Pith. sign in

REVIEW 1 cited by

Measuring the Instability of Fine-Tuning

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 2302.07778 v2 pith:JLBJ4O62 submitted 2023-02-15 cs.CL

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

Fine-tuning pre-trained language models on downstream tasks with varying random seeds has been shown to be unstable, especially on small datasets. Many previous studies have investigated this instability and proposed methods to mitigate it. However, most studies only used the standard deviation of performance scores (SD) as their measure, which is a narrow characterization of instability. In this paper, we analyze SD and six other measures quantifying instability at different levels of granularity. Moreover, we propose a systematic framework to evaluate the validity of these measures. Finally, we analyze the consistency and difference between different measures by reassessing existing instability mitigation methods. We hope our results will inform the development of better measurements of fine-tuning instability.

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. Full citation record

  1. A gentle push funziona benissimo: making instructed models in Italian via contrastive activation steering

    cs.CL 2024-11 conditional novelty 5.0 of 10

    Contrastive activation steering on about 30 Italian prompts matches or beats instruction fine-tuning for Italian on MMLU, HellaSwag, and ARC, with markedly higher Italian language consistency.

Pith tools