🎓 PhD student @ischool.uw.edu (he/him)
🤝 Interested in pluralistic alignment & scalable oversight in the context of social media algorithms
Academic Website: https://sohamde.in/ | 📍Seattle, WA
Soham De
Loading...
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...
LLM-generated questions achieve representation levels comparable to—or better than—the theoretically optimal subsets, and consistently outperform human-selected slates (lower value is better) (5/7)
🚨 New paper! 🔍
“Question the Questions: Auditing Representation in Online Deliberative Processes”
In deliberative polls, participants propose questions for experts but only a few make it to the panel. How representative are those chosen questions of everyone’s interests? 🧵👇
We infer general utilities using LLM text-embeddings, assuming participants derive high utility from questions semantically similar to ones they propose (3/7)
All thanks to my amazing collaborators Lodewijk Gelauff, Ashish Goel, Smitha Milli, Ariel Procaccia and Alice Siu!!!
This was some work I did Meta FAIR this summer (more on the way!)
Read more here: arxiv.org/abs/2511.04588 (7/7)
Our auditing tools are integrated into a deliberation platform
used in 50+ countries, allowing moderators to measure and improve representation in real time (thanks, Harshvardhan Agarwal and others!) (6/7)
Our team at the @cip.uw.edu is currently seeking applications for up to two postdoctoral scholar positions. Applications received prior to January 15, 2026 will be given priority. Learn more about the positions, salary range, qualifications and application process: apply.interfolio.com/177901
We formalize representation using Justified Representation (JR) from social choice theory and introduce the first efficient algorithms for auditing JR in general utility settings (2/7)
"Understanding the strengths and limitations of community-based responses to misinformation" — very nice commentary by @ekvraga.bsky.social in PNAS, covering my recent paper on causal effects of Community Notes w/ @isaacslaughter.bsky.social @axelp.bsky.social @msaveski.bsky.social
We audit historical deliberations from the Stanford Deliberative Democracy Lab, comparing:
(a) human-moderator selections
(b) theoretically optimal subsets
(c) LLM-generated questions (4/7)
