I had a great time at #EMNLP2023 and am now at #NeurIPS23. I am very excited to meet new people. Feel free to DM to meet up and say 👋. I will be presenting Attention Lens (arxiv.org/abs/2310.16270) as a a poster at the Attributing Model Behavior at Scale workshop on Friday!

✨Trillion Parameter Models in Science✨ We present an initial vision for a shared ecosystem to take the next step in large language models for scientific research – Trillion Parameter Models (TPMs). #LLM are becoming more powerful by the day. But, there is still work done to

Interested in understanding how #LLM s work, why they often fail to reason, and how to improve performance? One tool to boost multi-hop reasoning is with targeted memory injections. This improves desired token probability by up to 424%! 🎥 Watch the talk by Mansi Sakarvadia now:

Mansi Sakarvadia presented her Master's thesis on "Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models". Watch the recording here: youtube.com/watch?v=4EE9DI…

🎉 I successfully defended my Master's dissertation in the area of interpretable Language Modeling! Check out my work's applications in better understanding multi-hop reasoning, bias localization, and malicious prompt detection in my talk: youtube.com/watch?v=4EE9DI…

Jordan Pettyjohn, Nathaniel Hudson, Mansi Sakarvadia, Aswathy Ajith, and Kyle Chard just published new work demonstrating detoxification strategies on Language Model outputs at BlackboxNLP! ""Mind Your Manners: Detoxifying Language Models via Attention Head Intervention" Congrats All!

Language models can memorize sensitive data! 🔒 Our new research by the team (Mansi Sakarvadia, Nathaniel Hudson, and others) with TinyMem shows unlearning methods like BalancedSubnet effectively mitigate memorization while keeping performance high. #AI #Privacy mansisak.com/memorization/

Excited to share our latest work: "SoK: On Finding Common Ground in Loss Landscapes Using Deep Model Merging Techniques"! 🧠 arxiv.org/abs/2410.12927 By Arham Khan, Todd Nief, Nathaniel Hudson, Mansi Sakarvadia, Daniel Grzenda, Aswathy Ajith, Jordan Pettyjohn, Kyle Chard, and Ian Foster.

Towards Interpreting Language Models: A Case Study in Multi-Hop Reasoning paper: arxiv.org/abs/2411.05037 This method improves multi-hop reasoning in language models by injecting “memories” into key attention heads, increasing accuracy in complex tasks. An open-source tool,

Congrats to Jordan for winning 1st place at SC24 student poster competition! It was super fun to mentor him this summer on his project "Mind Your Manners: Detoxifying Language Models via Attention Head Intervention".

Reflecting on my 2024 PhD journey: passed my qualifying exam, spent the summer at Berkeley, mentored undergrad students, and tackled the fast pace of AI/ML research. It’s been a year of milestones and growth! Read more here: mansisak.com/blog/2025/year… #PhDJourney #AIResearch

Check out a recent interview in which I discuss the recent Nobel Prizes and some thoughts on the impact on both the domain sciences and ML communities.

"Without long-term, foundational, and high-risk federal research investments, the seeds of innovation cannot take root," Rebecca Willett and Henry Hoffman write in a new commentary piece. trib.al/YHfsWNP