Sahand Sabour

AKA Sam/山姆 🇮🇷🇨🇳 PhD @ Tsinghua, Conversational AI Lab 💻 I work on emotionally intelligent LLMs.

[Sahand Sabour @SahandSabour]

It feels like AI is getting smarter every day—but what if it’s not just smarter, but sneakier? 🤖🧠 What if your AI assistant wasn’t just helping you, but subtly manipulating your decisions? 🤔 Here's what we found in our new study: https://t.co/yNyiUnJ0c4 [1/11] 🧵

[Tim Althoff @timalthoff]

I’m excited to share our new @Nature paper 📝, which provides strong evidence that the walkability of our built environment matters a great deal to our physical activity and health.

Details in thread.🧵

https://t.co/omO3YcHrvG

[Sahand Sabour @SahandSabour]

The leaderboard for EmoBench is now live at https://t.co/gjXvzKagxi 🚀 This also includes results from some newer LLMs (compared to the original paper).
Next step -> updating the repo with a bunch of very much needed improvements (https://t.co/ttNkSNtl4j)

[Sahand Sabour @SahandSabour]

For more information, read our paper on Arxiv: https://t.co/nACf8TnKKT
We will also publish more info on data and code via https://t.co/eASJIQZPCY
Thanks to all the amazing collaborators for working on this massive project!
@timalthoff @radamihalcea @liusiyang_641 @advaitmb

[Sahand Sabour @SahandSabour]

It feels like AI is getting smarter every day—but what if it’s not just smarter, but sneakier? 🤖🧠 What if your AI assistant wasn’t just helping you, but subtly manipulating your decisions? 🤔 Here's what we found in our new study: https://t.co/yNyiUnJ0c4 [1/11] 🧵

[Sahand Sabour @SahandSabour]

By revealing human susceptibility to AI-driven manipulation, we risk enabling misuse. However, we believe transparency is critical, and understanding these risks is the first step toward building safeguards and ensuring AI is used to benefit society, not exploit it. [11/11]

[Siyang Liu @liusiyang_641]

"The Invisible Minority" – Older Adults 👵👴
Age bias is often overlooked compared to gender or race, yet by 2030, 1 in 6 people will be over 60!
Our study at #EMNLP2024 reveals LLMs tend to align with younger values.
Let's explore to make AI helpful and harmless for all ages!

[Sahand Sabour @SahandSabour]

Scenes from #ACL2024NLP and Bangkok 🇹🇭 Thank you for this great experience! Very nice to meet all the amazing people that shared a conversation with me (should take more pics next time)!

[ACL 2027 @aclmeeting]

🎉SAC Awards:

8) COKE: A Cognitive Knowledge Graph for Machine Theory of Mind by Wu et al.

9) MIDGARD: Self-Consistency Using Minimum Description Length for Structured Commonsense Reasoning by Nair and Wang

#NLProc #ACL2024NLP

[Sahand Sabour @SahandSabour]

Super excited to see our work on human cognitive modeling got an AC award at #ACL2024 check it out on arXiv: https://t.co/q3DPPQV3c4

[Sahand Sabour @SahandSabour]

From yesterday’s poster session st #ACL2024 Thank you all for dropping by and having a chat!

[Sahand Sabour @SahandSabour]

Live Muay Thai fights at #ACL2024 🥊 this is awesome!!!