Top Tweets for #ModelEditing
Der Patch blieb erhalten, seine Wirkung verschwand: Was ein Gemma-Test über weitere Trainingsschritte zeigt. #KI #LLM #FineTuning #ModelEditing
Every detail matters! From model editing to smooth Live2D rigging, bringing virtual characters to life with expressive movements and natural animations.
DM for commissions!
#Live2D #VTuberRigging #ModelEditing #Live2DModel #VTuberCommissions
RFW
📍 Find us at ACL 2025 – Hall 5X, Poster #83
🌐 More details & resources: https://t.co/nqzLMmDxrt
See you there!
#ACL2025 #ModelEditing #KnowledgeEditing
🛑 Stop using teacher forcing to evaluate model editing!
Our ACL 2025 poster shows why past evaluations mislead progress & how to test editing in the wild.
📍 July 30, 11:00 AM – come chat!
#ModelEditing #LLM #ACL2025NLP
🛑 Stop using teacher forcing to evaluate model editing!
Our ACL 2025 poster shows why past evaluations mislead progress & how to test editing in the wild.
📍 July 30, 11:00 AM – come chat!
#ModelEditing #LLM #ACL2025NLP
🎉 Excited to share that our work "The Mirage of Model Editing" has been accepted as a main conference paper at #ACL2025! Many thanks to my supervisor @fei__sun, our collaborators, and special thanks to @HuaWenyue31539 for insightful discussions!
Thrilled to announce our paper has been accepted for an Oral Presentation at ACL 2025 (8% of accepted papers)! 🎉 https://t.co/MhdOtbEfy3
We dive deep into why current #LLM editing methods often fail robustness tests and propose a solution. #ACL2025 #LLMs #ModelEditing
1/X
😯To assess the real-world effectiveness of model editing techniques, we evaluated them on practical QA tasks and found that current editing methods perform substantially worse than previously reported (38.5% vs. 96%).
This is a systematic study on technical AGI safety and security.
Interpretability techniques like steering vectors and circuit analysis can help us understand and improve LLM safety—but they can also be misused. #Safety #ModelEditing #KnowledgeEditing #LLM #NLP
Excited to share @GoogleDeepMind's AGI safety and security strategy to tackle risks like misuse and misalignment. Rather than high-level principles, this 145-page paper outlines a concrete, defense-in-depth technical approach: proactively evaluating & restricting dangerous capabilities, implementing Amplified Oversight & robust training methods, all backed by system-level security.
#NAACL24 Come see the work of @domenic_rosati and David in the second interpretability session (11:00 am).
If you are not around, see the recording here:
#syntacticprobing: https://t.co/BCESyldnzQ
#modelediting: https://t.co/1vQBf1AuWO
We can better control, edit and regulate large language models.#NLP #AI #LLMs #KnowledgeEditing #ModelEditing
New Anthropic research paper: Scaling Monosemanticity.
The first ever detailed look inside a leading large language model.
Read the blog post here: https://t.co/6RYwxt6nWI
#KnowledgeEditing #NLP #LLMs #AI #ModelEditing The slides is available at:
https://t.co/WOHQEQ1sJA
More materials can be found at:
https://t.co/U4MXtTXSOX
https://t.co/6Ji6oR8wLU
The tutorial of Knowledge Editing for Large Language Models at LREC-COLING 2024 @LrecColing is in progress. #NLP #LLMs #KnowledgeEditing
🚀 Exciting update! EasyEdit now supports editing Mistral-7B.
You need manually update transformers==4.34.0🔄.
Plus, we have fixed some bugs in MEND evaluation, further refining performance. Stay ahead with the latest enhancements! #AI #EasyEdit #LLMs #NLP #ModelEditing #KnowledgeEditing
📌ArXiv: https://t.co/y3R9ivKB38
📌KnowEdit Benchmark: https://t.co/t1BJfGwlJS
📌ArXiv: https://t.co/yqAX1kPbOA
📌Paper List: https://t.co/wVD9WiBWIt
Can we update Knowledge Graph (KG) embeddings without re-training after deployment🤔. In our #AAAI24 paper, we propose a new task of editing language model-based KG embeddings with new benchmarks and baselines🤖📷🔪@RealAAAI. #NLP #LLM #ModelEditing #KnowledgeEditing #KnowledgeGraph
ArXiv:https://t.co/dmLVvmtTR6
Code:https://t.co/kIdIWeMe4y
HF Spaces:https://t.co/7wq2sbpa3z
Leaderboard:https://t.co/F1palpF2Ht
Curious about editing Large Language Models? Drop by our poster on "Can We Edit Multimodal Large Language Models?" at #EMNLP2023! @emnlpmeeting #NLP #LLM #ModelEditing #KnowledgeEditing
🗓️ Date: Dec 8th 🕚 Time: 16:00 📍 Location: East Foyer #34
📚 Dive into our research:
🔗 Paper: https://t.co/RIwhVANPp0
🔗 GitHub: https://t.co/yqAX1kPbOA
🚀Delighted to explore "Knowledge Editing for Large Language Models" at #AAAI24 alongside @zxlzr, @JasonForJoy, @yao_yunzhi, and @Bizhen_Ray. Immense gratitude to the organizers.
@RealAAAI
#Tutorial #NLP #LLM #ModelEditing
📚 Paper: https://t.co/0X7hfZ5HkN
Excited to chat about “Knowledge Editing for Large Language Models" at #AAAI24 in our tutorial with Jiachen Gu, Yunzhi Yao, Zhen Bi and Shumin Deng! Thanks a lot to the organizer. Dive deeper into the topic with resources on https://t.co/wVD9WiBWIt. @RealAAAI #LanguageModels #Tutorial #NLP #LLM #ModelEditing #KnowledgeEditing #EasyEdit #KnowLM
Related paper: https://t.co/iNBIiI6Tzy
Tools: https://t.co/yqAX1kPbOA
🚀 EasyEdit now supports efficient editing for #Baichuan2, #ChatGLM2, #InternLM, #Qwen. Plus, we've fixed some bugs for an even smoother experience! ✨ #Update #TechNews #NLP #ModelEditing #KnowledgeEditing #AI #LLMs #EasyEdit #KnowLM
Check it out: https://t.co/yqAX1kPbOA
🔥 Sneak peek: editing personality for LLMs is coming soon!
Our EasyEdit now supports editing multi-modal LLMs. Currently, you can edit MiniGPT-4 and Blip2. Check out the details here: https://t.co/rAJjQzp97m. Feel free to follow us for updates.
Related paper: https://t.co/RIwhVANPp0. 🚀📚 #EasyEdit #ModelEditing #KnowledgeEditing #MultiModal #MiniGPT4 #Blip2 #NLP #AI
#ReadingGroup at @lingoiitgn!
@HimanshuBeniwaI and @kndcse will be presenting on #LLM studio, #ModelEditing #toolkits, and different #Model #Editing #Techniques in our weekly reading group today. ✨
#ML #AI #NLProc #NLP
The research team includes @HimanshuBeniwaI, PhD student and PMRF Fellow, CSE, IITGN; @kndcse MTech student, CSE, and Prof @mayank_iitgn, Assistant Professor, CSE.
#IITGNResearchCapsules #ResearchCapsule #IITGNResearchers #ML #NLProc #ModelEditing
@EduMinOfIndia @PIB_India
Check out this new work by @dana_arad4 and @OrgadHadas on editing knowledge in text to image models.
#modelediting
Text-to-image models encode factual knowledge within their parameters, but what can we do if these facts are incorrect, or become outdated? ⏱️
We present ReFACT a method for editing factual knowledge in text-to-image models by editing the text encoder (1/5)
Check out our paper list on Model Editing over at https://t.co/jFI6IC8dek. Here's to shaping the future of large language models! #AI #ModelEditing #LargeLanguageModels
Trends for you
Most Popular Users
Elon Musk 
@elonmusk
241M followers
Barack Obama
@barackobama
118.8M followers
Cristiano Ronaldo
@cristiano
114.5M followers
Donald J. Trump
@realdonaldtrump
111.9M followers
Narendra Modi
@narendramodi
107M followers
Rihanna
@rihanna
98.7M followers
NASA
@nasa
92.2M followers
Justin Bieber
@justinbieber
91.8M followers
KATY PERRY
@katyperry
90M followers
Taylor Swift
@taylorswift13
84M followers
Lady Gaga
@ladygaga
75.5M followers
Virat Kohli
@imvkohli
73.4M followers
Kim Kardashian
@kimkardashian
70.8M followers
YouTube
@youtube
68.7M followers
Neymar Jr
@neymarjr
66.4M followers
Bill Gates
@billgates
65.2M followers
Selena Gomez
@selenagomez
63.1M followers
The Ellen Show
@theellenshow
62.2M followers
CNN
@cnn
61.7M followers
X
@x
60.6M followers