Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning

11 May 2022  ·  Haokun Liu, Derek Tam, Mohammed Muqeeth, Jay Mohta, Tenghao Huang, Mohit Bansal, Colin Raffel ·

Few-shot in-context learning (ICL) enables pre-trained language models to perform a previously-unseen task without any gradient-based training by feeding a small number of training examples as part of the input. ICL incurs substantial computational, memory, and storage costs because it involves processing all of the training examples every time a prediction is made. Parameter-efficient fine-tuning (e.g. adapter modules, prompt tuning, sparse update methods, etc.) offers an alternative paradigm where a small set of parameters are trained to enable a model to perform the new task. In this paper, we rigorously compare few-shot ICL and parameter-efficient fine-tuning and demonstrate that the latter offers better accuracy as well as dramatically lower computational costs. Along the way, we introduce a new parameter-efficient fine-tuning method called (IA)$^3$ that scales activations by learned vectors, attaining stronger performance while only introducing a relatively tiny amount of new parameters. We also propose a simple recipe based on the T0 model called T-Few that can be applied to new tasks without task-specific tuning or modifications. We validate the effectiveness of T-Few on completely unseen tasks by applying it to the RAFT benchmark, attaining super-human performance for the first time and outperforming the state-of-the-art by 6% absolute. All of the code used in our experiments is publicly available.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Few-Shot Text Classification RAFT T-Few Avg 0.758 # 1
ADE 0.804 # 2
B77 0.695 # 1
NIS 0.833 # 2
OSE 0.676 # 1
SOT 0.915 # 1
SRI 0.508 # 2
TAI 0.736 # 1
ToS 0.75 # 1
TEH 0.586 # 2
TC 0.879 # 2
Over 0.95 # 1