Swabha @swabhs - Bluesky Profile

Latest posts by swabhs.bsky.social on Bluesky

Reasoning about the "why" behind user behavior can improve LLM personas! ✨🧠📈

📝Excited to share our new work: Improving LLM Personas via Rationalization with Psychological Scaffolds

🔗 arxiv.org/abs/2504.17993
🧵 (1/n)

29.04.2025 01:05 — 👍 14 🔁 4 💬 1 📌 0

Improving LLM Personas via Rationalization with Psychological Scaffolds Language models prompted with a user description or persona can predict a user's preferences and opinions, but existing approaches to building personas -- based solely on a user's demographic attribut...

📖 So fun to collaborate with amazing folks at USC (Xiang Ren, @swabhs.bsky.social ) and Apple (Rik Koncel-Kedziorski, Tim Paek) on this work! 🤝💡📣
Excited to finally share this—let us know what you think! 🙌🏽✨🎉

More details in our draft here: arxiv.org/abs/2504.17993

(8/n)

29.04.2025 01:05 — 👍 2 🔁 1 💬 0 📌 0

#socalnlp is the biggest it's ever been in 2024! We have 3 poster sessions up from 2! How many years until it's a two-day event?? 🤯

22.11.2024 21:50 — 👍 26 🔁 3 💬 2 📌 0

We at UT Linguistics are hiring for 🔥 2 faculty positions in Computational Linguistics! Assistant or Associate professors, deadline Dec 1.
UT has a super vibrant comp ling & #nlp community!!

Apply here 👉 apply.interfolio.com/158280

19.11.2024 22:38 — 👍 12 🔁 7 💬 0 📌 1

And we're having a great time at #EMNLP2024, come talk to us!

14.11.2024 23:34 — 👍 15 🔁 2 💬 0 📌 0

#EMNLP2024 has been a treat so far! Of course it doesn't hurt to win an outstanding paper award with my incredible PhD students Jaspreet Ranjit and @brihi.bsky.social and our wonderful collaborators at USC 😜
Paper: dill-lab.github.io/oath-frames/

14.11.2024 23:31 — 👍 17 🔁 1 💬 0 📌 1

Ahh sorry I missed Lucy - I was oot

08.10.2023 12:56 — 👍 1 🔁 0 💬 0 📌 0

Hoping against hope that bluesky will be a breath of fresh air🤞Bit much?

17.05.2023 03:23 — 👍 4 🔁 0 💬 0 📌 0

Try sweet maria

17.05.2023 03:19 — 👍 1 🔁 0 💬 0 📌 0

@swabhs is following 20 prominent accounts

Lianhui Qin
@lianhui

NLP/ML Assistant Professor @UCSD

Rebecca Dorn
@rebeccadorn

PhD candidate at USC. Studying inequitable social systems in NLP, social media and content moderation. They/She http://rebedorn.github.io

Atharva Kulkarni
@athrvkk

CS PhD at USC | Prev - CMU, Apple, IIIT Delhi | Robust, Generalizable, and Trustworthy NLP https://athrvkk.github.io/

Deqing Fu
@deqing

CS PhD Student @USC. deqingfu.github.io

Berk Ustun
@berkustun

Assistant Prof at UCSD. I work on safety, interpretability, and fairness in machine learning. www.berkustun.com

Guy Van den Broeck
@guyvdb

🎓 CS Prof at UCLA 🧠 Researching reasoning and learning in artificial intelligence: tactable deep generative models, probabilistic circuits, probabilistic programming, neurosymbolic AI https://web.cs.ucla.edu/~guyvdb/

Sameer Singh @Neurips
@sameer-singh

CS Prof at UC Irvine, CTO/Cofounder at Spiffy AI Work on evaluation and robustness of LLMs

Yisong Yue
@yisongyue

AI professor at Caltech. General Chair ICLR 2025. http://www.yisongyue.com

Marek Rei
@marekrei

AI/ML/NLP researcher and Senior Lecturer at Imperial College London. Working on language models for planning, reasoning and interpretable decision making

Alisa Liu
@alisawuffles

phd student at @uwcse

Mina Lee
@mnlee

Assistant Professor @ UChicago CS/DSI (NLP & HCI) | Writing with AI ✍️ https://minalee-research.github.io/

Mechanical Dirk
@mechanicaldirk

Training big models at @ai2.bsky.social.

Hamish Ivison
@hamishivi

I (try to) do NLP research. Antipodean abroad. currently doing PhD @uwcse, prev @usyd @ai2 🇦🇺🇨🇦🇬🇧 ivison.id.au

Serena Booth
@reniebird

CS Prof at Brown University, PI of the GIRAFFE lab, former AI Policy Advisor in the US Senate. PhD at MIT CSAIL '23, Harvard '16, former Google APM. Dog mom to NSDTR Ducki.

Ari
@ari-holtzman

Assistant Professor @ UChicago CS & DSI UChicao Leading Conceptualization Lab http://conceptualization.ai Minting new vocabulary to conceptualize generative models.

Sunipa Dev
@sunipadev

Responsible, and Inclusive #NLProc. Senior RS @ Google Research. she/her

Kawin Ethayarajh
@kawinethayarajh

Postdoc at Princeton PLI. Formerly PhD at Stanford CS. Working on behavioral machine learning. https://kawine.github.io/

Xinyan Velocity Yu
@velocityyu

NLP/ML @usc, @uwcse. she/her.🏹🤖👩🏻‍🍳. velocitycavalry.github.io. Multilinguality, retrieval, refining LLMs…

Ameya Godbole
@ameyagodbole

PhD student USC NLP working on generalization and reasoning, prev UMassAmherst, IITG (he/him)

Noah A. Smith
@nlpnoah

Researcher in NLP, ML, computer music. Prof @uwcse @uwnlp & helper @allen_ai @ai2_allennlp & familiar to two cats. Single reeds, tango, swim, run, cocktails, מאַמע־לשון, GenX. Opinions not your business.