Workshop on Large Language Model Memorization @l2m2_workshop
The First Workshop on Large Language Model Memorization. sites.google.com/view/memorizat… World Joined September 2024-
Tweets23
-
Followers138
-
Following12
-
Likes36
L2M2 will be tomorrow at VIC, room 1.31-32! We hope you will join us for a day of invited talks, orals, and posters on LLM memorization. The full schedule and accepted papers are now on our website: sites.google.com/view/memorizat…
I'm psyched for my 2 *different* talks on Friday @aclmeeting: 1.@llm_sec (11:00): What does it mean for an AI agent to preserve privacy? 2.@l2m2_workshop (16:00): Emergent Misalignment thru the Lens of Non-verbatim Memorization (& phonetic to visual attacks!) Join us!
I'll be at #ACL2025 next week! Catch me at the poster sessions, eating sachertorte, schnitzel and speaking about distributional memorization at the @l2m2_workshop
L2M2 is happening this Friday in Vienna at @aclmeeting #ACL2025NLP! We look forward to the gathering of memorization researchers in the NLP community. Invited talks include: @yanaiela @niloofar_mire @rzshokri and see our website for the full program. sites.google.com/view/memorizat…
For years it’s been an open question — how much is a language model learning and synthesizing information, and how much is it just memorizing and reciting? Introducing OLMoTrace, a new feature in the Ai2 Playground that begins to shed some light. 🔦
Do language models just copy text they've seen before, or do they have generalizable abilities? ⬇️This new tool from Ai2 will be very useful for such questions! And allow me to plug our paper on this topic: We find that LLMs are mostly not copying! direct.mit.edu/tacl/article/d… 1/2
Do language models just copy text they've seen before, or do they have generalizable abilities? ⬇️This new tool from Ai2 will be very useful for such questions! And allow me to plug our paper on this topic: We find that LLMs are mostly not copying! direct.mit.edu/tacl/article/d… 1/2 https://t.co/18djjcx8MF
As infini-gram surpasses 500 million API calls, today we're announcing two exciting updates: 1. Infini-gram is now open-source under Apache 2.0! 2. We indexed the training data of OLMo 2 models. Now you can search in the training data of these strong, fully-open LLMs. 🧵 (1/4)
Hi all, reminder that our direct submission deadline is April 15th! We are co-located at ACL'25 and you can submit archival or non-archival. You can also submit work published elsewhere (non-archival) Hope to see your submission! sites.google.com/view/memorizat…
Want to know what training data has been memorized by models like GPT-4? We propose information-guided probes, a method to uncover memorization evidence in *completely black-box* models, without requiring access to 🙅♀️ Model weights 🙅♀️ Training data 🙅♀️ Token probabilities 🧵1/5
Adding or removing PII in LLM training can *unlock previously unextractable* info. Even if “John.Mccarthy” never reappears, enough Johns & Mccarthys during post-training can make it extractable later! New paper on PII memorization & n-gram overlaps: arxiv.org/abs/2502.15680
we show for the first time ever how to privacy audit LLM training. we give new SOTA methods that show how much models can memorize. by using our methods, you can know beforehand whether your model is going to memorize its training data, and how much, and when, and why! (1/n 🧵)
🎉 Happy to announce that the L2M2 workshop has been accepted at @aclmeeting! #NLProc #ACL2025 More details will follow soon. Stay tuned and spread the word! 📣
Mohammad Reza Ghasemi... @MoRezaMadani
72 Followers 179 Following PhD at @UniMelb | Former Researcher @UniTrento | Former MSc Student @UniBo | Former Visiting PGR Student @EdinburghUni | NLP, LLM.
Ece Takmaz @ecekt2
1K Followers 2K Following Postdoc at @UniUtrecht, previously PhD candidate at @UvA_Amsterdam
Ryuto Koike @sponddd
388 Followers 653 Following PhD-ing @sciencetokyo_en. Prev @Penn. Responsible AI.
Ahanaf Ariq @AhanafAriq
125 Followers 4K Following Deep Learning Theorist | Topological Data Analyst | IRPO 3rd | IYMC Bronze | Hessian Optimizer | Aspirant AI/ML Researcher
Ben Nassi @ben_nassi
1K Followers 4K Following 🇮🇱 | #BringThemHomeNow | 🎩 @BlackHatEvents Review Board | 🦄 @PwnieAwards x1 | AI Red Teaming | AI Security @BlackHatEvents Speaker x 6 |
paul @paul_okewunmi
1K Followers 4K Following ML/AI Engineer | MLH Fellow'23 @ Meta | Drone Hobbyist
Patrick Drake @time8machine
17K Followers 6K Following Neurodivergent physics student with a keen interest in multisensory integration and emergent perception. Exploring research on a proposed ‘sixth sense’. Δ
FedericoRanaldi @FedeRanaldi
87 Followers 164 Following Visiting PhD at @edinburghnlp | PhD Candidate in Data Science at @unitorvergata | NLP Researcher at @HumanCentricArt
Tomasz Limisiewicz @TomLimi
532 Followers 474 Following Postdoctoral researcher at @meta Fair and @uwnlp , Interested in going into the inner workings of neural networks, multilingualism, and fairer NLP (he/him)
p_h_c_g @phcg16021983
41 Followers 1K Following
Amir H. Kargaran @amir_nlp
799 Followers 3K Following On job maket (Fall 2025) / 🤖 PhD student @CisLmu/ 🛠️ Multilingual NLP / Previous: Intern @huggingface. My views!
Jaymari Chua @JaymariChua
70 Followers 777 Following generative AI safety research; ex-Amazon big data engineer
Anindya Das Antar @AntarAnindya
346 Followers 2K Following Ph.D. candidate, @UMichCSE, @umich_hcc_lab, @CompHCILab Interested in Human-centered behavior modeling, Interactive eXplainable AI (#HCXAI), User-AI alignment
Anubrata Das 🦋 @ N... @d_anubrata
679 Followers 2K Following Ph.D. Candidate @UTiSchool Thinking about Human-Centered NLP | #NLP + #HCI
Cui Ding @CuiDing_CL
57 Followers 108 Following
Zhaocong Yang @allen_yang8
546 Followers 4K Following CS PhD student @ UNCC Data Storytelling; Viz Recommendation; RAG; HCI
Andrea Santilli @teelinsan
836 Followers 2K Following Research Scientist in NLP & LLMs | Prev: @Apple, @NousResearch, @BigscienceW, @picampusschool #NLProc
Valentina Pyatkin @valentina__py
3K Followers 1K Following Postdoc at the Allen Institute for AI @allen_ai and @uwnlp
Pepa Atanasova @atanasovapepa
967 Followers 720 Following Tenure-Track Assistant Professor @DIKU_Institut @CopeNLU; interested in xAI, accountability, xAI diagnostics, mis-/disinformation
Sachit Malik @isachitmalik
167 Followers 4K Following Hola | Security Engineering at Apple | Alum: Carnegie Mellon; IIT Delhi
Arjun Chandra @boelger
600 Followers 859 Following Dad of 4. Founder and CEO @brua_io sculpting a socially responsible role for AI. Led large model training stability @graphcoreai. PhD in AI @uobcompsci (2011).
Arnav Goel @_goel_arnav
692 Followers 368 Following MSML @mldcmu | Pre-training, alignment and memorization | ex - @MSFTResearch, @nlp_usc, @Mila_Quebec, IBM | CSAI @IIITDelhi '25
Gauri@DHS2025 @geekytwoshoes
314 Followers 4K Following
rahul x @rahulme74418504
58 Followers 2K Following
Kerem Zaman @KeremZaman3
495 Followers 1K Following PhD student @unc_ai_group working on explainable, interpretable and safe AI systems | prev. BSc @UniBogazici | kal '18
Peter Carragher @PeterVCarragher
64 Followers 134 Following Societal Computing PhD student @S3DatCMU
Neha Srivastava @Neha04Sri
1 Followers 91 Following
Eva Louise Marie Gabr... @e681554349
11 Followers 7K Following
Diana 🐺 @devoidikk
425 Followers 2K Following She/her | 🇲🇽 sCHOLAr | ReseARCHER 🏹 at @cambridgenlp | Prev: @tohoku_nlp | Tweets mostly in Spanish about random stuff, and in English from time to time.
Ximena Gutiérrez @XimGutierrez
662 Followers 954 Following Computational linguist. Currently associate professor @ceiich_unam @UNAM_MX. Before I was a postdoc researcher @uzh_spur.
Alisha Srivastava @AlishaSrivas
33 Followers 135 Following Applied Science @solarialabs | Data Science @manningcics | President @umassproduct.
Gaurav Kumar @GAURAVk11967092
49 Followers 140 Following Senior Machine Learning Engineer @Moveworks AI. Working on search, ranking, and LLM based problems for enterprise.
Hedwig @enjoysomelife
3 Followers 92 Following
Jongwook Han @jwhansnu
11 Followers 113 Following PhD Student at @SeoulNatlUni Research interest: Value alignment in LLMs. Lab member of : https://t.co/OtCxOTbRLy
Buluchacha @YiboY42383
5 Followers 225 Following
Chau Minh Pham @chautmpham
467 Followers 457 Following PhD student @umdcs | Long-form Narrative Generation & Analysis | Intern @AdobeResearch @MSFTResearch
Vikas Raunak @vyraun
696 Followers 5K Following Senior Research Scientist @GoogleDeepMind. Working on Gemini.
Ilya Lasy @Misterion77
15 Followers 175 Following PhD Student @tu_wien Machine Learning Engineer. Geek & TTRPG Lover. Musician.
Taylor Sorensen @ma_tay_
791 Followers 483 Following CS PhD candidate @uwcse/@uwnlp, living at and visiting @Stanford/@stanfordnlp prev @byuacme, intern @GoogleDeepMind, @allen_ai he/him
Tiago Pimentel @tpimentelms
2K Followers 294 Following Postdoc at @ETH_en. Formerly, PhD student at @Cambridge_Uni.
MilaNLP @MilaNLProc
4K Followers 477 Following The Milan Natural Language Processing Group #NLProc #ML #AI
CambridgeNLP @cambridgenlp
9K Followers 199 Following The Natural Language Processing Group @Cambridge_Uni, Computer Science department #NLProc #ML. Account managed by @Eric_chamoun, @richarddm1, @pietro_lesci.
Johnny Tian-Zheng Wei @johntzwei
524 Followers 838 Following 🇺🇸🇨🇳 PhD student at USC. I'm interested in the legal issues of AI.
Pratyush Maini @pratyushmaini
3K Followers 468 Following Data Quality x Privacy | PhD @mldcmu | Founding Team @datologyai | BTech @iitdelhi
Yangsibo Huang @YangsiboHuang
4K Followers 703 Following research scientist @googledeepmind. gemini thinking & coding. phd @princeton. opinions are my own.
Verna Dankers @vernadankers
875 Followers 288 Following Postdoc @Mila_Quebec @McGill_NLP 🇨🇦 PhD in #NLProc from @Edin_CDT_NLP 🏴 interpretability x memorisation x (non-)compositionality. she/her
Robin Jia @robinomial
4K Followers 891 Following Assistant Professor @CSatUSC | Previously Visiting Researcher @facebookai | Stanford CS PhD @StanfordNLP
Pietro Lesci @pietro_lesci
718 Followers 2K Following Final-year PhD student @cambridge_uni. Causality & language models | ex @bainandcompany @ecb @amazonscience. Passionate musician, professional debugger.Trends for United States
You might like
