Pith. sign in

REVIEW 1 cited by

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

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2212.10391 v2 pith:6YYTC2PX submitted 2022-12-20 cs.CL

classification cs.CL
keywords labelembeddingralpsentenceclassificationretrievalsemanticallytext
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 3 citations worldwide. Full citation record

  1. Scalable Semantic Steering of Embedding Projections

    cs.HC 2026-07 conditional novelty 6.0 of 10

    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.

Pith tools