🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Thrilled to share that our NoLiMa paper has been accepted to ICML 2025! 🎉🎉🎉 Huge thanks to my amazing co-authors! #NLProc ICML Conference

Announcement: I have left this platform and moved to Bsky. I will no longer check messages here. Some exciting news are shared on Bsky. Find me there. Hope to see you there, too

Now accepted to #ACL2025 main conference! 🎉

Three papers accepted to ACL 2025🥰 On cross-lingual knowledge editing, probing, and multilingual interpretability🔍 Sincere thanks to all the amazing coauthors and supervisors! ❤️ Looking forward to meeting old friends and knowing new people soon in Vienna! 🇦🇹

🎉Excited to share our paper on cross-lingual inconsistency is accepted to #ACL2025 🇦🇹! We dissect why LLMs produce inconsistent outputs across languages using interpretability analysis, and propose a simple shortcut-based fix, evaluated on 17 languages. arxiv.org/abs/2504.04264

🚨 New paper accepted to #ACL2025! We present LangSAMP, a multilingual pretraining method that adds language + script embeddings after the Transformer block—right before the language modeling head. ✅ Boosts language neutrality ✅ Helps crosslingual transfer

Consider submitting your multilingual NLP work to the MELT workshop @ COLM 2025: melt-workshop.github.io Deadline: June 23

New paper: We investigate multilingual refusal mechanisms in LLMs and find that: The "refusal direction" - a single vector that controls whether models reject requests - is universal across languages. Paper: arxiv.org/abs/2505.17306 🧵 Co-lead with Mingyang Wang and Yihong Liu

New paper: How does pretraining on programming languages + English shape LLMs' concept space? 🔍Do LLMs use English or a programming language as a kind of pivot language? 🧠Are neurons language-specific or shared across programming languages and English? 🔗arxiv.org/abs/2506.01074

Life Update: I recently joined Google DeepMind to work on LLM agents and privacy.

I'll be on the job market in Fall 2025, looking for opportunities in research or applied NLP (postdoc or industry). If you think there’s a potential fit, I’d love to connect! Website: kargaranamir.github.io CV: drive.google.com/file/d/1IfQjXE… I'll also be attending ACL 2025.

I’ll be at ICML Conference next week presenting NoLiMa! Poster on Tue July 15, 4:30–7pm PDT (E-2312). Happy to grab a coffee and chat about long-context, memory, research, or just to catch up. I’ll be in Toronto for a couple of days after the conference, let me know if you’re around!

🎉 Our paper “Algorithmic Fidelity of LLMs in Generating Synthetic German Public Opinions” is accepted at #ACL2025 main conference as an oral presentation! 🇩🇪🤖 We study how well LLMs simulate real survey responses using open-ended German data, showing the left-leaning bias.

🚨 Can LLMs generate explanations that are as useful as human ones for modeling label distributions in NLI?🌹"A Rose by Any Other Name" shows that they can 💬 We explore scalable, explanation-based annotation via LLMs. 📍Come find us in Vienna 🇦🇹! (July 28, 18:00-19:30, Hall 4/5)

Happening now! East Exhibition Hall E-2312

🤔 Can LLMs read between the lines? Our another #ACL2025 paper surveys resources on how LLMs handle pragmatics like implicatures, deixis, and more. We map out a new landscape for both LLMs and linguistics in pragmatic research. 📄 arxiv.org/abs/2502.12378 🧠💬 #LLMs #Pragmatics

Leaving Vancouver after ICML’s closing fireworks 😁🎆 Heading to Toronto for a few days, then off to ACL 2025 to present: Collapse of Dense Retrievers A work by Mohsen Fayyaz that I was fortunate to collaborate on. Also co-presenting two other papers…🧵 [1/4]