Methods › Natural Language Processing › Language Models › ULMFiT

Universal Language Model Fine-tuning

ULMFiT

40 papers tagged archive 2025-07-28

Introduced by Jeremy Howard et al. in Universal Language Model Fine-tuning for Text Classification

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Universal Language Model Fine-tuning, or ULMFiT, is an architecture and transfer learning method that can be applied to NLP tasks. It involves a 3-layer AWD-LSTM architecture for its representations. The training consists of three steps: 1) general language model pre-training on a Wikipedia-based text, 2) fine-tuning the language model on a target task, and 3) fine-tuning the classifier on the target task.

As different layers capture different types of information, they are fine-tuned to different extents using discriminative fine-tuning. Training is performed using Slanted triangular learning rates (STLR), a learning rate scheduling strategy that first linearly increases the learning rate and then linearly decays it.

Fine-tuning the target classifier is achieved in ULMFiT using gradual unfreezing. Rather than fine-tuning all layers at once, which risks catastrophic forgetting, ULMFiT gradually unfreezes the model starting from the last layer (i.e., closest to the output) as this contains the least general knowledge. First the last layer is unfrozen and all unfrozen layers are fine-tuned for one epoch. Then the next group of frozen layers is unfrozen and fine-tuned and repeat, until all layers are fine-tuned until convergence at the last iteration.

PaperSource

In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 40 · with a code link: 17 · where Syntology ran a sample: 1 (0 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (1 of 40 tagged: 0 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 40 of 40, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 51 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Transfer Learning14
General Classification12
Language Modelling12
Text Classification12
Language Modeling11
Sentiment Analysis9
text-classification8
Classification7
Decision Making3
Hate Speech Detection3
Sentiment Classification3
BIG-bench Machine Learning2
Language Identification2
Management2
Marketing2
Sentence2
Text Categorization2
Transliteration2
Word Embeddings2
regression2

Usage over time archive 2025-07-28

Papers per year tagged with ULMFiT: 2018 to 2025, peak 13 13 0 2018: 1 paper 2018 2019: 12 papers 2019 2020: 13 papers 2020 2021: 8 papers 2021 2022: 1 paper 2022 2023: 2 papers 2023 2024: 2 papers 2024 2025: 1 paper 2025
Papers per year the archive tags with this method, by the paper's archive date (40 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Language Models

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections