch, @AIatMeta), former quant 📈 (@GoldmanSachs), former former gymnast 🤸♀️ My opinions are my own. 🇧🇬-🇬🇧Hanqi Yan @yan_hanqi
302 Followers 459 Following PhD @WarwickNLP @kclinfon robust and interpretable representation learning for NLP. Former @MBZUAI @Hongkongpolyu | M.S @PKU1898 | B.E @beihang1952kermode_adr @KermodeAdr
2 Followers 34 FollowingAlexandra Pafford @ANPafford
22 Followers 198 Following Psychology Research MSc student at University of AmsterdamEdna_ @Edna1282739
5 Followers 710 FollowingEva_VD @EvaVD867189
3 Followers 755 FollowingJonas Bacci @jonasbacci
5 Followers 64 FollowingJake Levinson @Jacob11son
672 Followers 2K Following 🌁 I talk about San Francisco. Want to connect? Email: [email protected]Matt Grenander @MattGrenander
4 Followers 71 FollowingAhmad Beirami @abeirami
4K Followers 2K Following Building safe, helpful, and scalable generative AI @Google | ex-{@AIatMeta, @EA, @MIT, @Harvard, @DukeU} | @GeorgiaTech PhD | زن زندگی آزادی | opinions my ownBanghua Zhu @BanghuaZ
2K Followers 772 Following PhD @Berkeley_EECS, statistics, info theory, LLM, RL, Human-AI Interactions.Arman Adibi @AdibiArman
479 Followers 2K Following Postdoc @Princeton | Ph.D. from @Penn, @WarrenCntrPenn | Studying machine learning and optimization.Berivan Isik @BerivanISIK
3K Followers 2K Following PhD @StanfordAILab. Scalable & trustworthy ML, transfer learning, language models, federated learning, privacy | prev: @Google @AWSCloud @VectorInstTheoretical Foundatio.. @tf2m_workshop
77 Followers 15 Following Workshop on Theoretical Foundations of Foundation Models @icmlconf 2024.Jordan Gong @jordan__gong
40 Followers 2K FollowingSerhan Yilmaz @srhnylmz14
68 Followers 695 Following current junior cs undergrad @sabanciu & NLP engineering intern @YapiKredi & president/founder @kaisabanci // prev @EPFL @BU_Tweets @kocuniversity // contact: dmMingshan Chang @shesshan_
4 Followers 82 Following CS graduate student at @UCAS1978; SIAT-NLP, CAS; #NLProc #AIAngelo Giacco @giaccoangelo
48 Followers 70 Following probabilistic ai and language models @ETH and @imperialcollegešăʍƥɮ ŧēχţ�.. @andreas16700
749 Followers 1K Following 23yo 丨bsc c.s ucy 🇨🇾 🔜 msc a.i uzh 🇨🇭 ⟦he/him⟧ 丨 🏳️🌈 丨 swift enthusiast 丨insta @andreas16700Arturo Villacañas @artuvillacanas
54 Followers 141 Following Interests: AI Safety & Security. Currently: @kasl_ai. Prev: @CISPA, @IMDEA_Software, @CCNCERT. 🏳️🌈Tianlin Liu @tianlinliu0121
374 Followers 927 Following Present: PhD student @UniBasel. Past: intern @GoogleDeepMind and @Google Brain.David Stap @davidstap
295 Followers 718 Following PhD candidate in Artificial Intelligence and Natural Language Processing @UvA_Amsterdam | Previously intern @Amazon | MSc AI from @UvA_AmsterdamShashank Sonkar @shashank_nlp
55 Followers 379 Following NLP+Education | Grad Student @rbaraniuk group | @RiceECE @rice_dsp @OpenStaxJames Parsloe @jamesparsloe
195 Followers 5K Following ML Engineer. Trying to increase the FLOPs I have access to. Used to make computers talk at Spotify/Sonantic.Leonardo Cotta @cottascience
1K Followers 273 Following Postdoc Fellow @VectorInst. Machine Learning, Sampling, and Causal Inference. Schooled at: @purduecs @dcc_ufmg. He/Ele. From BH 🔺 🇧🇷SyeMD @perseushidden
58 Followers 2K Following . e/acc . decentralize all power . playing at the meeting place of medicine, bits and biologyHelio @AereoHelio
108 Followers 2K FollowingErvin Lang @ervinlang
63 Followers 1K FollowingXiuquan Lv @ustcwizard
67 Followers 717 FollowingWilliam Jurayj @williamjurayj
48 Followers 191 Following Machine Learning. Language Processing. Opinions my own, follow != endorsement, etc.Bokun Wang @bokun_wang_
3 Followers 1K Following Ph.D. student at @TAMU CSE working on optimization and ML | ex-intern at @KAUST_News and @ArmMojtaba Vàlipour @ValipourMojtaba
393 Followers 3K Following CS PhD at @UWaterloo, Founding Engineer at Coastal Carbon and part time Researcher at @huawei Noah’s Arc Lab, prev enjoyed my time at @oraclelabs, & @CVC_UABMohammed Hamdy @mhamdy_res
82 Followers 3K Following A curious explorer of human and machine learning 🧐🤝🤖Arda Demirci @ardademirci_14
142 Followers 3K Following(((ل()(ل() 'yoav))).. @yoavgo
46K Followers 2K FollowingSasha Rush @srush_nlp
51K Followers 463 Following Professor, Programmer in NYC. Cornell Tech, Hugging Face 🤗 https://t.co/cZl0wTfqGzTal Linzen @tallinzen
16K Followers 894 Following Professor @nyuling and @NYUDataScience, research scientist @GoogleAIDelip Rao e/σ @deliprao
46K Followers 5K Following Busy inventing the shipwreck. @Penn. Past: @johnshopkins, @UCSC, @Amazon, @Twitter ||Art: #NLProc, Vision, Speech, #DeepLearning || Life: 道元, improv, running 🌈Christopher Manning @chrmanning
126K Followers 114 Following Director, @StanfordAILab. Assoc. Director, @StanfordHAI. Founder, @stanfordnlp. Prof. CS & Linguistics, @Stanford. IP @aixventureshq. 🇦🇺 Do #NLProc & #AI. 👋Sam Bowman @sleepinyourhat
35K Followers 3K Following AI alignment + LLMs at NYU & Anthropic. Views not employers'. No relation to @s8mb. I think you should join @givingwhatwecan.Percy Liang @percyliang
49K Followers 408 Following Associate Professor in computer science @Stanford @StanfordHAI @StanfordCRFM @StanfordAILab @stanfordnlp | cofounder @togethercompute | PianistYoav Artzi @yoavartzi
13K Followers 163 Following Research/prof @cs_cornell + @cornell_tech🚡 / https://t.co/9YnWry7yHs / https://t.co/3VmRSyYm2d / asso. faculty director @arxiv / building https://t.co/f9QkzO5kaCKyunghyun Cho @kchonyc
60K Followers 2K Following a combination of a mediocre scientist, a mediocre manager, a mediocre advisor & a mediocre PC at @nyuniversity (@CILVRatNYU) & @genentech (@PrescientDesign).Graham Neubig @gneubig
30K Followers 582 Following Associate professor at CMU, studying natural language processing and machine learning.Naomi Saphra @nsaphra
7K Followers 1K Following Waiting on a robot body. ML/NLP. All opinions are universal and held by both employers and family. Same username on every lifeboat off this sinking ship.Jacob Andreas @jacobandreas
13K Followers 955 Following Teaching computers to read. Assoc. prof @MITEECS / @MIT_CSAIL (he/him). https://t.co/5kCnXHjtlY https://t.co/2A3qF5vdJwLuca Soldaini 🎀 @soldni
6K Followers 1K Following I like tokens! Lead for OLMo data team at @allen_ai, open source science fan, @QueerInAI organizer 🤖☕️🍕they/themAkari Asai @AkariAsai
11K Followers 650 Following Ph.D. student @uwcse & @uwnlp. NLP. IBM Ph.D. fellow (2022-2023). Meta student researcher (2023-) . ☕️ 🐕 🏃♀️🧗♀️🍳Nathan Schneider @complingy
4K Followers 1K Following Computational Linguist and Professional Nerd at Georgetown University he/him pronouns, ALL the prepositions @[email protected] @complingy.bsky.socialKayo Yin @kayo_yin
8K Followers 554 Following PhD student @berkeley_ai @berkeleynlp working on interpretability and signed languages. Former @msftresearch @deepmind @carnegiemellon @polytechnique. 🇫🇷🇯🇵Felix Hill @FelixHill84
9K Followers 777 Following Research Scientist, Deepmind I try to think hard about everything I tweet, esp on 90s football and 80s music None of my opinions are really someone else'sDanish Pruthi @danish037
6K Followers 627 Following Faculty at Indian Institute of Science, Bangalore. PhD from @LTIatCMU.Mark Dredze @mdredze
4K Followers 786 Following John C Malone Professor at @JohnsHopkins @JHUCompSci @jhuclsp @jhumceh; Part time @techatbloomberg (tweets my own) Mastodon @[email protected]Theoretical Foundatio.. @tf2m_workshop
77 Followers 15 Following Workshop on Theoretical Foundations of Foundation Models @icmlconf 2024.Zhāng, Miǎo 张淼 @Miao_Zhang_dr
738 Followers 711 Following Post-doc at @cl_uzh doing corpus phonetics. SW Mandarin, Changsha Xiang, Mandarin, Japanese, English, Korean, German, Ikema. He/him. https://t.co/3GwrjPl0v3Peyman Milanfar @docmilanfar
67K Followers 262 Following Distinguished Scientist at Google Research. Computational Imaging, Machine Learning, and Vision. Tweets = personal opinions. May change or disappear over time.Neel Nanda @NeelNanda5
13K Followers 89 Following Mechanistic Interpretability lead @DeepMind. Formerly @AnthropicAI, independent. In this to reduce AI X-risk. Neural networks can be understood, let's go do it!Eghbal Hosseini @eghbal_hosseini
385 Followers 526 Following PhD candidate in Neuroscience @mitbrainandcog working with @ev_fedorenkoTaz Chu 朱立福 @taz_chu
6K Followers 363 Following mcgill math. pigeon roosting in my favourite pigeonhole. i also run the twitter account @prisonmathprojXiang Yue @xiangyue96
2K Followers 416 Following Postdoc @LTIatCMU. PhD from Ohio State @osunlp. Training & evaluating foundation models. Pushing the boundaries of AI🤖. Previously @MSFTResearch.Kaj Bostrom @alephic2
291 Followers 371 Following NLP geek getting a PhD at @utcompsci. I like generative modeling and procedural art (he/him). Also at @[email protected]Lena S. Bolliger @lsbolliger
57 Followers 103 Following PhD candidate in NLP @cl_uzh, University of Zurich.CLS @ChengleiSi
2K Followers 3K Following vibing @stanfordnlp | real AGI is the friends we made along the wayBut With Raptors @ButWitRaptors
119K Followers 1 Following @actionmoviekid and @awakeland3d put raptors in things. Somehow Tom Cruise is also involved Watch #VFXandChill every Friday at 10am pacific at https://t.co/Ypi3tXDhiF!Sasho Nikolov (thesas.. @thesasho
4K Followers 430 Following Associate professor at U of T. Computer science and math research: (differentially) private data analysis, geometry, discrepancy, optimization.Tamar Regev @tamaregev
464 Followers 212 Following Postdoc @ MIT lab of @ev_fedorenko. Cognitive neuroscience of language and speech.Avijit Thawani (Avi) @thawani_avijit
845 Followers 1K Following Graduating PhD @USC_ISI. LLMs/GenAI. Fintech Founding MLE. Filmmaker 100k+ views. Lived in UK, Singapore, India, US. ex: Microsoft Research, Amazon Alexa, AI2.Pedro Domingos @pmddomingos
78K Followers 165 Following Professor of computer science at UW and author of 'The Master Algorithm' and '2040'. Into machine learning, AI, and anything that makes me curious.Sheldon Axler @AxlerLinear
12K Followers 29 Following Emphasis here on 3 of my books: (1) Linear Algebra Done Right; (2) Measure, Integration & Real Analysis; (3) Harmonic Function Theory (with Bourdon & Ramey).Vered Shwartz @VeredShwartz
10K Followers 1K Following Assistant Professor at @UBC_CS and @VectorInst working on Natural Language ProcessingJesse Thomason @_jessethomason_
3K Followers 1K Following Assistant Prof @CSatUSC leading the GLAMOR lab https://t.co/VQhcMiC8hE (he/him; 💖💜💙)Evžen @__evzen
127 Followers 560 Following Data Science student @ETH_en🇨🇭 looking for research opportunities in AI interpretabilityCharlotte Bunne @_bunnech
3K Followers 485 Following PostDoc at @Genentech and @Stanford and Incoming Assistant Professor at @EPFL in Computer Science and Life Sciences.Caroline Andrews @candrews_vl
156 Followers 208 Following Postdoc at University of Zurich working on psycholinguistics of ergative languagesBLAST @BLAST_CU
32 Followers 147 Following Boulder Language and Social Technologies research group at @CUBoulder @BoulderNLP. Led by @ml_pacheco_Nodens @NodensKoren
50 Followers 197 Following Machine Learning Researcher & Computational Astrophysicist. Aspiring Pianist. Studying gravitational waves and the universe using ML @ETH @CSatETH 😃Xin Cynthia Chen @XinCynthiaChen
344 Followers 336 Following Direct PhD student @ETH_en, with research focus on AI Safety and Alignment. Formerly at @CHAI_Berkeley.NLLG @NL2GMannheim
83 Followers 101 Following Natural Language Learning Group University of Mannheim We do exist & we grow! Text generation, Evaluation, Digital Humanities, Social Science #NLProc #NLPhenrique is writing h.. @fromlonelyboy
151 Followers 742 Following sou um personagem não acabado do novo de baixo orçamento, o figurante nos livros da saga dos anos noventa e eu danço com baleias.Natalie Wynn @ContraPoints
606K Followers 2K Following Ex-philosopher, good YouTuber, bad Tweeter. Email: [email protected]Hamza Khwaja @hamza_khw
995 Followers 3K FollowingESSLLI @ESSLLI_official
670 Followers 0 Following This is the official Twitter account of the European Summer School in Logic, Language, and Information.Xinzi Hou 侯鑫子 @xinzi_hou
22 Followers 41 Following PhD student @UoYLangLing | tone & intonation, Chinese dialects, phonetics & phonology | 中文,English,粤语水平一般,ちょっと日本語。NCCR Evolving Languag.. @NCCR_Language
2K Followers 302 Following Exploring the past, present, and future of language 💬|🐵|🧠|📱 @unige_en @uzh_en @UniNeuchatel. Funded by @snsf_ch.Khanh Nguyen @khanhxuannguyen
1K Followers 457 Following Postdoc at CHAI Berkeley with Prof. Stuart Russell, Prev. Postdoc at Princeton NLP, PhD @umdcs, Human-AI Communication, Interactive Learning, NLP.Paul Alexander Butler @PaulAlexButler
403 Followers 1K Following Games & Nature & Mythology. Bones & Feathers. Owner of Games and Stuff @gamesandstuffmd Co-owner @freerpgday Co-creator of Overlight RPG. He/Him. Poly.Melanie Weber @mweber_PU
1K Followers 224 Following Assistant Professor at Harvard @hseas. Previously Hooke Research Fellow @OxUniMaths and PhD @Princeton. Studying Geometry and Machine Learning.Jay Cummings @LongFormMath
35K Followers 669 Following Math prof @SacState. Author of long-form textbooks on proofs (https://t.co/YqXnxDmOe0) & real analysis (https://t.co/3IGQ6BIx5Z). Math History book in late 2024Ehud Reiter @EhudReiter
2K Followers 87 Following I am a computer scientist who works on natural language generation and evaluation, often in healthcare contexts. I teach at Aberdeen University.antonio vergari 💥 .. @tetraduzione
4K Followers 1K Following human being | associate prof in #ML #AI @ancAtEd | PI of #APRIL https://t.co/7uTqRZtmEd | #probabilistic #models #tractable #generative #neuro #symbolic |Ryan Adams @ryan_p_adams
34K Followers 1K Following Machine Learning Researcher, CS Professor (@PrincetonCS), Dad, WoodworkerDie Linke @dieLinke
345K Followers 2K Following Kämpft für soziale Sicherheit, Frieden und Klimagerechtigkeit! Unsere Gruppe im Bundestag: @dielinkebt #dielinkeJonathan Clark @JonClarkSeattle
3K Followers 2K Following Research Scientist @ Google: Multilingual NLP, Machine Learning, C++. Previously MT@Microsoft and CMU. Opinions are my own.Sebastin Santy @SebastinSanty
948 Followers 824 Following PhD student at @uwcse. NLP x HCI. Often building interfaces, but also curious about social aspects of language.Michael Saxon @m2saxon
2K Followers 1K Following CS PhD cand @ucsbNLP 🌊🌴 @NSF GRFP 🧐analyzing semantics in generative lang/img AI models🤖 Big tech ex-intern. BS/MS @ASU 🌵🏜 Frequemt typos, critics welcomeNLPurr @NLPurr
1K Followers 759 Following SciComm of Academic NLP Papers | Research Scientist | Explainability, Prompting, Benchmarking, Metrics, Red-Teaming & Eval of LLMsXin Eric Wang @xwang_lk
7K Followers 1K Following Multimodal and Embodied AI Researcher / Professor @UCSC. Director of https://t.co/Y4swOBag21. AI for Humanity in the long run. he/himApril Wang @AprilWang95
2K Followers 545 Following Assistant professor @ETH Zurich; HCI, programming, educational technology, and more@kevdududu @vesteinns @niklas_stoehr @JenniferCWhite @AaronSchein @ryandcotterell i like the math color coding you guys are doing now
grateful to share this work with @vesteinns, @niklas_stoehr, @JenniferCWhite, @AaronSchein, @ryandcotterell! Paper: arxiv.org/abs/2404.04633 Code: github.com/kdu4108/measur…
What makes an entity susceptible? We show a relationship between the susceptibility score of an entity and BOTH frequency statistics in its training data AND degree in a knowledge graph. Also, as models get bigger, real entities are less susceptible than fake unknown ones (7/n)
finally, we showcase how these scores can be useful to model practitioners in two downstream applications–friend-enemy stance detection and analyzing gender biases in models. e.g., we find for those 2 questions, enemy duos are less susceptible than friend duos! (8/8)
and assertive contexts are relatively more persuasive to medium-sized models (2.8b) than smaller/larger ones, especially for yes-no questions (6/n)
So, what makes a context persuasive? Across 122 relations (e.g., alumniOf, capitalOf, highestPoint), we find some general patterns: being relevant to the queried entity is more important than being assertive for all model sizes (5/n)
We build a dataset of queries, entities, & contexts using 122 relations from a knowledge graph and use our measures to analyze model behavior (what kinds of contexts are more persuasive? what makes an entity susceptible?) across 6 model sizes in the Pythia suite (4/n)
An entity's *susceptibility score* says, in an info-theoretic sense, how much the model’s answer depends on context for that entity. It's the mutual information btwn answer & context, conditioned on the entity (and also the expected p-score over all contexts for the entity) (3/n)
To answer this, we introduce measures based on mutual information for the *persuasiveness* of a context and the *susceptibility* of an entity. Intuitively, a context's *persuasion score* is how much a model's answer distribution to a query changes when provided the context. (2/n)
LMs often need to integrate information from context and prior knowledge (e.g. for in-context learning, RAG, etc). But to judge how reliable LMs are at this, a first step is understanding *exactly how much does the LM depend on info given in-context vs its prior knowledge*? (1/n)
Paper: arxiv.org/abs/2404.04633 Code: github.com/kdu4108/measur…
How much does an LM depend on information provided in-context vs its prior knowledge? Check out how @vesteinns, @niklas_stoehr, @JenniferCWhite, @AaronSchein, @ryandcotterell + I answer this by measuring a *context's persuasiveness* and an *entity's susceptibility*🧵
@ryandcotterell thanks for writing it in the first place 💙
@srush_nlp @ryandcotterell Crazy that you're asking everyone to read lecture notes I *have* to read
@giaccoangelo @srush_nlp @ryandcotterell consider yourself lucky; the best attention explanation we get at @TU_Muenchen goes like this: V, Q, W where V is *a bunch of interesting things* sadly, i am not even exaggerating
Monograph on "Formal Aspects of Language Modeling" from @ryandcotterell et al. arxiv.org/abs/2311.04329 It would be so nice if everyone read this and we had shared foundations. Particularly for interpretability.
Honored to see my name among these amazing colleagues, @PsychScience Rising Stars! psychologicalscience.org/members/awards…
This is joint work with my great colleagues @OpedalAndreas Haruki Ying @ryandcotterell @bschoelkopf Abu @mrinmayasachan 📜Paper: arxiv.org/abs/2401.18070
New paper alert! We dive into the world of LLMs and cognitive biases, focusing on how models tackle arithmetic word problems—do they show the same biases as humans? Here’s a summary 🤖📚 #LLMs #MachineLearning #AI arxiv.org/abs/2401.18070
Slowly realizing that two days ago I successfully defended my PhD! 🤯 I’m extremely grateful to my supervisors, @IAugenstein and @ryandcotterell, my PhD committee, @SergeBelongie, @pascalefung, @licwu, and all of my colleagues and collaborators!
Massive congrats to @karstanczak for passing her PhD defence with flying colours! 🎊🥂🥳 Very proud of you 🤗🥹 Thanks to @SergeBelongie @pascalefung @licwu for serving on the committee. Karolina’s thesis on multilingual gender bias probing: di.ku.dk/english/resear… #NLProc