Log inSign up
Siyan Sylvia Li ☀️ ACL 2026
836 posts
user avatar
Siyan Sylvia Li ☀️ ACL 2026
@Sylvia_Sparkle
3rd year PhD @columbianlp • Prev @stanfordnlp @GeorgiaTech • NLP, Dialogue Systems, Education • Caffeine Gremlin 🩷💜💙
siyan-sylvia-li.com
Joined October 2019
751
Following
1,887
Followers

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
  • Pinned
    user avatar
    Siyan Sylvia Li ☀️ ACL 2026
    @Sylvia_Sparkle
    Oct 28, 2024
    Concerned about sending private data to LLM providers, but local LLMs aren't as good? Introducing PAPILLON 🦋, a system that uses local LLMs to create privacy-preserving LLM queries for you. 🦋 prevents leakage of PII (93%) while retaining response quality on 85% of queries! 🧵
    78K
  • user avatar
    Siyan Sylvia Li ☀️ ACL 2026
    @Sylvia_Sparkle
    Feb 22, 2024
    🌟嗨大家好!我们是哥伦比亚大学自然语言处理实验室!我们现在在开发一个可以提供语法反馈和鼓励式反馈的英语学习聊天机器人,想要征求大家在设计方面的宝贵意见! forms.gle/4ggypHSkU1jYP9… 大家也可以在Google Form 里报名参加我们的聊天机器人试用! ✨麻烦各位多多转发!谢谢!
    docs.google.com
    聊天机器人设计反馈
    你好!我们现在在开发一个可以帮助英语学习的聊天机器人平台,想要征求你的反馈和意见。
    114K
  • user avatar
    Siyan Sylvia Li ☀️ ACL 2026
    @Sylvia_Sparkle
    Oct 30, 2025
    Please share widely: Columbia's student-run Computer Science PhD Pre-Submission Application Review (PAR) Program is back in full swing! If you are interested in having current CS PhD students review your personal statement, please apply by November 10!! cs.columbia.edu/cscu-phd-par-p…
    22K
  • user avatar
    Siyan Sylvia Li ☀️ ACL 2026
    @Sylvia_Sparkle
    Mar 24, 2023
    📣✨ I'm starting my PhD @columbianlp in the fall! I will be working with @Zhou_Yu_AI and Dr. Julia Hirschberg on dialogue system applications in mental health, education, and healthcare!! I'm very excited and thankful for everyone who has supported me along the way :)
    29K
  • user avatar
    Siyan Sylvia Li ☀️ ACL 2026
    @Sylvia_Sparkle
    Jul 7, 2025
    🎉 Excited to announce that the 4th HCI+NLP workshop will be co-located with @emnlp in Suzhou, China! 🌍📍 Join us to explore the intersection of human-computer interaction and NLP. 🧵 1/
    16K
  • user avatar
    Siyan Sylvia Li ☀️ ACL 2026
    @Sylvia_Sparkle
    Aug 10, 2022
    In a conversation, you should ideally say things. But when should you say those things? And how can you teach a model to know when to say those things? I am super hyped to present our paper at @sigdial 2022! This is joint work with @AshwinParanjape. 🧵 arxiv.org/abs/2208.03812
  • user avatar
    Siyan Sylvia Li ☀️ ACL 2026
    @Sylvia_Sparkle
    Oct 26, 2025
    "Taylor Swift is an Instruction-tuned version of Bob Dylan." -- @ChrisGPotts (he said I should tweet it)
    12K
  • user avatar
    Siyan Sylvia Li ☀️ ACL 2026
    @Sylvia_Sparkle
    Oct 26, 2025
    Look it's me in third row!! Super happy and honored to come back and catch up with everyone 🥹
    user avatar
    Stanford NLP Group
    @stanfordnlp
    Oct 25, 2025
    Today, we’re overjoyed to have a 25th Anniversary Reunion of @stanfordnlp. So happy to see so many of our former students back at @Stanford. And thanks to @StanfordHAI for the venue!
    21K
  • user avatar
    Siyan Sylvia Li ☀️ ACL 2026
    @Sylvia_Sparkle
    Jan 23, 2025
    PAPILLON 🦋 has been accepted into NAACL Main Conference!! 🥳🥳🥳✨✨✨ Check out the original PAPILLON thread below to learn more about our approach for privacy preservation during inference-time interactions with LLMs!
    user avatar
    Siyan Sylvia Li ☀️ ACL 2026
    @Sylvia_Sparkle
    Oct 28, 2024
    Concerned about sending private data to LLM providers, but local LLMs aren't as good? Introducing PAPILLON 🦋, a system that uses local LLMs to create privacy-preserving LLM queries for you. 🦋 prevents leakage of PII (93%) while retaining response quality on 85% of queries! 🧵
    13K
  • user avatar
    Siyan Sylvia Li ☀️ ACL 2026
    @Sylvia_Sparkle
    Sep 20, 2024
    Just got accepted into EMNLP Findings!! See everyone in Miami 🌟
    user avatar
    Siyan Sylvia Li ☀️ ACL 2026
    @Sylvia_Sparkle
    Jun 27, 2024
    🌺Education chatbots should be *empathetic* and encouraging! Announcing EDEN, a spoken conversation partner for English learning. Through a user study, we find that certain design choices that make EDEN more empathetic correlate with higher resilience for language learners!🧵
    7.6K
  • user avatar
    Siyan Sylvia Li ☀️ ACL 2026
    @Sylvia_Sparkle
    Jun 21, 2024
    Had a very lovely time at #NAACL!! I met up with old friends and made new friends :D Also did my first conference presentation as a PhD student!!! Thanks everyone and see you at the next conference!!!
    5.6K
  • user avatar
    Siyan Sylvia Li ☀️ ACL 2026
    @Sylvia_Sparkle
    Dec 9, 2024
    📢 Announcing the release of data and code for the PAPILLON system! PAPILLON allows a laptop-hosted model like Llama-3.2-3B to use more powerful API models like GPT-4o-mini as a tool, seeking to avoid (not yet 100% prevent) leaking private PII. Still very early/experimental! 🧵
    user avatar
    Siyan Sylvia Li ☀️ ACL 2026
    @Sylvia_Sparkle
    Oct 28, 2024
    Concerned about sending private data to LLM providers, but local LLMs aren't as good? Introducing PAPILLON 🦋, a system that uses local LLMs to create privacy-preserving LLM queries for you. 🦋 prevents leakage of PII (93%) while retaining response quality on 85% of queries! 🧵
    12K
  • user avatar
    Siyan Sylvia Li ☀️ ACL 2026
    @Sylvia_Sparkle
    Nov 18, 2024
    I had a wonderful time at #EMNLP2024 !! I beached. And I chatted with old friends and new friends!! It was great talking about Education + NLP and about Privacy!! Excited for the next conference :)
    6.2K
  • user avatar
    Siyan Sylvia Li ☀️ ACL 2026
    @Sylvia_Sparkle
    Oct 19, 2022
    Coming to a Findings of EMNLP near you: GPT-3 fails to demonstrate a structural understanding of noun compounds once we remove some lexical clues in our prompts. Joint work with Riley Carlson and @ChrisGPotts. Paper link: arxiv.org/pdf/2210.09492… 🧵