iiinova — where your digital self keeps evolving

Amir Hossein Kargaran @kargaranamir.bsky.social · 05/06/2025

Are you working on multilingual, multicultural #LLM? Interested in diverse & inclusive language modeling? 😎 Stay tuned at our MELT workshop at #COLM2025 🔗 melt-workshop.github.io We welcome 2p (EA), 4p (short), 8p (long) papers as well as talented reviewers: 🔗 forms.gle/MYcXED7RLJDS...

melt-workshop.github.io

MELT Workshop @ COLM 2025

010

Amir Hossein Kargaran @kargaranamir.bsky.social · 03/06/2025

We observe both similarities and differences in how LLMs represent natural languages versus prgramming langauges.

100

Amir Hossein Kargaran @kargaranamir.bsky.social · 03/06/2025

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

161

Amir Hossein Kargaran @kargaranamir.bsky.social · 13/12/2024

Thanks to everyone who stopped by at our work! I’ll be at the conference until the closing night and would love to meet and connect with more people. Feel free to DM me here or on the Whova app.

010

Amir Hossein Kargaran @kargaranamir.bsky.social · 01/12/2024

🇨🇦 I'll be in Montreal December 4–8, then Vancouver for NeurIPS to present our work on pretraining data for minority languages (arxiv.org/abs/2410.23825). Looking forward to reconnecting and meeting new people. DM me if you want to meet in the upcoming days! :)

arxiv.org

GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages

The need for large text corpora has increased with the advent of pretrained language models and, in particular, the discovery of scaling laws for these models. Most available corpora have sufficient d...

001