iiinova — where your digital self keeps evolving

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)

000

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)

100

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)

100

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)

100

We infer general utilities using LLM text-embeddings, assuming participants derive high utility from questions semantically similar to ones they propose (3/7)

100

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)

Sophie Greenwood @sjgreenwood.bsky.social · 10/03/2025

🚨 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? 🧵👇

182

Reposted by Soham De

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...

8171118

Supernotes: Driving Consensus in Crowd-Sourced Fact-Checking | Proceedings of the ACM on Web Conference 2025

More results and implementation details in our full paper, here: dl.acm.org/doi/10.1145/... If you're in Sydney and attending www2025.thewebconf.org come say hi, I'd love to chat! I'll also be presenting this as a poster on Day 5, noon in the Parkside Ballroom @ ICC Sydney

dl.acm.org

You will be notified whenever a record that you have chosen has been cited.

010

Beyond helpfulness, participants also rated the Supernotes more favorably than the best existing notes on quality, clarity, coverage, context, and argumentativeness.

Supernotes are also found to be superior on several other parameters, such as source quality, clarity, comprehensiveness, context and (lack of) argumentativeness

In a human-subjects evaluation, participants rated Supernotes significantly more helpful than the best existing human-written notes on Community Notes.

Supernotes are more helpful than the best existing notes

We propose "Supernotes" to improve existing Community Notes by (a) summarizing relevant information across multiple human-written notes, and (b) using LLMs to compose these notes in language that is more broadly appealing and helpful

Soham De @sohamde.in · 03/04/2025

I'll be in Sydney presenting ✨Supernotes✨ at the ACM WebConf 🚀 (WWW'25). Incase you missed it, here's a very short thread about it: 🧵 Full paper: dl.acm.org/doi/10.1145/... #www2025 #thewebconf2025

1101

Congratulations, Sanjush!

000

Reposted by Soham De

New_ Public @newpublic.org · 27/01/2025

This week’s newsletter brings together past, present and future of fact-checking social media: ✔️ Sorting out moderation vs fact-checking ✔️ Where social media fact-checking came from ✔️ What actually works and what else to consider

newpublic.substack.com

🕵🏼‍♀️✅ Fact-checking’s future: can social media handle the truth?

Who should decide what’s true online?

0114

Soham De @sohamde.in · 05/12/2024

Super cool & important work from @matthewdeverna.com!

051

Soham De @sohamde.in · 25/11/2024

Yes! I've been lurking here for about a year and it finally feels a little like Academic Twitter again!