Elisa Tsai

Cats all over the world form a 🐈 routing system❕CSE@Umich: Web Security, GenAI Application, Efficient ML

[Elisa Tsai @MustbeElisa]

ml conf review’s so broken…

[Yiping Lu @2prime_PKU]

Anyone knows adam?

[Elisa Tsai @MustbeElisa]

I did some data analysis of my 2024 Google calendar events on the first day of Spring break: https://t.co/QGEDwMkQPs

[Elisa Tsai @MustbeElisa]

If you're at NDSS, come chat at the poster session! #NDSS2025 #WWW2025 #AI #LLMs #ConsumerProtection

[Elisa Tsai @MustbeElisa]

Presenting our WWW 2025 paper "Harmful Terms and Where to Find Them" at the NDSS poster session today!

Many T&Cs hide unfavorable financial terms—hidden fees, tricky refunds, forced arbitration. We use LLMs to analyze 1.8M T&C lines and build a tool that flags them in real-time.

[Elisa Tsai @MustbeElisa]

🔍 Paper (arXiv): https://t.co/NPWrYlYd4d
💻 Code (GitHub): https://t.co/OZhZZKjylT
📊 Dataset (Hugging Face): https://t.co/ZMq8b864su
🔍 Read more in my blog post: https://t.co/yZ3flNWwR7

[Elisa Tsai @MustbeElisa]

It feels like LLMs don’t just boost productivity; they augment my thinking. I firmly believe that LLMs are changing human cognitive processes: streamlining learning, accelerating problem-solving, and reshaping how we interact with information. Ah, what a time to be alive. (9/9)

[Elisa Tsai @MustbeElisa]

I have some thoughts about how LLMs have transformed my life, but I can't quite articulate them. (1/9)

[Elisa Tsai @MustbeElisa]

When I encountered unfamiliar words (English isn’t my native language), I used an LLM-based etymology tool (that I also found on my X timeline) to analyze them (https://t.co/rkD0K0M6sf). (8/9)

[Elisa Tsai @MustbeElisa]

this is so cool

[Tanishq Mathew Abraham, Ph.D. @iScienceLuvr]

Language Models Use Trigonometry to Do Addition

"We first discover that numbers are represented in these LLMs as a generalized helix, which is strongly causally implicated for the tasks of addition and subtraction, and is also causally relevant for integer division, multiplication, and modular arithmetic. We
then propose that LLMs compute addition by manipulating this generalized helix using the “Clock” algorithm: to solve a + b, the helices for a and b are manipulated to produce the a + b answer helix which is then read out to model logits. "

[Elisa Tsai @MustbeElisa]

...and there’s always a light at the end of the frog https://t.co/QeAJtiz3Dj

[Elisa Tsai @MustbeElisa]

Today in Xplore Engineering we showed 4-7th graders how to train ML models, and how to fool them 🤖

credit: Oreo

[Ram @ramakrishnan13s]

Excited to attend #FOCI2023 and #PETS2023 in person this week! @MustbeElisa will be presenting our paper on detecting DNS manipulation using TLS certificate information on Thursday, July 13! Come find us in Section 7B!

[Elisa Tsai @MustbeElisa]

@__phw thanks a lot for sharing your experience! The chapters on open-sourcing code & "conferenceware" resonate a lot with me 🤍

[Elisa Tsai @MustbeElisa]

I came across Philipp Winter's Research Power Tools. I found it very insightful and applicable (also interesting and amusing to read). I put the digest of it on telegraph:

https://t.co/ixghwYQDc8