Thank you @mdredze for bringing me on to evaluate patient-facing chatbots. Loved tackling the hard problem of evaluating open-ended tasks in high-stakes AI, especially with domain experts in the loop. Will miss you and everyone at Dredze lab!
Congratulations to @SonalSSJ on finishing her postdoc with my group. We worked on systems to identify errors and omissions in medical chatbot responses.
One paper is already out, and several more are on their way.
Great work @SonalSSJ !
proceedings.mlr.press/v297/y…
7
251
Had the best time TAing the JSALT workshop on Responsible AI & Evaluation alongside @krisgligoric and @deliprao!
Awesome discussions on bias and judging LLM-as-judge
@jhuclsp JSALT Summer school!!! 😀😀
What is happening today?
Responsible AI and Evaluation (Hosts: Kristina Gligoric & Delip Rao)
clsp.jhu.edu/the-12th-freder…
1
216
Sonal Joshi retweeted
I just finished the first year of my PhD. Rather than just share my own perspective, I sat down with 7 other students in my cohort and talked with them about their experiences in depth. In my new post, I share some of our biggest lessons: jonathanivey.github.io/2026/…
Sonal Joshi retweeted
I will present MedExpert, a clinician-annotated Factuality and Completeness dataset with Severity levels for Medical Chatbot Evaluation at ML4H in San Diego today. Happy to chat from Dec 1 to 3! See paper at: openreview.net/pdf?id=rkLAzD…
@mdredze @Alexir563 @jhuclsp @SonalSSJ
Excited to be one of 2025 CAMLIS Student Scholarship Recipient!
We are excited to share that CAMLIS is sponsoring six outstanding students to attend #CAMLIS2025!
These students are joining us from near and far, bringing fresh perspectives and energy to our community! Please join us in giving them a warm welcome.
103
Sonal Joshi retweeted
We introduce WaltzRL🎶, a multi-agent RL framework that treats LLM safety as a positive-sum game between conversation & feedback agents. It strikes an elegant balance between helpfulness & harmlessness, boosting safety & reduces overrefusals without degrading capabilities!
💃New Multi-Agent RL Method: WaltzRL💃
📝: arxiv.org/abs/2510.08240
- Makes LLM safety a positive-sum game between a conversation & feedback agent
- At inference feedback is adaptive, used when needed
-> Improves safety & reduces overrefusals without degrading capabilities!
🧵1/5
Sonal Joshi retweeted
👩🔬International Day of Women and Girls in Science is this Saturday, #February11.
@UN_Women @WomenScienceDay
#WomenInScience #GirlsInScience #CdnSci
Es emocionante compartir historias de ciencia!👩🔬👩🔬
un.org/es/#un_podcasts
Sonal Joshi retweeted
#MerlionChallenge News:
Can your speech processing systems handle the challenge of vibrantly multilingual
naturalistic speech and figure out which language is spoken when?
Join the MERLion CCS challenge at #INTERSPEECH2023!
sites.google.com/view/merlio….
Having been here for 3 years, I vouch that JHU CLSP is an amazing place to do a Ph.D! Check out below for the application process and live session to answer questions about admissions:
Are you applying to PhD programs in CS/ECE for #NLProc? Consider our fantastic program!
Learn more about the admissions process here:
clsp.jhu.edu/apply-for-phd/
Join our AMA on Admissions on November 15. Register here:
forms.gle/LTb2JrrRZnLa6CVM9
Sonal Joshi retweeted
In addition to our mentoring program, Prof Mark Dredze @mdredze will be hosting an admissions AMA on November 15 at 9:30 PM EST (to accommodate more time zones) 🙌.
Please pre-register to receive a zoom link: forms.gle/LTb2JrrRZnLa6CVM9
Reply with questions you want answered.
It's ✨grad app season✨ and @jhuclsp has a student-run application mentoring program for those looking for guidance with their application.
Open to prospective PhD applicants!
Apply here: forms.gle/MaMUfaEMr3URMMfS9
Submit materials by Nov 20.
Spread the word. #NLProc
Sonal Joshi retweeted
It's ✨grad app season✨ and @jhuclsp has a student-run application mentoring program for those looking for guidance with their application.
Open to prospective PhD applicants!
Apply here: forms.gle/MaMUfaEMr3URMMfS9
Submit materials by Nov 20.
Spread the word. #NLProc
Sonal Joshi retweeted
#Lhotse now supports annotating audio files with OpenAI's #Whisper! Here's a quick demo I created in 10 mins to transcribe the first 100 recordings from VoxCeleb.
See PR from @PiotrZelasko: github.com/lhotse-speech/lho…
Here's the sample audio: tinyurl.com/3vjxnubk
Sonal Joshi retweeted
Expert Session 8 - "Speech as a disease biomarker" by Catarina Botelho and Ayimnisagul Ablimi starts at 17:00! #ICASSP2022
Presenting our paper (in-person!) today (Tue, 24 May, 5.30pm Singapore Time) at @ieeeICASSP Singapore in Session SPE-L7. If you are interested in adversarial attacks, please do come to see me attempt to summarize our 16-page journal paper in 12 mins ⏩ ieeexplore.ieee.org/document…
Missing you so much @jvillalba1980 @PiotrZelasko Laureano Moro-Velázquez & Najim Dehak.Wish you were here for my first in-person oral presentation in PhD. Nevertheless, thank you so much for your constant support and the opportunity! This truly wouldn't be possible without you🙏
1
9
Sonal Joshi retweeted
Join us for @ieeeICASSP tutorial 💬 🤖 "Adversarial Robustness & Reprogramming for Speech & Language Processing" I will present the 2nd section of the tutorial on neural reprogramming & prompting. Jointly with @pinyuchenTW @IBMResearch @GeorgiaTech_ECE 2022.ieeeicassp.org/tutorial…
Sonal Joshi retweeted
Just released Lhotse v1.2 with 4 new recipes, better consistency across recipe outputs (thanks @rdesh26) and a bunch of minor features and bug fixes.
github.com/lhotse-speech/lho…
Sonal Joshi retweeted
📢Submission portal is open for the 8th Doctoral Consortium at #INTERSPEECH2022📢
If you are a doctoral student👨💻and wishes to get feedback on your ongoing project from a panel of experts.
Submit your abstract before: 16 of June
More info on our website: isca-students.org/sacweb/