When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations
Context-based fine-tuning methods, including prompting, in-context learning, soft prompting (also known as prompt tuning), and prefix-tuning, have gained popularity due to their ability to often match the performance of full fine-tuning with a fraction of the parameters. Despite their empirical successes, there is little theoretical understanding of how these techniques influence the internal computation of the model and their expressiveness limitations. We show that despite the continuous embedding space being more expressive than the discrete token space, soft-prompting and prefix-tuning are potentially less expressive than full fine-tuning, even with the same number of learnable parameters. Concretely, context-based fine-tuning cannot change the relative attention pattern over the content and can only bias the outputs of an attention layer in a fixed direction. This suggests that while techniques like prompting, in-context learning, soft prompting, and prefix-tuning can effectively elicit skills present in the pretrained model, they may not be able to learn novel tasks that require new attention patterns.
Code (1)
Tasks
In-Context LearningSimilar Papers 제목 키워드 기반
Prompting a Pretrained Transformer Can Be a Universal Approximator
Despite the widespread adoption of prompting, prompt tuning and prefix-tuning of transformer models, our theoretical understanding of these fine-tuning methods remains limited. A key question is whether one can arbitrari…
Understanding Prompt Tuning and In-Context Learning via Meta-Learning
Prompting is one of the main ways to adapt a pretrained model to target tasks. Besides manually constructing prompts, many prompt optimization methods have been proposed in the literature. Method development is mainly em…
In-Context LearningMeta-LearningSpeech Prefix-Tuning with RNNT Loss for Improving LLM Predictions
In this paper, we focus on addressing the constraints faced when applying LLMs to ASR. Recent works utilize prefixLM-type models, which directly apply speech as a prefix to LLMs for ASR. We have found that optimizing spe…
Prefix-Tuning: Optimizing Continuous Prompts for Generation
Fine-tuning is the de facto way to leverage large pretrained language models to perform downstream tasks. However, it modifies all the language model parameters and therefore necessitates storing a full copy for each tas…
Language ModelingLanguage ModellingTable-to-Text GenerationText GenerationDiscourse-Aware Soft Prompting for Text Generation
Current efficient fine-tuning methods (e.g., adapters, prefix-tuning, etc.) have optimized conditional text generation via training a small set of extra parameters of the neural language model, while freezing the rest fo…
BlockingConditional Text GenerationLanguage ModelingLanguage Modelling+1