most citedSkill-it! A Data-Driven Skills Framework for Understanding and Training Language Models

4 citations · 10 across the 5 of their papers we have counts for

collaborators

5 papers

cs.CL20232 cited

SuperHF: Supervised Iterative Learning from Human Feedback

Gabriel Mukobi, Peter Chatain, Su Fong +4

While large language models demonstrate remarkable capabilities, they often present challenges in terms of safety, alignment with human values, and stability during training. Here,…

cs.CL20234 cited

Skill-it! A Data-Driven Skills Framework for Understanding and Training Language Models

Mayee F. Chen, Nicholas Roberts, Kush Bhatia +4

The quality of training data impacts the performance of pre-trained large language models (LMs). Given a fixed budget of tokens, we study how to best select data that leads to good…

cs.LG20234 cited

Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification

Neel Guha, Mayee F. Chen, Kush Bhatia +3

Recent work has shown that language models' (LMs) prompt-based learning capabilities make them well suited for automating data labeling in domains where manual annotation is expens…

cs.LG2023

Reward Learning as Doubly Nonparametric Bandits: Optimal Design and Scaling Laws

Kush Bhatia, Wenshuo Guo, Jacob Steinhardt

Specifying reward functions for complex tasks like object manipulation or driving is challenging to do by hand. Reward learning seeks to address this by learning a reward model usi…

cs.LG2023

Congested Bandits: Optimal Routing via Short-term Resets

Pranjal Awasthi, Kush Bhatia, Sreenivas Gollapudi +1

For traffic routing platforms, the choice of which route to recommend to a user depends on the congestion on these routes -- indeed, an individual's utility depends on the number o…