English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Explaining the decisions of neural models is crucial for ensuring theirtrustworthiness at deployment time. Using Natural Language Explanations (NLEs)to justify a model's predictions has recently gained increasing interest.However, this approach usually demands large datasets of human-written NLEs forthe ground-truth answers, which are expensive and potentially infeasible forsome applications. For models to generate high-quality NLEs when only a fewNLEs are available, the fine-tuning of Pre-trained Language Models (PLMs) inconjunction with prompt-based learning recently emerged. However, PLMstypically have billions of parameters, making fine-tuning expensive. We proposeSparseFit, a sparse few-shot fine-tuning strategy that leverages discreteprompts to jointly generate predictions and NLEs. We experiment with SparseFiton the T5 model and four datasets and compare it against state-of-the-artparameter-efficient fine-tuning techniques. We perform automatic and humanevaluations to assess the quality of the model-generated NLEs, finding thatfine-tuning only 6.8% of the model parameters leads to competitive results forboth the task performance and the quality of the NLEs.

SPARSEFIT: Few-shot Prompting with Sparse Fine-tuning for Jointly Generating Predictions and Natural Language Explanations