most citedRL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold

1 citations · 1 across the 1 of their papers we have counts for

collaborators

5 papers

cs.LG20241 cited

RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold

Amrith Setlur, Saurabh Garg, Xinyang Geng +3

Training on model-generated synthetic data is a promising approach for finetuning LLMs, but it remains unclear when it helps or hurts. In this paper, we investigate this question f…

cs.LG2024

DataComp-LM: In search of the next generation of training sets for language models

Jeffrey Li, Alex Fang, Georgios Smyrnis +56

We introduce DataComp for Language Models (DCLM), a testbed for controlled dataset experiments with the goal of improving language models. As part of DCLM, we provide a standardize…

cs.LG2024

Post-Hoc Reversal: Are We Selecting Models Prematurely?

Rishabh Ranjan, Saurabh Garg, Mrigank Raman +2

Trained models are often composed with post-hoc transforms such as temperature scaling (TS), ensembling and stochastic weight averaging (SWA) to improve performance, robustness, un…

cs.LG2023

Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shift

Saurabh Garg, Amrith Setlur, Zachary Chase Lipton +3

Self-training and contrastive learning have emerged as leading techniques for incorporating unlabeled data, both under distribution shift (unsupervised domain adaptation) and when…

cs.CV2023

TiC-CLIP: Continual Training of CLIP Models

Saurabh Garg, Mehrdad Farajtabar, Hadi Pouransari +5

Keeping large foundation models up to date on latest data is inherently expensive. To avoid the prohibitive costs of constantly retraining, it is imperative to continually train th…