Marios Papachristou
@papachristoumarios.bsky.social
94 followers 280 following 27 posts
Assistant Professor at @ASU WP Carey Information Systems PhD from Cornell CS ex: @msftresearch, @twitter, @ntua website: https://papachristoumarios.github.io/
Posts Media Videos Starter Packs
Reposted by Marios Papachristou
emmapierson.bsky.social
The US government recently flagged my scientific grant in its "woke DEI database". Many people have asked me what I will do.

My answer today in Nature.

We will not be cowed. We will keep using AI to build a fairer, healthier world.

www.nature.com/articles/d41...
My ‘woke DEI’ grant has been flagged for scrutiny. Where do I go from here?
My work in making artificial intelligence fair has been noticed by US officials intent on ending ‘class warfare propaganda’.
www.nature.com
Reposted by Marios Papachristou
yyahn.bsky.social
A simple Keyboard Maestro script to change arxiv.org/pdf/xxxx to arxiv.org/abs/xxxx

I should have set this up years ago... 🥲
papachristoumarios.bsky.social
GeomScale also participates in the Google Summer of Code program, which aims to help students contribute to large open-source projects. It is an amazing opportunity if you want to be involved with open-source scientific software!

FYI: github.com/GeomScale/gs...
GitHub - GeomScale/gsoc25: GeomScale in Google Summer of Code 2025
GeomScale in Google Summer of Code 2025. Contribute to GeomScale/gsoc25 development by creating an account on GitHub.
github.com
papachristoumarios.bsky.social
Volesti is an open-source package for volume computation and sampling in high-dimensional constrained spaces.

High-dimensional constrained sampling has many applications in computational biology, finance, Bayesian inference, differential privacy, runtime verification, and many others.
papachristoumarios.bsky.social
Excited to be giving a talk today at ASU ML day (1.50-2.50 pm MST) on our work with Yuan Yuan on our work on network formation with LLMs, and the same talk on Sunday at the Network Science and Economics Conference at Stanford!

Event Link: asuevents.asu.edu/event/machin...
Machine Learning Day 2025 | ASU Events
You are invited to Arizona State University’s West Valley campus for the sixth annual Machine Learning Day! This event offers a unique platform for scholars and professionals from Arizona and beyond t...
asuevents.asu.edu
papachristoumarios.bsky.social
Read our latest work published in JOSS (@joss-openjournals.bsky.social)!
joss-openjournals.bsky.social
Just published in JOSS: 'volesti: A C++ library for sampling and volume computation on convex bodies' https://doi.org/10.21105/joss.07886
Reposted by Marios Papachristou
nkgarg.bsky.social
*Please repost* @sjgreenwood.bsky.social and I just launched a new personalized feed (*please pin*) that we hope will become a "must use" for #academicsky. The feed shows posts about papers filtered by *your* follower network. It's become my default Bluesky experience bsky.app/profile/pape...
Reposted by Marios Papachristou
sjgreenwood.bsky.social
Please repost to get the word out! @nkgarg.bsky.social and I are excited to present a personalized feed for academics! It shows posts about papers from accounts you’re following bsky.app/profile/pape...
papachristoumarios.bsky.social
Finally, we conduct a survey study involving human participants to assess our system's ability to aggregate preferences and reasoning. Our findings show that the system exhibits strong performance in both dimensions.

10/10
papachristoumarios.bsky.social
Our results indicate efficient coordination with reduced interactions between members and the LLM-based system. The system also effectively refines proposed options over time, ensuring their quality and equity.

9/n
papachristoumarios.bsky.social
We create synthetic employee profiles and simulate conversations at scale, leveraging LLMs to evaluate the system to avoid a costly real-user study.

8/n
papachristoumarios.bsky.social
Our system extracts individual preferences and suggests options that satisfy a significant portion of the members. We apply this system to corporate meeting scheduling.

7/n
papachristoumarios.bsky.social
Therefore, in this work, we ask a question: Can we leverage LLMs to elicit the members’ intents and form mutually agreeable plans?

We propose a system leveraging LLMs to facilitate group decision-making by managing conversations and balancing preferences among individuals.

6/n
papachristoumarios.bsky.social
In this regard, Large Language Models (LLMs) have shown its tremendous potential in extracting intent from free text, handling several constraints, and aggregating multiple inputs.

5/n
papachristoumarios.bsky.social
Several tools have been used to schedule common activities. However, they are not able to handle open-ended preferences beyond strict availability constraints.

4/n
papachristoumarios.bsky.social
Moreover, the members usually have diverse preferences, personal constraints, and social dynamics between them.

3/n
papachristoumarios.bsky.social
In our everyday life, we often face decisions that require collective input. For example, scheduling a gathering or deciding where to go for a group event are frequent tasks that involve back-and-forth group discussions.

2/n
papachristoumarios.bsky.social
I am happy to announce that our paper "LEVERAGING LLMs FOR COLLECTIVE DECISION-MAKING" has been accepted at the ACM CSCW conference! 🎉

This is joint work with Longqi Yang (@ylongqi.bsky.social) and Chin-Chia Hsu and as part of my internship at Microsoft.

Preprint: arxiv.org/abs/2311.04928

1/n
Leveraging Large Language Models for Collective Decision-Making
In various work contexts, such as meeting scheduling, collaborating, and project planning, collective decision-making is essential but often challenging due to diverse individual preferences, varying ...
arxiv.org