Pith. sign in

Empowering Sentence Encoders with Prompting and Label Retrieval for Zero-shot Text Classification

1 Pith paper cite this work, alongside 3 external citations. Polarity classification is still indexing.

1 Pith paper citing it
3 external citations · Pith
abstract

With contrastive pre-training, sentence encoders are generally optimized to locate semantically similar samples closer to each other in their embedding spaces. In this work, we focus on the potential of their embedding spaces to be readily adapted to zero-shot text classification, as semantically distinct samples are already well-separated. Our framework, RaLP (Retrieval augmented Label Prompts for sentence encoder), encodes prompted label candidates with a sentence encoder, then assigns the label whose prompt embedding has the highest similarity with the input text embedding. In order to compensate for the potentially poorly descriptive labels in their original format, RaLP retrieves sentences that are semantically similar to the original label prompt from external corpora and use them as additional pseudo-label prompts. RaLP achieves competitive or stronger performance than much larger baselines on various closed-set classification and multiple-choice QA datasets under zero-shot settings. We show that the retrieval component plays a pivotal role in RaLP's success, and its results are robustly attained regardless of verbalizer variations.

fields

cs.HC 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

Scalable Semantic Steering of Embedding Projections

cs.HC · 2026-07-04 · conditional · novelty 6.0

Group-level hybrid prototypes from one LLM call match per-item LLM steering quality on LitCovid while reducing LLM cost by over three orders of magnitude.

citing papers explorer

Showing 1 of 1 citing paper.

  • Scalable Semantic Steering of Embedding Projections cs.HC · 2026-07-04 · conditional · none · ref 10 · internal anchor

    Group-level hybrid prototypes from one LLM call match per-item LLM steering quality on LitCovid while reducing LLM cost by over three orders of magnitude.