Haosen Ge, Ph.D.

Data Scientist @WhartonAIAI | Ph.D. from @Princeton

[Hamsa Bastani @hamsabastani]

Conformal prediction sets are a useful way to capture uncertainty for LLMs & deep learning models. But they're data-hungry! We propose a semi-bandit algo to learn these sets online. Check out our @icmlconf paper: https://t.co/EQgTl3Xubc

Work led by @HaosenGe & with @obastani

[Haosen Ge, Ph.D. @HaosenGe]

Our paper is cited in Chapter 7 of the 2025 Economic Report of the President! https://t.co/m0dZhMztGY

[Hamsa Bastani @hamsabastani]

Excited to see our paper "Generative AI Can Harm Learning" cited in Ch 7 of the 2025 Economic Report of the President: https://t.co/vZmX4Cy7CD

Paper: https://t.co/toKa5BVDLQ, co-authored with @obastani @Alpsungu @HaosenGe Ozge & Rei

[Haosen Ge, Ph.D. @HaosenGe]

@kanxu526 Big congrats!

[Haosen Ge, Ph.D. @HaosenGe]

Thrilled to see that our paper made some waves! 🚀

[Hamsa Bastani @hamsabastani]

Pardon the brag but SO excited to see our paper at the top of @newsycombinator (for like 15 mins). Usually only 15 people read our papers 😅

@obastani @Alpsungu @HaosenGe Ozge Rei @WhartonAIAI

[Handi Li @Handi_Rita_Li]

Excited to see Philip K.H. Wong Centre @HKUniversity for promoting my working paper! I examined how Open Government Information mobilizes legal resistance in China but suffers a potenial backlash from local governments. Welcome any comments!

[Haosen Ge, Ph.D. @HaosenGe]

3/ To address this issue, we propose a class of new algorithms: compliance robust algorithms. We demonstrate that it is possible to convert any machine learning model into compliance robust models that guarantee improvement in outcome accuracy and fairness.

[Haosen Ge, Ph.D. @HaosenGe]

It's fantastic to see the increased interest in our research! I firmly believe it addresses a crucial question that any organization looking to implement AI to support human decision-making should consider.

[Wharton AI & Analytics Initiative @WhartonAIAI]

.@Wharton's@hamsabastani, Haosen Ge from @WhartonAnalytics, & @obastani explore AI-human collaboration challenges in their latest research featured in @Medium's "How to Improve AI Fairness in an Unfair World."

Check it out here: https://t.co/21wZSgfU63

[Haosen Ge, Ph.D. @HaosenGe]

2/In a nutshell, our research highlights a key issue with current AI decision support systems: the potential for AI-assisted humans to perform worse than either AI operating alone or humans without AI. This contradicts the very purpose of integrating AI systems.

[Haosen Ge, Ph.D. @HaosenGe]

@sid_devic @SimonsInstitute @hamsabastani @obastani Thank you! We are hoping to add that as an extension. In general, we can make an ϵ-compliance-robust guarantee, and the guarantee becomes stronger as we estimate the human decision function more accurately.

[Haosen Ge, Ph.D. @HaosenGe]

Excited to present my work with @hamsabastani and @obastani at the Simons Institute for the Theory of Computing (@SimonsInstitute) !

We delve into the challenges with algorithmic fairness when dealing with human decision makers who can selectively comply.

[Hamsa Bastani @hamsabastani]

If you play chess, consider signing up for the study 😊🙏

[Haosen Ge, Ph.D. @HaosenGe]

It's been an incredible experience to present in this fantastic event! I've learned a lot from the brilliant work of others!

[The Warren Center for Network & Data Sciences @WarrenCntrPenn]

Here's the full schedule for Friday, looking forward to the event!

[Hamsa Bastani @hamsabastani]

Deadline in 2 days, send us your extended abstracts!!

[ESL StarCraft II @ESLSC2]

The winning moment ~

#Oliveira wins #IEM Katowice and is your 2023 @StarCraft World Champion!

#IEM #ESLProTour

[Haosen Ge, Ph.D. @HaosenGe]

@in_young_park @ProfZhaoMIT @BU_MSE Looking forward to listening to Prof Park’s talk!

[Haosen Ge, Ph.D. @HaosenGe]

@rorytruex Truly happy for you!

[Haosen Ge, Ph.D. @HaosenGe]

An extremely fulfilling experience. A huge thanks to mentors @ Princeton Research Computing!
https://t.co/1G3rCN7cYK

[Erik Brynjolfsson @erikbryn]

Nothing to see here.

Just an AI system learning to strategically plan world conquest, negotiate with humans in English and then betray them via the game of Diplomacy.

https://t.co/zkN1EuJnAe

[James Zou @james_y_zou]

Given a trained #ML model, can we estimate how well it works on new data w/o seeing any labels?

Can we still do it even if both covariates and labels shift in data?

Our #NeurIPS2022 paper shows how to est model perf on new data in this hard case! https://t.co/VCmlNvWLjc 1/2

[Misha Laskin @MishaLaskin]

In our new work - Algorithm Distillation - we show that transformers can improve themselves autonomously through trial and error without ever updating their weights.

No prompting, no finetuning. A single transformer collects its own data and maximizes rewards on new tasks.

1/N