AI Paper Atlas

Research map / Continual learning / Domain and prompt-based

LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5

Chengwei Qin, Shafiq Joty

ICLR 2022 · Continual learning › Domain and prompt-based · approach: Prompt-based continual learning · 33 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add generated pseudo-sample replay and KL label consistency to prompt tuningPrompt tuning on NER domains · CoNLL03 + OntoNotesF1: 44.34_{\pm 0.46} -> 47.59_{\pm 2.16}Improved
add generated pseudo-sample replay and KL label consistency to prompt tuningPrompt tuning on classification domains · AGNews + Amazon + DBPedia + Yahooaccuracy: 28.47_{\pm 9.65} -> 52.71_{\pm 4.19}Improved
add generated pseudo-sample replay and KL label consistency to prompt tuningPrompt tuning on summarization domains · CNNDM + WikiHow + XSumA-RG: 15.67_{\pm 0.24} -> 17.05_{\pm 0.92}Improved
replace generated pseudo samples with randomly selected real replay samplesLFPT5 on NER domains · CoNLL03 + OntoNotesF1: 47.59_{\pm 2.16} -> 48.72_{\pm 0.9}Improved
replace generated pseudo samples with randomly selected real replay samplesLFPT5 on classification domains · AGNews + Amazon + DBPedia + Yahooaccuracy: 52.71_{\pm 4.19} -> 67.23_{\pm 1.36}Improved
replace generated pseudo samples with randomly selected real replay samplesLFPT5 on summarization domains · CNNDM + WikiHow + XSumA-RG: 17.05_{\pm 0.92} -> 17.48_{\pm 0.25}Improved
add KL label-consistency loss rather than omit it (ablation)LFPT5 on summarization · CNNDM + WikiHow + XSumA-RG: 16.27_{\pm 0.50} -> 17.11_{\pm 0.59}Improved
increase KL loss weight to 0.40 (ablation)LFPT5 on summarization · CNNDM + WikiHow + XSumA-RG: 17.11_{\pm 0.59} -> 16.26_{\pm 0.32}Hurt
use 4 pseudo samples instead of 2 (ablation)LFPT5 on summarization · CNNDM + WikiHow + XSumA-RG: 16.28_{\pm 0.95} -> 17.05_{\pm 0.92}Improved
increase pseudo samples beyond 4 (ablation)LFPT5 on summarization · CNNDM + WikiHow + XSumA-RG: 17.05_{\pm 0.92} -> 16.80_{\pm 0.52}; 16.74_{\pm 0.45}; 16.79_{\pm 0.64}Hurt
initialize new task prompts from prompts learned on a prior task (ablation)LFPT5 learning task types · Classification and summarization transferaccuracy: 84.75 -> 86.00; 67.66 -> 65.01; 22.97 -> 22.80Mixed
use separate LFPT5 task prompts rather than multitask fine-tuningLFPT5 on three task types · NER, classification, and summarizationF1: 57.81 -> 63.28; 23.36 -> 23.68; 83.25 -> 84.50Improved

Later papers that compared with this method

4 later accepted papers report LFPT5 as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy