Artem Shelmanov
@ArtemShelmanov
Research Scientist
I just met Caiqi Zhang – one of the users of our Python framework for uncertainty quantification, LM-Polygraph. It’s incredibly rewarding to see our work helping other researchers achieve outstanding results! LM-Polygraph: github.com/IINemo/lm-poly… #EMNLP2024 #Uncertainty #NLP
Wrapping up the second productive day of #EMNLP2024 with a social event at the Frost Museum of Science! #ACL #NLP #MBZUAI #MIAMI
#COLING2025 is over, it was incredible! It was an pleasure and honor to be part of the the great COLING organizational team. A massive shoutout to all our volunteers who made this event possible. Finally, a huge thanks to all participants, I hope you had a fantastic time!
The main #COLING2025 has just started! I am thrilled and honored to be part of the local organizing committee for such a prestigious and prominent NLP event. Experiencing and contributing to the event from behind the scenes has been an absolutely fascinating experience!
I planned a small tour around the MBZUAI campus for #COLING2025 participants, but it ended up attracting over 20 people! Thank you all for visiting and making it such a memorable event =) #COLING2025 #AbuDhabi #MBZUAI
Had an engaging visit to @mbzuai well planned and guided by @ArtemShelmanov. Unless someone is living in a cave, everyone knows all the exciting work coming out of this place esp in the LLM themes. Glad to finally see it in person 😇
Hosting the GenAIDetect workshop at COLING 2025! Kudos to Firoj Alam for leading the general organization and to Yuxia Wang for leading the preparation and presenting our Shared Task overview paper: github.com/mbzuai-nlp/COL… #COLING #AbuDhabi #COLING2025 #NLP
We are excited to announce Libra-Leaderboard: The first LLM leaderboard dedicated to balancing safety and capability in LLMs. As AI advances, ensuring its safety becomes more critical than ever. By prioritizing safety measurement, we aim to inspire the AI community to make safety…
NLProc enthusiasts! 🎉 Attending #COLING2025? Don’t miss the GenAI Workshop on January 19th! 🗓️✨ Join us for insightful keynote talks and engaging presentations. Secure your spot now and be part of the conversation! 🚀 #GenAI #AIWorkshop @COLING2025 #AI #ContentDetection…
I am having a pleasure to read a very nice uncertainty quantification survey with an interesting vision of current challenges: "A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions" arxiv.org/pdf/2412.05563
Honored to share that I and my great colleagues are organizing a tutorial on "Uncertainty Quantification for LLMs" at #ACL2025! Artem Shelmanov, Maxim Panov, Ekaterina Sergeevna Fadeeva, Artem Vazhentsev, Roman Konstantinovich Vashurin and Timothy Baldwin.
Our paper has been accepted to 𝐓𝐀𝐂𝐋! Benchmarking Uncertainty Quantification Methods for Large Language Models arxiv.org/pdf/2406.15627 It introduces LM-Polygraph - a benchmark for uncertainty quantification and hallucination detection in LLMs. github.com/IINemo/lm-poly…
On the final day of #EMNLP2024, at the MRL workshop, we presented the work on Vikhr -- state-of-the-art LLM for Russian: Paper: aclanthology.org/2024.mrl-1.15/ Model: huggingface.co/Vikhrmodels/Vi… Github: github.com/VikhrModels/ef… Huge kudos to Alexandr Nikolich, who couldn’t attend in person!
