$k$NN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference
This work addresses a key problem for users of large language models by enabling scalable, calibration-free inference, though it is incremental as it builds on existing ICL and nearest neighbor approaches.
The paper tackles the limitations of In-Context Learning (ICL) in large language models, which cannot scale with training data due to context length restrictions and suffers from biases requiring calibration, by proposing $k$NN Prompting, a method that uses nearest neighbor inference to achieve calibration-free performance and scale effectively with up to 1024 shots, outperforming state-of-the-art calibration-based methods.
In-Context Learning (ICL), which formulates target tasks as prompt completion conditioned on in-context demonstrations, has become the prevailing utilization of LLMs. In this paper, we first disclose an actual predicament for this typical usage that it can not scale up with training data due to context length restriction. Besides, existing works have shown that ICL also suffers from various biases and requires delicate calibration treatment. To address both challenges, we advocate a simple and effective solution, $k$NN Prompting, which first queries LLM with training data for distributed representations, then predicts test instances by simply referring to nearest neighbors. We conduct comprehensive experiments to demonstrate its two-fold superiority: 1) Calibration-Free: $k$NN Prompting does not directly align LLM output distribution with task-specific label space, instead leverages such distribution to align test and training instances. It significantly outperforms state-of-the-art calibration-based methods under comparable few-shot scenario. 2) Beyond-Context: $k$NN Prompting can further scale up effectively with as many training data as are available, continually bringing substantial improvements. The scaling trend holds across 10 orders of magnitude ranging from 2 shots to 1024 shots as well as different LLMs scales ranging from 0.8B to 30B. It successfully bridges data scaling into model scaling, and brings new potentials for the gradient-free paradigm of LLM deployment. Code is publicly available.