Pith. sign in

REVIEW 1 cited by

An Empirical Study on Few-shot Knowledge Probing for Pretrained Language Models

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 2109.02772 v2 pith:XVG2NR6Y submitted 2021-09-06 cs.AI

classification cs.AI
keywords knowledgeprobingfew-shotrelationsavailabledatasetexistinglanguage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Prompt-based knowledge probing for 1-hop relations has been used to measure how much world knowledge is stored in pretrained language models. Existing work uses considerable amounts of data to tune the prompts for better performance. In this work, we compare a variety of approaches under a few-shot knowledge probing setting, where only a small number (e.g., 10 or 20) of example triples are available. In addition, we create a new dataset named TREx-2p, which contains 2-hop relations. We report that few-shot examples can strongly boost the probing performance for both 1-hop and 2-hop relations. In particular, we find that a simple-yet-effective approach of finetuning the bias vectors in the model outperforms existing prompt-engineering methods. Our dataset and code are available at \url{https://github.com/cloudygoose/fewshot_lama}.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Noise or Nuance: An Investigation Into Useful Information and Filtering For LLM Driven AKBC

    cs.CL 2025-09 conditional novelty 5.0 of 10

    In a no-retrieval, no-fine-tuning setting, LLM-provided hints, self-judging filters, and regex-based parsing substantially change triple completion quality, with the judge filter roughly doubling F1.

Pith tools