Lei Xu
@XuLeonard
Followers
52
Following
52
Media
2
Statuses
22
Applied Scientist @Amazon HealthAI | Formerly @MIT
NYC
Joined February 2015
Can LLMs support behavioral health documentation without compromising quality? Our ACL 2025 paper introduces TN-Eval: a comprehensive framework for evaluating therapy notes, co-designed with 22 licensed therapists. Key finding: In blind tests, therapists rated LLM-generated
1
2
8
This aligns with the growing trend β echoed by efforts like OpenAI's #HealthBench β of using structured criteria to guide and evaluate LLM applications in clinical settings.
1
0
0
In this work, we propose detailed rubrics tailored to the behavioral health domain and show that rubric-based evaluations offer significantly more reliability than standard Likert-scale ratings.
1
0
0
Excited to share that our paperΒ "π»π΅-π¬πππ: πΉπππππ πππ
π¬πππππππππ π·ππππππππ πππ π΄ππππππππ πππ πΈππππππ ππ π©πππππππππ π»ππππππ π΅ππππ"Β has been accepted toΒ ACL 2025! π
1
0
0
One more step towards better healthcare using AI. πππ
1/ π Excited to share our latest work β accepted to #ICLR2025 and featured in MIT News today! ποΈ MIT News: https://t.co/lPbVmAbf9i π Paper: https://t.co/AoBsV3qeUo π§΅ Thread π
0
0
1
Really excited to announce that our NeurIPS 2019 paper on 'Modeling tabular data using conditional GAN' has surpassed 1k citations! It's inspiring to see researchers applying the model innovatively in the era of LLMs. #NeurIPS #GAN #SyntheticData #MIT
0
0
3
Iβm attending NAACL at Seattle. Happy to grad βοΈ πΊ and chat. #NAACL2022
0
0
4
Researchers w/ MIT's Laboratory for Information & Decision Systems in the College of Computing released the Synthetic Data Vault β a one-stop shop where users can get as much data as they need for their projects, without compromising privacy. https://t.co/I1MZzoql0F
news.mit.edu
A set of open-source synthetic data generation tools meant to expand access to data without compromising privacy has been made available to the public by researchers in the Laboratory for Information...
0
2
0
Watching this animation is like a tour down memory lane of old processors.
Fascinating: Mooreβs Law predictions vs actual growth in transistor count. by @datagrapha
https://t.co/zuI86EntTa
13
279
1K
#NeurIPS2019 Our paper "Modeling Tabular data using Conditional GAN" is accepted as a poster! @lab_dai
0
0
3
An incident has taken place outside the US embassy compound in Beijing, CNN has confirmed.
33
107
126
MIT machine learning just got a whole lot stronger with new hires Pulkit Agrawal (@pulkitology), Jacob Andreas (@jacobandreas) and Cathy Wu (@wucathy). All starting in Fall 2019. All coming from my alma mater UC Berkeley :)
2
18
183