Akari Asai @AkariAsai
Ph.D. student @uwcse & @uwnlp. NLP. IBM Ph.D. fellow (2022-2023). Meta student researcher (2023-) . ☕️ 🐕 🏃♀️🧗♀️🍳 akariasai.github.io Seattle, WA Joined December 2017-
Tweets1K
-
Followers11K
-
Following648
-
Likes7K
Llama 3 70B in LLMLean! Suggests proofs or next steps that are checked in Lean Try it out with a @togethercompute API key: github.com/cmu-l3/llmlean
How to enjoy the best of both worlds of efficient training (less communication and computation) and inference (constant KV-cache)? We introduce a new efficient architecture for long-context modeling – Megalodon that supports unlimited context length. In a controlled head-to-head…
📢 Excited to share that we will organize the 3rd workshop on Knowledge-Augmented NLP at ACL 2024. We will have six amazing speakers! We welcome your submissions and invite you to discuss with our speakers and organizers at the workshop. Looking forward to seeing you in Thailand!
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!
Version II of the tutorial on neural theorem proving: github.com/cmu-l3/ntptuto… Some new additions - Train a model that gets 29.5% on miniF2F - Data extraction in Lean, based on lean-training-data - LLMLean tool (github.com/cmu-l3/llmlean)
Version II of the tutorial on neural theorem proving: github.com/cmu-l3/ntptuto… Some new additions - Train a model that gets 29.5% on miniF2F - Data extraction in Lean, based on lean-training-data - LLMLean tool (github.com/cmu-l3/llmlean) https://t.co/Nm6DtxEHZ4
We hosted an NSF workshop on Open-Source Generative AI last week at Cornell Tech that brought together practitioners and academics in this area. 🧵of really interesting talks. Ludwig Schmidt - Open Source AI for Multimodality. youtube.com/watch?v=c1vMvU…
Learn how to build Self-RAG from Scratch 🛠️ We’re excited to feature a cool blog post by Florian June showcasing how to build dynamic RAG with reflection baked in - completely from scratch! 1️⃣ Run retrieval only when a “[retrieval]” token is generated 2️⃣ After retrieval, do…
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
RAG is all the RAGe these days, but we (still) don't quite know how to evaluate it properly... This year, we are taking a stab at it in the context of TREC, building on 30+ years of experience in evaluating IR systems. trec-rag.github.io
Search is more than just a single query: users have complex information needs! Sadly, most LLMs in information retrieval are not designed to work with rich instruction, and only support short, keyword-heavy queries 😭 We introduce benchmark & model for instruction-based…
Search is more than just a single query: users have complex information needs! Sadly, most LLMs in information retrieval are not designed to work with rich instruction, and only support short, keyword-heavy queries 😭 We introduce benchmark & model for instruction-based…
🌟Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision 🌟 arxiv.org/abs/2403.09472 How can we keep improving AI systems when their capabilities surpass those of human supervisors? (1/n)
Tools can empower LMs to solve many tasks. But what are tools anyway? github.com/zorazrw/awesom… Our survey studies tools for LLM agents w/ –A formal def. of tools –Methods/scenarios to use&make tools –Issues in testbeds and eval metrics –Empirical analysis of cost-gain trade-off
RAG 2.0 is about making retrieval-augmented generation more end-to-end & learned, e.g. Self-RAG, RA-DIT, GRIT - High-impact research direction imo! 😊
RAG 2.0 is about making retrieval-augmented generation more end-to-end & learned, e.g. Self-RAG, RA-DIT, GRIT - High-impact research direction imo! 😊
Checkout our #EACL2024 paper: "Smaller LMs are Better Machine-Generated Text Detectors", where we compare ALL models of different sizes against each other and show GPT2-small (120M) can detect ChatGPT generations better than a 7B GPTNeo model! arxiv.org/abs/2305.09859
Happy to share REPLUG🔌 is accepted to #NAACL2024 Introduce a retrieval-augmented LM framework that combines a frozen LM with a frozen/tunable retriever. Improving GPT-3 in language modeling & downstream tasks by prepending retrieved docs to LM inputs arxiv.org/abs/2301.12652
Now accepted to NAACL 2024 ❤️ Excited to present this in Mexico City and continue building upon this work🎊
Now accepted to NAACL 2024 ❤️ Excited to present this in Mexico City and continue building upon this work🎊
It is currently PhD visit days at UW. Choosing among schools for a PhD is a tough choice. I wrote a blog post about some ways to think about this choice to make it easier and to find the school that is the best fit for you: timdettmers.com/2022/03/13/how…
Reliable, Adaptable, and Attributable Language Models with Retrieval Argues that retrieval-augmented language models can be more reliable and adaptable than traditional parametric models, and proposes a roadmap for their advancement. 📝arxiv.org/abs/2403.03187
Graham Neubig @gneubig
31K Followers 586 Following Associate professor at CMU, studying natural language processing and machine learning.Kayo Yin @kayo_yin
8K Followers 556 Following PhD student @berkeley_ai @berkeleynlp working on interpretability and signed languages. Former @msftresearch @deepmind @carnegiemellon @polytechnique. 🇫🇷🇯🇵Tim Dettmers @Tim_Dettmers
29K Followers 819 Following PhD Student at @UW. I blog about deep learning and PhD life at https://t.co/Y78KDJJFE7.Kyunghyun Cho @kchonyc
61K Followers 2K Following a combination of a mediocre scientist, a mediocre manager, a mediocre advisor & a mediocre PC at @nyuniversity (@CILVRatNYU) & @genentech (@PrescientDesign).Ofir Press @OfirPress
10K 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.William Wang @WilliamWangNLP
14K Followers 716 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.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_uscWenhu Chen @WenhuChen
11K Followers 520 Following AI researcher @UWaterloo @GoogleAI @VectorInst. Interested in natural language processing, diffusion models. I direct TIGER-Lab at UWaterloo.Yao Fu @Francis_YAO_
14K Followers 2K Following PhD @EdinburghNLP on LLMs and Machine Reasoning. Ex. @Columbia @PKU1898 @MITIBMLab @allen_ai AGI has yet to come, so keep runningWeijia Shi @WeijiaShi2
5K Followers 967 Following PhD student @uwcse @uwnlp | Visiting Researcher @MetaAI | Undergrad @CS_UCLA | https://t.co/eLBQmgkvymLuca Soldaini 🎀 @soldni
6K Followers 1K Following I like tokens! Lead for OLMo data team at @allen_ai (makin Dolma 🍇), open source science fan, @QueerInAI organizer 🤖☕️🍕they/themAna Marasović @anmarasovic
4K Followers 604 Following Asst prof @UUtah · Ex @allen_ai @uwnlp postdoc @HD_NLP PhD · she/her 🇭🇷Yu Su @ysu_nlp
6K Followers 857 Following Dist. Assist. Prof.@OhioState, Director @osunlp, 20% Researcher@Microsoft. I like to think about intelligence, artificial or biologicalColin Raffel @colinraffel
30K Followers 654 Following nonbayesian parameterics, sweet lessons, and random birds. Friend of @srush_nlpGabriel Ilharco @gabriel_ilharco
4K Followers 1K Following Building cool things @xAI. Prev. PhD at UW, Google AITakami Sato @tkm2261
10K Followers 829 Following ML Security Researcher / Kaggle Grandmaster / CS Ph.D. candidate at UC Irvine / I will be in the job market this Fall. Please feel free to contact me via DMMr.Li 李先生 @FelixLee2022
11 Followers 105 Following Shenzhen,China. Business travel in USA. Mobile phone/ tablet/ IOT etc.Amit Kumar Singh Yada.. @Aksy01021999
183 Followers 721 Following he/him | ECE PhD candidate at Purdue University, VIPER Lab | Director Medalist, BTech- IIT Gandhinagar | Ex @Enphase | Ex-Rakuten ResearchCRUD Baby @vermontbrooklyn
124 Followers 3K Following Apprentice Software BioMancer. Aspirational Machinic NeoPlatonist || Segui il tuo corso, e lascia dire le genti. || v/accGautham @ALongDeadStar
346 Followers 2K Following A tiny speck of star dust suspended in an infinite cosmos 💫🪐coasting_nc @coasting_
66 Followers 235 FollowingElectronicsseeker @libertarian108
7 Followers 912 Followingacidoom @acidoom
102 Followers 964 FollowingNir Peled @_nir_peled
74 Followers 313 Following𝕫𝕙𝕖 @_zhecui
1 Followers 1K FollowingKarthik Chandramouli @pujalords
2K Followers 4K Following Hoop 🏀 Dad, Investor, Startup Advisor @bookendai @mhubchicago #StarTrek 🖖🏽 #Lean ex-Toyota Motorola @Harvard @Kennedy_School @UofL Krishna Take The WheelS_Tsui @STsui4
0 Followers 395 Followingandres pesti @andrespestip
303 Followers 5K Followingdev potatopotato @devpotatopotato
1 Followers 136 Following CS student in Seoul National University. Passionate about AGI.Nikita @nikitavoloboev
4K Followers 6K Following Make @LearnAnything_ Learn in public: https://t.co/GbFvuErkYn macOS course: https://t.co/JdbJWru6zG https://t.co/94R8ER7K2h https://t.co/ROkqhyhpEKZhiyong Wang @Zhiyong16403503
381 Followers 2K Following Visiting Ph.D. student at Cornell University. Ph.D. candidate at CUHK. Working on bandits and reinforcement learning theory.elon musk4045 @DavidLu30868261
37 Followers 736 Following... @dercrazypug
61 Followers 145 FollowingShinto @shinto_ai
323 Followers 581 Following Hokkaido Univ. M1 / Field : AI, ALIFE, CogSci / CHAIN 5期生 / Intern at Araya / JSAI2024, JCSS2024 発表予定Yin-Hong Cao @caoyinhong
117 Followers 1K Following Postdoc in Jiayang Li Lab, Institute of Genetics and Developmental Biology, CAS. Focus on the Multi-omics of dandelions & rice🌱🌾Recruiting Top-Tier Talents👇Quarkstar @Quarkstar9
16 Followers 107 Followingryan zhang @whiskyzj
51 Followers 1K FollowingHarsh Maheshwari @HarshMheshwari
1K Followers 1K Following Enthusiastic about #GenerativeAI #DataScience 🤖 | Constantly curious learner 🌱 | Applied scientist 2 at @amazon | Writer at @medium | @IITKGP Graduatehuzaifa jawad @huzaifajaw25291
2 Followers 71 FollowingArhant Chaterjee @ArhantC69420
106 Followers 832 FollowingAgamdeep Singh @agammessi10
44 Followers 724 Following Trying to make a business out of RAG and training a foundational pose comparison model @ MOON lab, IISERB.Falalu Ibrahim Lawan @falalu247
100 Followers 1K Following Educator, STEM ambassador, mentor, passionate about learning and codingYao Tang @tyao923
17 Followers 189 Following Undergrad @SJTU1986 CS, working on RL & Decision MakingWilliam Li @Williamiumli
18 Followers 139 Following Incoming Ph.D. student @UCSanDiego, M.S.E. in CS @JohnsHopkins, B.S. in CS at SCUTSimon Batzner @simonbatzner
4K Followers 690 Following RS at Google DeepMind. Prev: Harvard, MIT, NASA, Google Brain.รักที่ไ.. @03Lv1I1Ma5cp5L
66 Followers 1K Following ความเซ็กซี่มีมากกว่าหนึ่งด้าน ติดตามฉันและค้นพบช่วงเวลาอื่นๆ ที่จะทำให้หัวใจคุณเต้นเร็วขึ้น! หน้าแรกของข้อมูลการติดต่อจะได้รับการอัปเดตตลอดเวลาSimon Dobnik @SimonDobnik
119 Followers 287 Following Professor at University of Gothenburg, Sweden. NLP researcher and lecturer.Ji-An Li @Ji_An_Li
159 Followers 689 Following NGP student at UCSD | Computational neuroscience | Neural networks | Marcelo Mattar Lab | Marcus Benna LabQingyang Xu @MiaoXingWuZhu94
1 Followers 27 FollowingVashisth @brownian_boy
94 Followers 269 FollowingFrank M @FrankM1075638
6 Followers 71 Followingsamanhappy @sunmeng72135695
43 Followers 183 Following A seasoned software engineer with a strong focus on backend development. Passionate about open source, sharing knowledge, and solving problems.William Berrios @w33lliam
446 Followers 1K Following Technical staff @ContextualAI. Past: collaborator @huggingface, @Artificio_Org @MIT_CBMM, @evl_uic. 🦙 Engineer @UNIoficial 🇵🇪Vishal Sivala @m74v8zctbs
0 Followers 107 Followingabderrahim zine @abderrahimzine6
25 Followers 594 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 | PianistYi Tay @YiTayML
29K Followers 97 Following chief scientist / cofounder @RekaAILabs 🫠 past: research scientist @google brain 🤯 currently learning to be a dad 🍼Graham Neubig @gneubig
31K Followers 586 Following Associate professor at CMU, studying natural language processing and machine learning.Kayo Yin @kayo_yin
8K Followers 556 Following PhD student @berkeley_ai @berkeleynlp working on interpretability and signed languages. Former @msftresearch @deepmind @carnegiemellon @polytechnique. 🇫🇷🇯🇵Sasha Rush @srush_nlp
52K Followers 464 Following Professor, Programmer in NYC. Cornell Tech, Hugging Face 🤗 https://t.co/cZl0wTfqGzTim Dettmers @Tim_Dettmers
29K Followers 819 Following PhD Student at @UW. I blog about deep learning and PhD life at https://t.co/Y78KDJJFE7.Kyunghyun Cho @kchonyc
61K 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/f9QkzO5kaCSam 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.Christopher Manning @chrmanning
126K Followers 115 Following Director, @StanfordAILab. Assoc. Director, @StanfordHAI. Founder, @stanfordnlp. Prof. CS & Linguistics, @Stanford. IP @aixventureshq. 🇦🇺 Do #NLProc & #AI. 👋Ofir Press @OfirPress
10K 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.Jia-Bin Huang @jbhuang0604
51K Followers 285 Following Associate Professor @umdcs; Part-time Research Scientist @Meta. I like pixels.William Wang @WilliamWangNLP
14K Followers 716 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.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_uscWenhu Chen @WenhuChen
11K Followers 520 Following AI researcher @UWaterloo @GoogleAI @VectorInst. Interested in natural language processing, diffusion models. I direct TIGER-Lab at UWaterloo.Jacob Andreas @jacobandreas
14K Followers 958 Following Teaching computers to read. Assoc. prof @MITEECS / @MIT_CSAIL (he/him). https://t.co/5kCnXHjtlY https://t.co/2A3qF5vdJwZhiqing Sun @EdwardSun0909
2K Followers 1K Following CS PhD @LTIatCMU working on scalable alignment. BS @PKU1898BAY AREA STATE OF MIN.. @YayAreaNews
35K Followers 0 Following 🎥 Independent Media | Follow & Hit The 🔔Mausam (IITD) @mishumausam
3K Followers 55 Following Founding Head, Yardi School of Artificial Intelligence at IIT Delhi. AI (NLP, ML, MDP) Researcher. Indian Classical Music aficionado.Hamish Ivison @hamishivi
475 Followers 596 Following Antipodean Abroad. he/him. I (try to) do NLP research. PhD student @uwcse, prev @Sydney_Uni @allen_ai 🇦🇺🇨🇦🇬🇧Ruibo Liu @RuiboLiu
2K Followers 1K Following Research Scientist @GoogleDeepMind. AI Research with Humans in Mind.Sohee Yang @soheeyang_
1K Followers 427 Following PhD student/research scientist intern at @ucl_nlp/@GoogleDeepMind (50/50 split). Previously MS at @kaist_ai and research engineer at Naver Clova. #NLProc & MLSaining Xie @sainingxie
14K Followers 1K Following researcher in #deeplearning #computervision | assistant professor at @NYU_Courant @nyuniversity | previous: research scientist @metaai (FAIR) @UCSanDiegoWAVLab | @CarnegieMel.. @WavLab
2K Followers 113 Following Shinji Watanabe's Audio and Voice Lab | WAVLab @LTIatCMU @SCSatCMU | Speech Recognition, Speech Enhancement, Spoken Language Understanding, and more.DeepSeek @deepseek_ai
4K Followers 0 Following Unravel the mystery of AGI with curiosity. Answer the essential question with long-termism.Yangsibo Huang @YangsiboHuang
1K Followers 726 Following PhD candidate @Princeton. Prev: @GoogleAI @AIatMeta.Aashish Yadavally | �.. @IAmAYadavally
91 Followers 277 Following PhD Student at @UT_Dallas, with a research focus on “learning-guided program analysis”, and other AI4SE problems I find intriguing.Vidhisha Balachandran @vidhisha_b
519 Followers 490 Following Senior Researcher @MSFTResearch, PhD from @LTIatCMU, Ex-Intern @allen_ai, @GoogleAI | NLP/AI | she/herjack morris @jxmnop
10K Followers 760 Following getting my phd in nlp @cornell_tech 🚠 // academic optimist // tweeting from the snack aisle at trader joesTaco Cohen @TacoCohen
21K Followers 3K Following Deep learner at FAIR. Into codegen, equivariance, generative models. Spent time at Qualcomm, Scyfer (acquired), UvA, Deepmind, OpenAI.Abhika Mishra @mishrabhika
32 Followers 14 FollowingJames Bradbury @jekbradbury
11K Followers 8K Following Compute at @AnthropicAI! Previously JAX, TPUs, and LLMs at Google, MetaMind/@SFResearch, @Stanford Linguistics, @Caixin.Nathan Lambert @natolambert
25K Followers 689 Following Figuring out AI @allen_ai, "rl boi" DM me papers. Writes @interconnectsai, talks @retortai Has phd and some credentialsAlbert Jiang @AlbertQJiang
2K Followers 407 Following AI4Maths @Cambridge_CL Science @MistralAI I bake my own opinions at temperature=2.0David Bau @davidbau
3K Followers 241 Following Computer Science Professor at Northeastern, Ex-Googler. Believes AI should be transparent. @[email protected] @davidbau.bsky.social https://t.co/wmP5LUZRTwFuzhao Xue @XueFz
4K Followers 542 Following Ph.D. candidate@NUSingapore, Intern of GEAR @NVIDIA | Google PhD Fellow | LLM, Foundation Model Scaling | Ex-@GoogleBrain | Zero-shot Cooking Learner🧑🍳Yue Dong @ NeurIPS 20.. @YueDongCS
3K Followers 797 Following Assistant Prof @UCRiverside. PhD from @Mila_Quebec @McGillU. Trustworthy NLP+AI safety & Summarization! Former intern @GoogleAI @MSFTResearch @allen_aiNiklas Muennighoff @Muennighoff
5K Followers 323 Following @ContextualAI | Interests: AI/LLM Research & Health ❤️ | Past: @huggingface @PKU1898Yijia Shao @EchoShao8899
2K Followers 280 Following CS Ph.D. student @StanfordNLP. Previous: undergraduate @PKU1898.Zora Zhiruo Wang @ZhiruoW
528 Followers 183 Following PhD student @LTIatCMU | previously: intern @Amazon Alexa AI | assistant researcher @Microsoft Research, Asia | intern @TencentMBZUAI @mbzuai
12K Followers 308 Following Official account of Mohamed bin Zayed University of Artificial Intelligence. Dedicated to research, innovation, and empowering brilliant minds in AI.Xinya Du @Xinya16
812 Followers 433 Following Assistant Professor of CS, at UT Dallas; Cornell CS PhD. #NLProc #DLCharlie Snell @sea_snell
4K Followers 5K Following PhD @berkeley_ai & student researcher @GoogleDeepMind. My friend told me to tweet more. I stare at my computer a lot and make thingsLinjie (Lindsey) Li @LINJIEFUN
2K Followers 295 Following researching @Microsoft, @UW, contributing to https://t.co/a3zper7NJGJerry Liu @jerryjliu0
44K Followers 1K Following co-founder/CEO @llama_index Careers: https://t.co/EUnMNmbCtx Enterprise: https://t.co/Ht5jwxSrQBTom Sawada @tsawada_ml
348 Followers 229 Following ML @ GaTech (PhD), EleutherAI. Prev: Co-founder@TheDuckAI, UChicago Math BS/MS '21. 日本語 DMs Open.Tak @RealtyPnw
32K Followers 1K Following 米国で金融屋しています 不動産、債券よりの証券、保険なんでもします 英語: @realtypnw_en ツイートは投資や税務の勧誘及びアドバイスには相当いたしませんOri Yoran @OriYoran
272 Followers 299 Following CS NLP researcher / P.hD candidate (Tel-Aviv University)Hamed Zamani @HamedZamani
3K Followers 1K Following Asst. Prof. @manningcics. Assoc. Director of the Center for Intelligent Information Retrieval (CIIR). Ex-Researcher at Microsoft. Interested in IR, RecSys & ML.Hailey Schoelkopf @haileysch__
3K Followers 812 Following she/her | research scientist @aiEleuther | LLM training/infra, eval, data | LM Evaluation Harness maintainerBen Bogin @ben_bogin
629 Followers 421 Following CS PhD student at Tel-Aviv University, studying #NLProc. https://t.co/LPRm6GDjvtSaadia Gabriel @GabrielSaadia
704 Followers 135 Following MIT Postdoc, incoming NYU Faculty Fellow and UCLA Assistant Professor. In her free time, interested in generation and ethics of AI.Shuyan Zhou @shuyanzhxyc
2K Followers 594 Following Ph.D. student @LTIatCMU working on agents | she/theyMichael 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 🌵🏜 🔜 @AMD opensrc GenAI RS internZhaofeng Wu @zhaofeng_wu
1K Followers 171 Following PhD student @MIT_CSAIL | Previously @ai2_allennlp | MS'21 BS'19 BA'19 @uwnlpGreat to have Noah Smith @nlpnoah talk at Georgia Tech today about open-source LLMs trained with open-source pre-training data (OLMo model by @allen_ai) for the Distinguished Speaker Series. photo credit: Nathan Deen @ICatGT host: @kartik_goyal_
🏅Our #CHI2024 paper received an Honorable Mention Award!!🏅 We examine HIV clients' views on data security & privacy for electronic and mobile data collection in Malawi. Very thankful for my mentors and the collaboration that made this work happen✨ arxiv.org/pdf/2404.04444
I brought Jordan Almonds to the ultrasound so I could have some after and celebrate if all was well haha
@jxmnop @orionweller @srchvrs @n0riskn0r3ward @spacemanidol @memray0 @Quantum_Stat @bo_wangbo Imo GritLM works well for training pure embedding/retrieval models at SoTA level with DDP, bf16, gradcache, accelerate etc (github.com/ContextualAI/g…)
Some personal updates: I joined OpenAI a few months ago, working on all things robustness/safety/privacy. Also, we are working to publish more of our safety work. See my first project here below, where we make initial progress on prompt injections and other attacks!
Introducing the Instruction Hierarchy, our latest safety research to advance robustness for prompt injections and other ways of tricking LLMs into executing unsafe actions. More details: arxiv.org/abs/2404.13208
Corrective RAG == retrieval with reflection 🔎🪞 A way to make RAG more advanced is to expand the decision making capabilities in the middle of the RAG process. - Pre-retrieval: use the LLM to do query decomposition, API parameter inference, etc. - Post-retrieval (as shown…
A way to fix bad retrieval issues in RAG is to add a “reflection” layer on the retrieved context 💡 Corrective RAG (CRAG, Yan et al.) adds a retrieval eval module that categorizes gathered information into “Correct”, “Incorrect”, and “Ambiguous”. In the event that context is…
LLM Assistant for navigating the settings/control panel/etc. of OSes and apps would actually be killer. I am so tired of googling for ten minutes when I want to know how to change the volume of notifications.
Due to massive improvements in LLM quality over the last few years, evaluating these models reliably and accurately is difficult. One of the most popular evaluation strategies is LLM-as-a-judge, which uses GPT-4 to evaluate model quality... Automatic metrics: Previously,…
STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases Presents a large-scale benchmark for evaluating retrieval systems on semi-structured knowledge bases. 📝arxiv.org/abs/2404.13207 👨🏽💻github.com/snap-stanford/…
Create a benchmark for RAG models where all of the questions require information from multiple documents to be synthesized answer them. Study how models trained on publicly released data do on it and stratify analysis based on how much of the required info is in the training data
[CL] AutoCrawler: A Progressive Understanding Web Agent for Web Crawler Generation W Huang, C Peng, Z Li, J Liang, Y Xiao, L Wen, Z Chen [Fudan University] (2024) arxiv.org/abs/2404.12753 - Web automation is important for enhancing operational efficiency, but traditional methods…
Please find below our poster for @LrecColing 2024. We are talking about open knowledge graphs like @wikidata and how they can be useful for #NLProc and other fields. Paper: arxiv.org/abs/2306.13186 Video: youtube.com/watch?v=yw6rzb… #Open @Wikimedia @WikiResearch #Bibliometrics.
Got some photos from @genlawcenter at DC, where I talked about Differential privacy, what it is and what it’s not! Talk slides: homes.cs.washington.edu/~niloofar/talk…
I will be talking about what differential privacy is, what it is not and what some common misconceptions are in privacy for generative AI in a couple hours @genlawcenter in DC! Join us on the live stream: tinyurl.com/genlaw-stream Slides: tinyurl.com/genlaw-dp-2024
[CL] Measuring Cross-lingual Transfer in Bytes arxiv.org/abs/2404.08191 - Recent research suggests monolingual models also have cross-lingual transfer capability, but the mechanisms remain unclear. This paper investigates this using byte-level tokenization and measuring…
We have just released 🍷 FineWeb: 15 trillion tokens of high quality web data. We filtered and deduplicated all CommonCrawl between 2013 and 2024. Models trained on FineWeb outperform RefinedWeb, C4, DolmaV1.6, The Pile and SlimPajama!
[CL] Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment arxiv.org/abs/2404.12318 - Cross-lingual reward model (RM) transfer is proposed to align language models (LMs) in a target language using a RM trained in a source language. This allows…
Today's (April 19) CIIR Talk at 1:30 PM EDT: Piecing the Puzzle: Language Models for Multi-Document Contexts by @armancohan from @YaleCompsci It will be livestreamed. Learn more here: ciir.cs.umass.edu/node/742
arxiv.org/abs/2404.11792 Real-Reasoning RAG, or Where to Get Performance Gains Out of RAG (from @aitomatic & @IBMResearch, #AIAlliance): • Fine-tuning the retriever model gives you more bang for your buck than the generator model. • Employing reasoning yields significant…
I’m concerned about GenAI and misinformation. I tried Meta AI: I asked about a translation in Fon, it 💯 got it wrong. I asked about a fictional character, it made up an identity w/ a period of existence & a permanent position at the UN lol. It’s alarming - It got my name tho :)