iiinova — where your digital self keeps evolving

Xuhui Zhou @nlpxuhui.bsky.social · 18/12/2025

LLM agent simulations for policy: A field full of potential, yet clouded by myths and big questions. 🏛️🤖 We’re opening a new venue to spark open discussion and drive this research forward. Join the conversation! 🧵

010

Reposted by Xuhui Zhou

Language Technologies Institute | CMU @ltiatcmu.bsky.social · 26/06/2025

New research from LTI, UMich, & Allen Institute for AI: LLMs don’t just hallucinate – sometimes, they lie. When truthfulness clashes with utility (pleasing users, boosting brands), models often mislead. @nlpxuhui.bsky.social and @maartensap.bsky.social discuss the paper: lti.cmu.edu/news-and-eve...

lti.cmu.edu

Does Your Chatbot Swear to Tell the Truth? - Language Technologies Institute - School of Computer Science - Carnegie Mellon University

New research finds that LLM-based agents can't always be trusted to be truthful

032

Xuhui Zhou @nlpxuhui.bsky.social · 28/04/2025

When interacting with ChatGPT, have you wondered if they would ever "lie" to you? We found that under pressure, LLMs often choose deception. Our new #NAACL2025 paper, "AI-LIEDAR ," reveals models were truthful less than 50% of the time when faced with utility-truthfulness conflicts! 🤯 1/

1259

Reposted by Xuhui Zhou

Joel Mire @joelmire.bsky.social · 06/03/2025

Reward models for LMs are meant to align outputs with human preferences—but do they accidentally encode dialect biases? 🤔 Excited to share our paper on biases against African American Language in reward models, accepted to #NAACL2025 Findings! 🎉 Paper: arxiv.org/abs/2502.12858 (1/10)

Screenshot of Arxiv paper title, "Rejected Dialects: Biases Against African American Language in Reward Models," and author list: Joel Mire, Zubin Trivadi Aysola, Daniel Chechelnitsky, Nicholas Deas, Chrysoula Zerva, and Maarten Sap.

13811

Reposted by Xuhui Zhou

Hao Zhu 朱昊 @zhuhao.me · 04/03/2025

We are getting closer to have agents operating in the real physical world. However, can we trust frontier models to make embodied decisions 🎮 aligned with human norms 👩‍⚖️ ? With EgoNormia, a 1.8k ego-centric video 🥽 QA benchmark, we show that this is surprisingly challenging!

1239

Xuhui Zhou @nlpxuhui.bsky.social · 19/02/2025

LLM agents can code—but can they ask clarifying questions? 🤖💬 Tired of coding agents wasting time and API credits, only to output broken code? What if they asked first instead of guessing? 🚀 (New work led by Sanidhya Vijay: www.linkedin.com/in/sanidhya-...)

173

Xuhui Zhou @nlpxuhui.bsky.social · 06/02/2025

Excited to share that I'm joining All Hands AI (www.all-hands.dev) this summer as a research intern! 🚀 AI agents are becoming incredibly powerful, but their true potential lies in how they interact with and assist humans in meaningful ways.

all-hands.dev

All Hands AI

1100

Reposted by Xuhui Zhou

Will Held @williamheld.com · 27/11/2024

I like the BlueSky approach to "verification". If you own a domain, you can make a DNS record to turn it into your BlueSky handle! bsky.social/about/blog/4...

bsky.social

How to verify your Bluesky account - Bluesky

Here's how to verify your Bluesky account by setting your website as your username.

0131

Reposted by Xuhui Zhou

Language Technologies Institute | CMU @ltiatcmu.bsky.social · 20/11/2024

Hello, Bluesky! Happy to be scrolling the friendly skies with you. Follow for news and updates on LTI folks and their trailblazing research. #AI #NLP #ML #computerscience

0132

Reposted by Xuhui Zhou

Maria Antoniak @mariaa.bsky.social · 20/11/2024

some little bluesky tips 🦋 your blocks, likes, lists, and just about everything except chats are PUBLIC you can pin custom feeds; i like quiet posters, best of follows, mutuals, mentions if your chronological feed is overwhelming, you can make and pin make a personal list of "unmissable" people

1725457

Reposted by Xuhui Zhou

Language Technologies Institute | CMU @ltiatcmu.bsky.social · 20/11/2024

Looking for all your LTI friends on Bluesky? The LTI Starter Pack is here to help! go.bsky.app/NhTwCVb

6159