Research map / Architectures and efficiency / Pruning and efficient tuning
On the Effectiveness of Parameter-Efficient Fine-Tuning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use SAM parameter selection instead of Adapter | RoBERTa-base · CoLA | score: 62.11 -> 60.89 | Hurt |
| Use SAM parameter selection instead of MagPruning | RoBERTa-base · STS-B | score: 90.30 -> 90.59 | Helped |
| Use SAM parameter selection instead of FullTuning | RoBERTa-base · MRPC | score: 89.55 -> 88.84 | Hurt |
| Use SAM parameter selection instead of MixOut | RoBERTa-base · RTE | score: 77.55 -> 76.79 | Hurt |
| Use SAM parameter selection instead of Random | RoBERTa-base · CB | score: 90.54 -> 88.93 | Hurt |
| Use SAM parameter selection instead of DiffPruning | RoBERTa-base · COPA | score: 72.10 -> 74.30 | Helped |
| Use SAM parameter selection instead of MagPruning | RoBERTa-base · WSC | score: 55.67 -> 59.52 | Helped |
| Use SAM parameter selection instead of Adapter | RoBERTa-base · AVG | average score: 76.03 -> 77.12 | Helped |
| Decrease the SAM tunable-parameter sparsity ratio (ablation) | SAM · GLUE and SuperGLUE tasks | score | Mixed |
| Adjust the DiffPruning mask during training | DiffPruning · CB | training error | Hurt |
Closest papers by meaning
- Linearization Explains Fine-Tuning in Large Language Models (NeurIPS 2025 · similarity 0.90)
- Data Mixing Optimization for Supervised Fine-Tuning of Large Language Models (ICML 2025 · similarity 0.90)
- Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs (ICLR 2024 · similarity 0.89)
- Data Efficient Adaptation in Large Language Models via Continuous Low-Rank Fine-Tuning (NeurIPS 2025 · similarity 0.89)
- Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark (ICML 2024 · similarity 0.89)
- SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models (ICML 2024 · similarity 0.89)
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.