Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

adversarial soft prompt tuning

Adversarial soft prompt tuning is a parameter-efficient transfer learning technique for pre-trained language models that combines continuous prompt optimization with adversarial training objectives. Rather than updating all model parameters or relying on fixed, discrete text templates, this method optimizes continuous, learnable prompt embeddings prepended to the input data. By pairing prompt tuning with an adversarial training component, such as a domain discriminator, the model learns soft prompt vectors that capture domain-invariant representations while filtering out domain-specific biases. This allows language models to align feature distributions across diverse source and target domains, improving cross-domain generalization and task performance without extensive computational overhead.

1 item

Adversarial Soft Prompt Tuning for Cross-Domain Sentiment Analysis

Adversarial Soft Prompt Tuning for Cross-Domain Sentiment Analysis

Hui Wu, Xiaodong Shi

Why you should read this

Proposes an adversarial soft prompt tuning framework that combines domain-specific continuous prompts with adversarial training to learn domain-invariant representations, setting new performance benchmarks for both single- and multi-source cross-domain sentiment classification.

Cross-domain sentiment analysis has achieved promising results with the help of pre-trained language models. As GPT-3 appears, prompt tuning has been widely explored to enable better semantic modeling in many natural language processing tasks. However, directly using a fixed predefined template for cross-domain research cannot model different distributions of the [MASK] token in different domains, thus making underuse of the prompt tuning technique. In this paper, we propose a novel Adversarial Soft Prompt Tuning method (AdSPT) to better model cross-domain sentiment analysis. On the one hand, AdSPT adopts separate soft prompts instead of hard templates to learn different vectors for different domains, thus alleviating the domain discrepancy of the [MASK] token in the masked language modeling task. On the other hand, AdSPT uses a novel domain adversarial training strategy to learn domain-invariant representations between each source domain and the target domain. Experiments on a publicly available sentiment analysis dataset show that our model achieves new state-of-the-art results for both single-source domain adaptation and multi-source domain adaptation.

Added

2026-10-02