6 papers · 1 filter
Fluid Language Model Benchmarking
Valentin Hofmann, David Heineman, Ian Magnusson +7
Language model (LM) benchmarking faces several challenges: comprehensive evaluations are costly, benchmarks often fail to measure the intended capabilities, and evaluation quality…
Establishing Task Scaling Laws via Compute-Efficient Model Ladders
Akshita Bhagia, Jiacheng Liu, Alexander Wettig +9
We develop task scaling laws and model ladders to predict the individual task performance of pretrained language models (LMs) in the overtrained setting. Standard power laws for la…
Signal and Noise: A Framework for Reducing Uncertainty in Language Model Evaluation
David Heineman, Valentin Hofmann, Ian Magnusson +5
Developing large language models is expensive and involves making decisions with small experiments, typically by evaluating on large, multi-task evaluation suites. In this work, we…
OLMES: A Standard for Language Model Evaluations
Yuling Gu, Oyvind Tafjord, Bailey Kuehl +3
Progress in AI is often demonstrated by new models claiming improved performance on tasks measuring model capabilities. Evaluating language models can be particularly challenging,…
Scalable Data Ablation Approximations for Language Models through Modular Training and Merging
Clara Na, Ian Magnusson, Ananya Harsh Jha +4
Training data compositions for Large Language Models (LLMs) can significantly affect their downstream performance. However, a thorough data ablation study exploring large sets of c…
Merge to Learn: Efficiently Adding Skills to Language Models with Model Merging
Jacob Morrison, Noah A. Smith, Hannaneh Hajishirzi +3
Adapting general-purpose language models to new skills is currently an expensive process that must be repeated as new instruction datasets targeting new skills are created, or can…