UW NLP @uwnlp
The NLP group at the University of Washington. Seattle, WA Joined September 2015-
Tweets1K
-
Followers11K
-
Following160
-
Likes903
The question below is pretty easy for humans. Why can't GPT-4 get it right? In our new preprint we introduce "time series reasoning" and show that modern language models are surprisingly bad at interpreting these critical data. arxiv.org/abs/2404.11757
The infini-gram paper is updated with the incredible feedback from the online community 🧡 We added references to papers of @JeffDean @yeewhye @EhsanShareghi @EdwardRaffML et al. arxiv.org/abs/2401.17377 Also happy to share that the infini-gram API has served 30 million queries!
When augmented with retrieval, LMs sometimes overlook retrieved docs and hallucinate 🤖💭 To make LMs trust evidence more and hallucinate less, we introduce Context-Aware Decoding: a decoding algorithm improving LM's focus on input contexts 📖 arxiv.org/pdf/2305.14739… #NAACL2024
🤔How can we align AI systems/LLMs 🤖 to better represent diverse human values and perspectives?💡🌍 We outline a roadmap to pluralistic alignment with concrete definitions for how AI systems and benchmarks can be pluralistic! arxiv.org/abs/2402.05070 First, models can be…
Helping people practice key skills in situations that are/feel realistic is one of the coolest, most appropriate applications of LMs, IMO. Check out our new work (captained by the intrepid @iwylin) on helping people communicate effectively in challenging interpersonal convos!
Helping people practice key skills in situations that are/feel realistic is one of the coolest, most appropriate applications of LMs, IMO. Check out our new work (captained by the intrepid @iwylin) on helping people communicate effectively in challenging interpersonal convos!
Ever find yourself delaying a conversation because you're nervous about how it might go?😩 We developed IMBUE, an #LLM-backed tool, to help you improve #communication skills and manage #emotions, through simulation and just-in-time feedback. Paper🔗: arxiv.org/pdf/2402.12556…
Big milestone! Welcome Dolma to infini-gram 📖, now available on our web interface and API endpoint. This brings the total size of the infini-gram indexes to 5 trillion tokens and about 5 quadrillion (5 x 10^15) unique n-grams. It is the largest n-gram LM ever built, both by the…
When you use ChatGPT, do you notice that it has a data cutoff date? 🗓️ But as models are pretrained on web text originating from many historical periods, do they have a sense that they should use their latest knowledge to answer questions rather than historical info? Excited to…
[Fun w/ infini-gram 📖 #6] Have you ever taken a close look at Llama-2’s vocabulary? 🧐 I used infini-gram to plot the empirical frequency of all tokens in the Llama-2 vocabulary. Here’s what I learned (and more Qs raised): 1. While Llama-2 uses a BPE tokenizer, the tokens are…
Do next-word predictors capture sentence meaning? 🧙♂️ We show that they do, as reflected in their assigned sentence cooccurrence probabilities. LMs are sensitive to entailment, assigning different prob. to sentences entailed by context vs not arxiv.org/abs/2402.13956
Do next-word predictors capture sentence meaning? 🧙♂️ We show that they do, as reflected in their assigned sentence cooccurrence probabilities. LMs are sensitive to entailment, assigning different prob. to sentences entailed by context vs not arxiv.org/abs/2402.13956
📢 Preprint: We can predict entailment relations from LM sentence co-occurrence prob. scores These results suggest predicting sentence co-occurrence may be one way that next-word prediction leads to (partial) semantic representations in LMs🧵
[Fun w/ infini-gram 📖 #5] What does RedPajama say about Letter Frequency? Image shows the letter distribution. Seems that there’s a lot less letter “h” in RedPajama than expected (using Wikipedia page as gold reference: en.wikipedia.org/wiki/Letter_fr…). Thoughts? 🤔 (I issued a single…
Excited to share that Sotopia (openreview.net/forum?id=mM7Vu…) has been accepted to ICLR 2024 as a spotlight 🌠! Sotopia is one of the unique platforms for facilitating socially-aware and human-centered AI systems. We've been busy at work, and have follow-ups coming soon, stay tuned!
The infini-gram API has served over 1 million queries during its first week of release! Thanks everyone for powering your research with our tools 🤠 Also, infini-gram now supports two additional corpora: the training sets of C4 and Pile, both in the demo and via the API. This…
The infini-gram API has served over 1 million queries during its first week of release! Thanks everyone for powering your research with our tools 🤠 Also, infini-gram now supports two additional corpora: the training sets of C4 and Pile, both in the demo and via the API. This…
Announcing the infini-gram API 🚀🚀 API Endpoint: api.infini-gram.io API Documentation: infini-gram.io/api_doc No API key needed! Simply issue POST requests to the endpoint and receive the results in a fraction of a second. As we’re in the early stage of rollout, please… pic.x.com/ckwsxijpjf
[Fun w/ infini-gram #3] Today we’re tracing down the cause of memorization traps 🪤 Memorization trap is a type of prompt where memorization of common text can elicit undesirable behavior. For example, when the prompt is “Write a sentence about challenging common beliefs: What…
Thanks for featuring our work @_akhaliq!! 😍 Super excited to announce the infini-gram engine that counts long n-grams and retrieve documents within TB-scale text corpora, with millisecond-level latency. Look forward to enabling more scrutiny into what LLMs are being trained on.…
Thanks for featuring our work @_akhaliq!! 😍 Super excited to announce the infini-gram engine that counts long n-grams and retrieve documents within TB-scale text corpora, with millisecond-level latency. Look forward to enabling more scrutiny into what LLMs are being trained on.…
The infini-gram engine just got 10x faster! 🚀🚀🚀 Try infini-gram here: hf.co/spaces/liujch1… To experience faster inference, select the “C++” engine before submitting your query. On RedPajama (1.4T tokens), the C++ engine can process count queries in 20 milliseconds on…
It’s year 2024, and n-gram LMs are making a comeback!! We develop infini-gram, an engine that efficiently processes n-gram queries with unbounded n and trillion-token corpora. It takes merely 20 milliseconds to count the frequency of an arbitrarily long n-gram in RedPajama (1.4T…
[Fun w/ infini-gram #2] Today we're verifying Benford's Law! Benford's Law states that in real-life numerical datasets, the leading digit should follow a certain distribution (left fig). It has usage in detecting fraud in accounting, election data, and macroeconomic data. The…
(((ل()(ل() 'yoav))).. @yoavgo
46K Followers 2K FollowingPercy Liang @percyliang
49K Followers 408 Following Associate Professor in computer science @Stanford @StanfordHAI @StanfordCRFM @StanfordAILab @stanfordnlp | cofounder @togethercompute | PianistSasha Rush @srush_nlp
51K Followers 463 Following Professor, Programmer in NYC. Cornell Tech, Hugging Face 🤗 https://t.co/cZl0wTfqGzGraham Neubig @gneubig
30K Followers 582 Following Associate professor at CMU, studying natural language processing and machine learning.Akari Asai @AkariAsai
11K Followers 650 Following Ph.D. student @uwcse & @uwnlp. NLP. IBM Ph.D. fellow (2022-2023). Meta student researcher (2023-) . ☕️ 🐕 🏃♀️🧗♀️🍳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.Delip 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 🌈Kyunghyun 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).William Wang @WilliamWangNLP
14K Followers 715 Following UCSB NLP Lab + ML Center. https://t.co/6TOnqbk6YT https://t.co/KJYhnav3Et Mellichamp Chair Prof. at UCSB CS. PhD @ CMU SCS. Areas: #NLProc, Machine Learning, AI.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/2A3qF5vdJwTal Linzen @tallinzen
16K Followers 894 Following Professor @nyuling and @NYUDataScience, research scientist @GoogleAIDanish Pruthi @danish037
6K Followers 627 Following Faculty at Indian Institute of Science, Bangalore. PhD from @LTIatCMU.Ana Marasović @anmarasovic
4K Followers 602 Following Asst prof @UUtah · Ex @allen_ai @uwnlp postdoc @HD_NLP PhD · she/her 🇭🇷Bill Yuchen Lin 🤖 @billyuchenlin
6K Followers 2K Following Research @allen_ai. I evaluate (multi-modal) LLMs, build agents, and study the science of LLMs. Previously: @GoogleAI & @MetaAI FAIR @nlp_uscAllen Institute for A.. @allen_ai
53K Followers 361 Following AI for the Common Good. › Join us: https://t.co/DqTs1G4bGO › Get our newsletter: https://t.co/tvb1VpySfLMark Dredze @mdredze
4K Followers 786 Following John C Malone Professor at @JohnsHopkins @JHUCompSci @jhuclsp @jhumceh; Part time @techatbloomberg (tweets my own) Mastodon @[email protected]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.Tim Dettmers @Tim_Dettmers
28K Followers 819 Following PhD Student at @UW. I blog about deep learning and PhD life at https://t.co/Y78KDJJFE7.Mike A. Merrill @Mike_A_Merrill
85 Followers 102 Following PhD Student @uwnlp @uwcse AI for time series and health prev. @GoogleAI @Apple @health_rhythms @CornellMikaStars★ @MikaStars39_
166 Followers 596 Following Second year B.A. / B.S. in @ZJU_China Prev: Bsc in @Polytechnique Devoted in LLM Architecture & InterpretabilityOum Ritchy @JusticeRitchy
765 Followers 7K Following #bible #catholic #évangile #john 8:58 Jésus leur dit: En vérité, en vérité, je vous le dis, avant qu'Abraham fût, je suis #injil #islam isn't #apocalypsejohnliujie @CoolWind6j
2 Followers 36 FollowingSong Yifan @gooffanita
11 Followers 36 Following ling student @UniofOxford; interested in language, speech, gender and tech.Chen Zheng @chenzheng_nlp
14 Followers 92 Following Research Scientist at Bytedance. Ph.D. at Michigan State University. Natural Language Processing boy. Ex-intern Baidu, JD Inc.Anish Acharya @AnishAc10645870
68 Followers 278 Following PhD UT Austin || ex Applied Scientist Amazon Alexa AI || Research interns at Meta, MSR ; TTIC || Researcher in ML Theory, NLP, Optimization,Etash Guha @etash_guha
62 Followers 155 Following Researcher @SambaNovaAI, ML Researcher at @RIKEN_JP Undergrad @GeorgiaTechTamil_03 @muthamilk2001
78 Followers 324 FollowingAlo @Hal90910
0 Followers 792 FollowingHung Chia Yu @hungchiayu123
19 Followers 87 Following Undergraduate student at @sutdsg. NLP ResearchPeter Yao @PeterYao10
6 Followers 253 FollowingLydia Nishimwe @LydiaNishimwe
88 Followers 194 Following PhD student in Neural Machine Translation @inria_paris ... just observing, don't mind me... 👀Zhuang Liu @liuzhuang1234
3K Followers 913 Following Research Scientist @MetaAI (FAIR, at NYC). machine learning, computer vision, neural networks. PhD from @Berkeley_EECSkenankortan @kenankorta55495
0 Followers 14 FollowingRahul Gupta @rahul1987iit
56 Followers 144 Following Responsible AI, Sr. Manager @ Amazon Views are my ownYan @asdasszy
5 Followers 109 FollowingMark R. Hinkle @mrhinkle
7K Followers 5K Following I help enterprises understand and use artificial intelligence. Leveraging my 25 years of enterprise software experience in emerging technology to drive results.Nicholas Lourie @NickLourie
117 Followers 178 Following I build things. 🤖 Doing a PhD at @nyuniversity (@CILVRatNYU) on better empirical methods for deep learning and data science. Advised by @kchonyc and @hhexiy.crystalWen @JackLiuWen
24 Followers 490 Following文博 @lidoyu
5 Followers 327 FollowingAlexis Trujillo @_AlexisTrujillo
289 Followers 2K Following AI enthusiast, Storyteller, Data Vizz, Next Data Analyst 🇲🇽 | AI | Chips🔬 | LLMs |Nearshoring 📈|Tableau | 💚@Platzi StudentWei-Rui Chen @WeiRuiChen01
50 Followers 83 Following PhD candidate and NLP researcher focusing on Multilingual NLP @UBC | @UBC_NLP | @UBCLangScisShahzaib S. Warraich @shahzaib_saqib1
35 Followers 219 Following Aitchisonian | Fulbrighter | Tech Entrepreneur | AI/ML Research Engineer | Tech/Econ Columnistdjhardcore007 @djhardcore007
68 Followers 491 FollowingHowieHwong @HowieH36226
1 Followers 71 FollowingSamuel Pyang @SamuelPyang23
111 Followers 397 FollowingKarl @tomatoxuhs
33 Followers 441 Followingvisoc @visoc25
0 Followers 19 FollowingYingjian Fu @yingjianfu
12 Followers 389 FollowingAadirupa Saha @AadirupaSaha
405 Followers 77 Following Research Interests: Machine Learning - Bandits, Reinforcement Learning, Optimization, Fairness, Privacy.Phung Cheng Fei @salmon_shitake
427 Followers 5K FollowingBatbout Al ba7it @notLagControl
232 Followers 603 Following I do not require a companion in my crusade of contempt.kanika kalra @KalraKanika23
4 Followers 211 FollowingChitranjan @chitranjanjain1
196 Followers 3K Following Investing in SaaS, devtools, cybersecurity, and AI @accel | Prev @manmatters_in | @cred_club | @BITSPilaniIndiaJunxi Yan @Yan_Junxi
2 Followers 21 FollowingShiqi Lou @lou_shiqi60535
8 Followers 100 FollowingShivam Mittal @shivammittal77
9 Followers 123 FollowingRasika Muralidharan @RasikaMuralidh1
100 Followers 412 FollowingOCHIENG ADIKA🅾️ @onexpeters12
80 Followers 225 Following(((ل()(ل() 'yoav))).. @yoavgo
46K Followers 2K FollowingPercy Liang @percyliang
49K Followers 408 Following Associate Professor in computer science @Stanford @StanfordHAI @StanfordCRFM @StanfordAILab @stanfordnlp | cofounder @togethercompute | PianistSasha Rush @srush_nlp
51K Followers 463 Following Professor, Programmer in NYC. Cornell Tech, Hugging Face 🤗 https://t.co/cZl0wTfqGzGraham Neubig @gneubig
30K Followers 582 Following Associate professor at CMU, studying natural language processing and machine learning.Akari Asai @AkariAsai
11K Followers 650 Following Ph.D. student @uwcse & @uwnlp. NLP. IBM Ph.D. fellow (2022-2023). Meta student researcher (2023-) . ☕️ 🐕 🏃♀️🧗♀️🍳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.Kyunghyun 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).Yoav 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/f9QkzO5kaCWilliam Wang @WilliamWangNLP
14K Followers 715 Following UCSB NLP Lab + ML Center. https://t.co/6TOnqbk6YT https://t.co/KJYhnav3Et Mellichamp Chair Prof. at UCSB CS. PhD @ CMU SCS. Areas: #NLProc, Machine Learning, AI.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/2A3qF5vdJwTal Linzen @tallinzen
16K Followers 894 Following Professor @nyuling and @NYUDataScience, research scientist @GoogleAIAna Marasović @anmarasovic
4K Followers 602 Following Asst prof @UUtah · Ex @allen_ai @uwnlp postdoc @HD_NLP PhD · she/her 🇭🇷Bill Yuchen Lin 🤖 @billyuchenlin
6K Followers 2K Following Research @allen_ai. I evaluate (multi-modal) LLMs, build agents, and study the science of LLMs. Previously: @GoogleAI & @MetaAI FAIR @nlp_uscAllen Institute for A.. @allen_ai
53K Followers 361 Following AI for the Common Good. › Join us: https://t.co/DqTs1G4bGO › Get our newsletter: https://t.co/tvb1VpySfLTim Dettmers @Tim_Dettmers
28K Followers 819 Following PhD Student at @UW. I blog about deep learning and PhD life at https://t.co/Y78KDJJFE7.Sebastian Ruder @seb_ruder
80K Followers 1K Following Multilingual LLMs @cohere • Prev: @GoogleDeepMind • Newsletter: https://t.co/7JGh2qpG98Ofir Press @OfirPress
9K Followers 3K Following I build tough benchmarks for LMs and then I get the LMs to solve them. Postdoc @Princeton. PhD from @nlpnoah @UW. Ex-visiting researcher @MetaAI & @MosaicML.Christopher Potts @ChrisGPotts
11K Followers 620 Following Stanford Professor of Linguistics and, by courtesy, of Computer Science, and member of @stanfordnlp and @StanfordAILab. He/Him/His.Chris Rytting @ChrisRytting
423 Followers 462 Following Postdoc @UWCSE w/ @timalthoff. PhD in CS/NLP from @BYU. Formerly @nvidia, OSPC @AEI, @NewYorkFed Macroeconomic Research.Valentina Pyatkin @valentina__py
2K Followers 1K Following Postdoc at the Allen Institute for AI @allen_ai and @uwnlpYaron Lipman @lipmanya
3K Followers 397 Following Faculty at @WeizmannScience, research scientist @MetaAI (FAIR). Interested in deep learning of irregular/geometric data and generative models.🎗️Yangsibo Huang @YangsiboHuang
1K Followers 726 Following PhD candidate @Princeton. Prev: @GoogleAI @AIatMeta.Xiang Yue @xiangyue96
2K Followers 422 Following Postdoc @LTIatCMU. PhD from Ohio State @osunlp. Training & evaluating foundation models. Pushing the boundaries of AI🤖. Previously @MSFTResearch.Joel Jang @jang_yoel
931 Followers 477 Following PhD student @uwcse. Research Intern at @nvidiaai robotics. Prev: @allen_aiPrithviraj (Raj) Amma.. @rajammanabrolu
5K Followers 517 Following Interactive & grounded AI, RL, NLP. Assistant Prof @UCSanDiego. Research Scientist @DbrxMosaicAI. Prev: @allen_ai, @GeorgiaTechSarah Wiegreffe @sarahwiegreffe
4K Followers 983 Following At @allen_ai @ai2_aristo @uwnlp. Research in language model transparency & interpretability. PhD from @mlatgt @icatgt @gtcomputing. Views my own.Hamish Ivison @hamishivi
488 Followers 595 Following Antipodean Abroad. he/him. I (try to) do NLP research. PhD student @uwcse, prev @Sydney_Uni @allen_ai 🇦🇺🇨🇦🇬🇧Joongwon Kim @danieljwkim
207 Followers 267 Following PhD student @uwcse @uwnlp | Former undergrad @Penn | #NLProcIz Beltagy @i_beltagy
2K Followers 422 Following Cofounder @SpiffyAI, Research Lead building OLMo at @allenai_org, formerly @UTCompSci PhD.Shangbin Feng @shangbinfeng
1K Followers 1K Following PhD student @uwcse @uwnlp. Understanding and expanding the knowledge abilities of LMs, social NLP, networks and structures. he/him. #水文学家Xiaochuang Han @XiaochuangHan
445 Followers 683 Following PhD student at the University of WashingtonTal August @tal_august
557 Followers 189 Following Incoming assistant professor @IllinoisCS Fall 2024, current postdoc @allen_ai, former PhD student @uwcse. HCI + NLP. Designing language for different people.Edvin LZ @eduniw
439 Followers 2K Following PhD student in decentralized deep learning at @RISEsweden and @KTHuniversity. Previously a visiting researcher at @NYUDataScienceArtidoro Pagnoni @ArtidoroPagnoni
799 Followers 425 Following PhD student in NLP at UW with Luke ZettlemoyerGPT-4/ChatGPT/GPT-3@R.. @realtimeqa
186 Followers 7 Following How well can GPT-3 answer your real-time questions? Examples from RealTime QA, a weekly-updated QA benchmark. Managed by @jungokasai and @KeisukeS_ .Reza Salehi @mrezasal1
138 Followers 1K Following PhD Student @uwcse & @uwnlp working on multimodal learning | ex. AIML intern @AppleTao Yu @taoyds
3K Followers 814 Following @XLangNLP lab, asst. prof. @HKUniversity. prev. postdoc @uwnlp; phd @Yale; intern @MSFTResearch, @SFResearch. he/him 🌈Yushi Hu @huyushi98
1K Followers 1K Following 🎓PhD student @uwnlp | Researcher @allen_ai Prev. @GoogleAI @UChicago @TTIC_Connect | NLP/CV/AI 📖🎹🪗📷⚽️Inna Lin @iwylin
700 Followers 911 Following 林琬音✨PhD Student @UWCSE 👩💻💭 I’m interested in human-centered NLP and ML for health and social good!Hila Gonen @hila_gonen
1K Followers 229 Following Postdoctoral Researcher at @UWNLP https://t.co/2cDfMi1JtpDaniel Fried @dan_fried
3K Followers 797 Following Assistant prof. @LTIatCMU @SCSatCMU, working on NLP: language interfaces, applied pragmatics, language-to-code, grounding. 🐘: @[email protected]Melanie Sclar @melaniesclar
2K Followers 412 Following PhD student @uwnlp @uwcse | Visiting Researcher @MetaAI FAIR Labs | Prev. Lead ML Engineer @asapp, intern @LTIatCMU | 🇦🇷tsvetshop @tsvetshop
797 Followers 131 Following Group account for Prof. Yulia Tsvetkov's lab at @uwnlp. We work on low-resource, multilingual, social-oriented NLP. Details on our website:Jiacheng Liu (Gary) @liujc1998
976 Followers 186 Following 🎓 PhD student @uwcse @uwnlp. 🛩 Private pilot. Previously: 🧑💻 @oculus, 🎓 @IllinoisCS. 📖 🥾 🚴♂️ 🎵 ♠️Oreva Ahia @orevaahia
1K Followers 968 Following PhD student @uwcse | ex: AI/ML Research Intern @apple | Co-organizer @AISaturdayLagos | Researcher @MasakhaneNLPDeng Cai @deng_cai
354 Followers 165 Following Research Scientist at Tencent AI Lab working on LLM. previously PhD student at CUHK working on NLP.Liwei Jiang @liweijianglw
2K Followers 451 Following 姜力炜 • Ph.D. student @uwnlp 💻 student researcher @allen_ai 🧊 advance AI & understand humans 📖 lifetime adventurerSherry Tongshuang Wu @tongshuangwu
4K Followers 1K Following Assist. Prof @SCSatCMU , CS PhD @uwcse. HCI+AI, map general-purpose models to specific use cases! prev. intern @MSFTResearch @GoogleAI @Apple. She/her.Gabriel Ilharco @gabriel_ilharco
4K Followers 1K Following Building cool things @xAI. Prev. PhD at UW, Google AISean Welleck @wellecks
3K Followers 222 Following Assistant Professor at CMU. Marathoner, @thesisreview.Saadia Gabriel @GabrielSaadia
701 Followers 135 Following MIT Postdoc, incoming NYU Faculty Fellow and UCLA Assistant Professor. In her free time, interested in generation and ethics of AI.Phillip Keung @phillipk999
143 Followers 28 Following NLP researcher and machine learning scientist at Amazon. UW PhD student.WAIL: ML at UW @uw_wail
800 Followers 300 Following Machine learning at @uwcse! We're the Washington AI Lab (WAIL).Weijia Shi @WeijiaShi2
5K Followers 963 Following PhD student @uwcse @uwnlp | Visiting Researcher @MetaAI | Undergrad @CS_UCLA | https://t.co/eLBQmgkvymMargaret Li @neurips .. @margs_li
792 Followers 120 Following 👩💻 PhD student @UWCSE / @UWNLP & @MetaAI. Formerly RE @FacebookAI Research, @Penn CS | 🏂💃🧋🥯 certified bi-coastal bb ♥️ IAH/PEK/PHL/NYC/SFO/SEAAshish Sharma @sharma_ashish_2
780 Followers 758 Following PhD Student @UWCSE | Natural Language Processing | Computational Social Science | Previously @MSFTResearch @IITKGPTim Althoff @timalthoff
4K Followers 2K Following Assistant Professor @UWCSE developing computational methods that leverage large-scale behavioral data to improve human well-being. Recruiting PhD students :-)Sachin @sacmehtauw
471 Followers 75 Following AI/ML Research Scientist at Apple and Affiliate Assistant Professor at the University of Washington, Seattle. Opinions are my own.The infini-gram paper is updated with the incredible feedback from the online community 🧡 We added references to papers of @JeffDean @yeewhye @EhsanShareghi @EdwardRaffML et al. arxiv.org/abs/2401.17377 Also happy to share that the infini-gram API has served 30 million queries!
You can now download & run SWE-agent (on any GitHub issue) in 1 line! Check our repo for deets: github.com/princeton-nlp/… Join our Discord to hear first about updates like this: discord.gg/AVEFbBn2rH
SWE-agent is blazing fast, and when it works it feels like magic! In this short demo I show how it solved a real bug in the neural network training code in scikit-learn. I also explain the process behind our agent-computer interface design choices.
SWE-Agent is an open-source software engineering agent with a 12.3% resolve rate on SWE-Bench! Check out SWE-agent in action at swe-agent.com Repo: github.com/princeton-nlp/…
When augmented with retrieval, LMs sometimes overlook retrieved docs and hallucinate 🤖💭 To make LMs trust evidence more and hallucinate less, we introduce Context-Aware Decoding: a decoding algorithm improving LM's focus on input contexts 📖 arxiv.org/pdf/2305.14739… #NAACL2024
Check out our work on "extracting distinguishing dialectal features via interpretable dialect classifiers" led by the amazing @ruoyuxyz ! Accepted to #NAACL2024
✨ Can we use interpretability methods to extract linguistic features that characterize dialects❓ 🎉 New preprint: arxiv.org/abs/2402.17914 (@ruoyuxyz, @orevaahia, @tsvetshop, @anas_ant) 👉Code & Data: github.com/ruoyuxie/inter… 🧵(1/6)
We're super happy to see people use our SWEbench.com benchmark to evaluate their coding agents!
Today we're excited to introduce Devin, the first AI software engineer. Devin is the new state-of-the-art on the SWE-Bench coding benchmark, has successfully passed practical engineering interviews from leading AI companies, and has even completed real jobs on Upwork. Devin is…
Figuring out which topic to work on is probably the most challenging task for deep learning researchers these days. I wrote a blog post to give you some ideas. Read it here: ofir.io/Tips-for-Findi…
🤔How can we align AI systems/LLMs 🤖 to better represent diverse human values and perspectives?💡🌍 We outline a roadmap to pluralistic alignment with concrete definitions for how AI systems and benchmarks can be pluralistic! arxiv.org/abs/2402.05070 First, models can be…
Helping people practice key skills in situations that are/feel realistic is one of the coolest, most appropriate applications of LMs, IMO. Check out our new work (captained by the intrepid @iwylin) on helping people communicate effectively in challenging interpersonal convos!
Ever find yourself delaying a conversation because you're nervous about how it might go?😩 We developed IMBUE, an #LLM-backed tool, to help you improve #communication skills and manage #emotions, through simulation and just-in-time feedback. Paper🔗: arxiv.org/pdf/2402.12556…
Big milestone! Welcome Dolma to infini-gram 📖, now available on our web interface and API endpoint. This brings the total size of the infini-gram indexes to 5 trillion tokens and about 5 quadrillion (5 x 10^15) unique n-grams. It is the largest n-gram LM ever built, both by the…
Can LLMs like #ChatGPT help us navigate challenging communication situations? 📢 Introducing ✨IMBUE✨, an LLM-based training system that helps people improve interpersonal effectiveness skills🧠 and manage negative emotions 💖
Ever find yourself delaying a conversation because you're nervous about how it might go?😩 We developed IMBUE, an #LLM-backed tool, to help you improve #communication skills and manage #emotions, through simulation and just-in-time feedback. Paper🔗: arxiv.org/pdf/2402.12556…
💜This is a joint work with an amazing team of researchers @sharma_ashish_2 @ChrisRytting @timalthoff at @uwnlp @uwcse, Jina Suh @Microsoft @MSFTResearch, and @electrotipe @Stanford. 10/10!! 🙌
Ever find yourself delaying a conversation because you're nervous about how it might go?😩 We developed IMBUE, an #LLM-backed tool, to help you improve #communication skills and manage #emotions, through simulation and just-in-time feedback. Paper🔗: arxiv.org/pdf/2402.12556…
When you use ChatGPT, do you notice that it has a data cutoff date? 🗓️ But as models are pretrained on web text originating from many historical periods, do they have a sense that they should use their latest knowledge to answer questions rather than historical info? Excited to…
[Fun w/ infini-gram 📖 #6] Have you ever taken a close look at Llama-2’s vocabulary? 🧐 I used infini-gram to plot the empirical frequency of all tokens in the Llama-2 vocabulary. Here’s what I learned (and more Qs raised): 1. While Llama-2 uses a BPE tokenizer, the tokens are…
[Fun w/ infini-gram 📖 #5] What does RedPajama say about Letter Frequency? Image shows the letter distribution. Seems that there’s a lot less letter “h” in RedPajama than expected (using Wikipedia page as gold reference: en.wikipedia.org/wiki/Letter_fr…). Thoughts? 🤔 (I issued a single…
Excited to share that Sotopia (openreview.net/forum?id=mM7Vu…) has been accepted to ICLR 2024 as a spotlight 🌠! Sotopia is one of the unique platforms for facilitating socially-aware and human-centered AI systems. We've been busy at work, and have follow-ups coming soon, stay tuned!
The infini-gram API has served over 1 million queries during its first week of release! Thanks everyone for powering your research with our tools 🤠 Also, infini-gram now supports two additional corpora: the training sets of C4 and Pile, both in the demo and via the API. This…
Announcing the infini-gram API 🚀🚀 API Endpoint: api.infini-gram.io API Documentation: infini-gram.io/api_doc No API key needed! Simply issue POST requests to the endpoint and receive the results in a fraction of a second. As we’re in the early stage of rollout, please… pic.x.com/ckwsxijpjf