iiinova — where your digital self keeps evolving

Reposted by Qing Xiao

Yuxuan Li @yuxuanli1225.bsky.social · 22/05/2025

🚨 New Preprint! 🚨 Smarter LLMs are more selfish. We show reasoning-enhanced models significantly prefer greed over cooperation. The more LLMs reason, the worse they cooperate. 👇 THREAD 👇 [Link to paper: arxiv.org/abs/2502.177... [1/n]

131

Reposted by Qing Xiao

Yuxuan Li @yuxuanli1225.bsky.social · 20/05/2025

🚨 New Paper! 🚨 “Groups that communicate diverse information make wiser decisions.” Right? Not always—for LLMs, just like humans. We bring this scrutiny to AI by introducing the Hidden Profile paradigm to assess how multi-agent LLMs actually reason together. arxiv.org/abs/2505.115... [1/n]

152

Qing Xiao @qingxiaohci.bsky.social · 23/04/2025

Thanks for sharing our research. Here to see how internal cross-functional teams (journalists, AI professionals) work in newsrooms!

000

Reposted by Qing Xiao

Yuxuan Li @yuxuanli1225.bsky.social · 30/01/2025

🚨 Advanced LLMs may sound unbiased—but it's a ruse. We show that demographically-informed language agents reveal stark, implicit biases in decision-making. New preprint: “Actions Speak Louder Than Words: Agent Decisions Reveal Implicit Biases in Language Models” 👉 arxiv.org/abs/2501.17420 [1/n]

1194

Qing Xiao @qingxiaohci.bsky.social · 09/12/2024

Just transitioning from Twitter to here, is there any scholars, especially those in Communication, HCI or media psychology, I could follow?

230