Deep dive: 4 NeurIPS 2023 best paper award papers - emergent ability, scaling, DPO, trustworthiness

Video Description

- Are Emergent Abilities of Large Language Models a Mirage? https://arxiv.org/abs/2304.15004 - Scaling Data-Constrained Language Models. https://arxiv.org/abs/2305.16264 - Direct Preference Optimization: Your Language Model is Secretly a Reward Model. https://arxiv.org/abs/2305.18290 - DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models. https://arxiv.org/abs/2306.11698 Jerry Liu's NeurIPS 2023 Reading List: https://pretty-sodium-5e0.notion.site/NeurIPS-2023-Reading-List-WIP-99a05177288f4dc98ee25291b3168b83 00:00 intro 00:31 paper 1: emergent abilities 04:33 paper 2: scaling data-constrained language models 08:15 paper 3: dpo 12:36 paper 4: trustworthiness 🔔 SUBSCRIBE to my channel: https://www.youtube.com/c/SophiaYangDS?sub_confirmation=1 ⭐ Stay in touch ⭐ 📚 DS/ML Book Club: http://dsbookclub.github.io/ ▶ YouTube: https://youtube.com/SophiaYangDS ✍️ Medium: https://sophiamyang.medium.com 🐦 Twitter: https://twitter.com/sophiamyang 🤝 Linkedin: https://www.linkedin.com/in/sophiamyang/ 💚 #ai