Pith. sign in

REVIEW

What Makes Pre-trained Language Models Better Zero-shot Learners?

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 2209.15206 v3 pith:P22EMWPX submitted 2022-09-30 cs.CL cs.AI

What Makes Pre-trained Language Models Better Zero-shot Learners?

classification cs.CL cs.AI
keywords promptzero-shottemplatesdatalabelledlanguagemethodperformance
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Current methods for prompt learning in zeroshot scenarios widely rely on a development set with sufficient human-annotated data to select the best-performing prompt template a posteriori. This is not ideal because in a realworld zero-shot scenario of practical relevance, no labelled data is available. Thus, we propose a simple yet effective method for screening reasonable prompt templates in zero-shot text classification: Perplexity Selection (Perplection). We hypothesize that language discrepancy can be used to measure the efficacy of prompt templates, and thereby develop a substantiated perplexity-based scheme allowing for forecasting the performance of prompt templates in advance. Experiments show that our method leads to improved prediction performance in a realistic zero-shot setting, eliminating the need for any labelled examples.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.