Input-Tuning: Adapting Unfamiliar Inputs to Frozen Pretrained Models

By Shengnan An, Yifei Li, Zeqi Lin, Qian Liu, Qiang Fu, Weizhu Chen, Nanning Zheng, Jian-Guang Lou. 2022

47 citations recorded by the source corpus.

Recently the prompt-tuning paradigm has attracted significant attention. By only tuning continuous prompts with a frozen pre-trained language model (PLM), prompt-tuning takes a step towards deploying a shared frozen PLM to serve numerous downstream tasks. Although prompt-tuning shows good performance on certain natural language understanding (NLU) tasks, its effectiveness on natural language generation (NLG) tasks is still under-explored. In this paper, we argue that one of the factors hindering the development of prompt-tuning on NLG tasks is the unfamiliar inputs (i.e., inputs are linguistically different from the pretraining corpus). For example, our preliminary exploration reveals a large performance gap between prompt-tuning and fine-tuning when unfamiliar inputs occur frequently in NLG tasks. This motivates us to propose input-tuning, which fine-tunes both the continuous prompts and the input representations, leading to a more effective way to adapt unfamiliar inputs to frozen PLMs. Our proposed input-tuning is conceptually simple and empirically powerful. Experimental results on seven NLG tasks demonstrate that input-tuning is significantly and consistently better than prompt-tuning. Furthermore, on three of these tasks, input-tuning can achieve a comparable or even better performance than fine-tuning.

Subfields: Artificial Intelligence, Representation & Self-Supervised Learning, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Representation & Self-Supervised Learning

In Meta & Continual Learning

Citations in the corpus

QLoRA: Efficient Finetuning of Quantized LLMs (2023, methodology): “…many other Parameter Efficient FineTuning (PEFT) methods have been proposed such as prompt tuning [49, 33, 34], tuning the embedding layer inputs [1], tuning hidden states (IA 3 ) [37], adding full layers [27], tuning biases [71], learning a mask over weights based on Fisher information [55],…”
Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning (2022, neutral): “[55] tune prompts along with input embeddings for boost in performance, and Chen et al.”
LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition (2023, methodology): “During each experimental sequence, we randomly select 20 LoRA modules from them as the candidate for our LoraHub learning.”
Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation (2022, result): “Consistent with the findings in An et al. (2022) for other generative tasks, we find that PROMPTTUNING, even with scale, falls far below MODELTUNING on monolingual English summarization.14 PROMPTTUNING is better on larger language shifts: Interestingly, PROMPTTUNING is competitive with or…”
RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning (2022, background): “…text with properties such as topic (Guo et al., 2021; Qian et al., 2022) and (lack of) toxicity (Liu et al., 2021a; Perez et al., 2022), or from modalities such as image (Mokady et al., 2021; Zhou et al., 2022), structured data (Li and Liang, 2021; An et al., 2022), and numbers (Wei et al., 2022b).”