Papers › Control Prefixes for Parameter-Efficient Text Generation
Control Prefixes for Parameter-Efficient Text Generation
Jordan Clive, Kris Cao, Marek Rei
Prefix-tuning is a powerful lightweight technique for adapting a large pre-trained language model to a downstream application. However, it uses the same dataset-level tuned prompt for all examples in the dataset. We extend this idea and propose a dynamic method, Control Prefixes, which allows for the inclusion of conditional input-dependent information, combining the benefits of prompt tuning and controlled generation. The method incorporates attribute-level learnable representations into different layers of a pre-trained transformer, allowing for the generated text to be guided in a particular direction. We provide a systematic evaluation of the technique and apply it to five datasets from the GEM benchmark for natural language generation (NLG). Although the aim is to develop a parameter-efficient model, we show Control Prefixes can even outperform full fine-tuning methods. We present state-of-the-art results on several data-to-text datasets, including WebNLG.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Data-to-Text Generation | Cleaned E2E NLG Challenge | Control Prefixes (T5-large) | BLEU (Test set) | 44.15 | #1 of 7 | Archive leaderboard | report |
| Data-to-Text Generation | WebNLG | Control Prefixes (A1, T5-large) | BLEU | 67.32 | #1 of 20 | Archive leaderboard | report |
| Data-to-Text Generation | WebNLG | Control Prefixes (A1, A2, T5-large) | BLEU | 67.15 | #2 of 20 | Archive leaderboard | report |
| Data-to-Text Generation | WebNLG Full | Control Prefixes (A1, A2, T5-large) | BLEU | 62.27 | #1 of 8 | Archive leaderboard | report |
| Data-to-Text Generation | WebNLG Full | Control Prefixes (A1, T5-large) | BLEU | 61.94 | #2 of 8 | Archive leaderboard | report |
| Text Generation | DART | Control Prefixes (T5-large) | METEOR | 0.411 | #5 of 7 | Archive leaderboard | report |
| Text Simplification | ASSET | Control Prefixes (BART) | FKGL | 5.97 | #3 of 12 | Archive leaderboard | report |
| Text Simplification | ASSET | Control Prefixes (BART) | QuestEval (Reference-less, BERTScore) | 0.64 | #3 of 12 | Archive leaderboard | report |
| Text Simplification | ASSET | Control Prefixes (BART) | SARI (EASSE>=0.2.1) | 43.58 | #3 of 12 | Archive leaderboard | report |
| Text Simplification | TurkCorpus | Control Prefixes (BART) | FKGL | 7.74 | #3 of 25 | Archive leaderboard | report |
| Text Simplification | TurkCorpus | Control Prefixes (BART) | QuestEval (Reference-less, BERTScore) | 0.66 | #3 of 25 | Archive leaderboard | report |
| Text Simplification | TurkCorpus | Control Prefixes (BART) | SARI (EASSE>=0.2.1) | 42.32 | #3 of 25 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
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