Pith. sign in

REVIEW 2 cited by

PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation

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 2208.10160 v2 pith:7PPA3CJL submitted 2022-08-22 cs.CL

classification cs.CL
keywords promptapproachpandaknowledgesourcetargetdistillationforgetting
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Prompt Transfer (PoT) is a recently-proposed approach to improve prompt-tuning, by initializing the target prompt with the existing prompt trained on similar source tasks. However, such a vanilla PoT approach usually achieves sub-optimal performance, as (i) the PoT is sensitive to the similarity of source-target pair and (ii) directly fine-tuning the prompt initialized with source prompt on target task might lead to forgetting of the useful general knowledge learned from source task. To tackle these issues, we propose a new metric to accurately predict the prompt transferability (regarding (i)), and a novel PoT approach (namely PANDA) that leverages the knowledge distillation technique to alleviate the knowledge forgetting effectively (regarding (ii)). Extensive and systematic experiments on 189 combinations of 21 source and 9 target datasets across 5 scales of PLMs demonstrate that: 1) our proposed metric works well to predict the prompt transferability; 2) our PANDA consistently outperforms the vanilla PoT approach by 2.3% average score (up to 24.1%) among all tasks and model sizes; 3) with our PANDA approach, prompt-tuning can achieve competitive and even better performance than model-tuning in various PLM scales scenarios. We have publicly released our code in https://github.com/WHU-ZQH/PANDA.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing

    cs.AI 2025-05 conditional novelty 6.0 of 10

    BalancEdit stores edits in a discrete codebook and sets each edit's influence radius from a rephrased positive sample and a black-image negative sample, balancing generality and locality better than prior editing base...

  2. Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition

    cs.CL 2025-04 conditional novelty 4.0 of 10

    A two-stage prompting method where a large model generates solution steps and a smaller model follows them; GSM8K gains are significant, MATH gains are not.

Pith tools