Language Technologies Institute | CMU

ltiatcmu.bsky.social

27 June 2025 18:40

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...

spqrz (M3GAN fan writer)

spqrz0.bsky.social

04 May 2025 20:45

I'd like to see the experiment repeated on Claude's models, as Anthropic seem to have a reputation for better ethical training than OpenAI & Meta, and it would be interesting to see if that makes a difference

Joel Mire

joelmire.bsky.social

06 March 2025 20:17

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)

Hao Zhu 朱昊

zhuhao.me

04 March 2025 22:06

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!

Akhila Yerukola

akhilayerukola.bsky.social

19 February 2025 20:45

Coding agents often don’t ask follow-up clarifying questions 🤷‍♀️ But interactivity isn’t about asking more questions—it’s about asking better questions! 🤖💬 Check out this new work led by Sanidhya Vijay! www.linkedin.com/in/sanidhya-...