11Today we’re joined by Sanmi Koyejo, assistant professor at Stanford University, to continue our NeurIPS 2024 series. In our conversation, Sanmi discusses his two recent award-winning papers. First, we dive into his paper, “Are Emergent Abilities of Large Language Models a Mirage?”. We discuss the different ways LLMs are evaluated and the excitement surrounding their“emergent abilities” such as the ability to perform arithmetic Sanmi describes how evaluating model performance using nonlinear metrics can lead to the illusion that the model is rapidly gaining new capabilities, whereas linear metrics show smooth improvement as expected, casting doubt on the significance of emergence. We continue on to his next paper, “DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models,” discussing the methodology it describes for evaluating concerns such as the toxicity, privacy, fairness, and robustness of LLMs.

🔔 Subscribe to our channel for more great content just like this: https://youtube.com/twimlai?sub_confi...


🗣️ CONNECT WITH US!
===============================
Subscribe to the TWIML AI Podcast: https://twimlai.com/podcast/twimlai/
Join our Slack Community: https://twimlai.com/community/
Subscribe to our newsletter: https://twimlai.com/newsletter/
Want to get in touch? Send us a message: https://twimlai.com/contact/


📖 CHAPTERS
===============================
00:00 - Introduction
05:26 - Emergent behavior paper background
10:45 - Emergent behavior paper methodology
12:51 - Behavior of different metrics
16:17 - Use of "toy models" examples
25:05 - Emergent behavior paper results
39:14 - DecodingTrust paper
47:06 - RLHF and its effect on model behavior
52:26 - Applicability of trustworthiness benchmark to real-world cases
1:00:13 - Conclusion


🔗 LINKS & RESOURCES
===============================
Are Emergent Abilities of Large Language Models a Mirage? -
https://arxiv.org/abs/2304.15004
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models -
https://arxiv.org/abs/2306.11698
STAIR: Stanford Trustworthy AI Research -
https://stair.cs.stanford.edu/
Argument for emergence: Common arguments regarding emergent abilities -
https://www.jasonwei.net/blog/common-...


📸 Camera: https://amzn.to/3TQ3zsg
🎙️Microphone: https://amzn.to/3t5zXeV
🚦Lights: https://amzn.to/3TQlX49
🎛️ Audio Interface: https://amzn.to/3TVFAIq
🎚️ Stream Deck: https://amzn.to/3zzm7F5