REVIEW 7 cited by
Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning
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
abstract
Few-shot in-context learning (ICL) enables pre-trained language models to perform a previously-unseen task without any gradient-based training by feeding a small number of training examples as part of the input. ICL incurs substantial computational, memory, and storage costs because it involves processing all of the training examples every time a prediction is made. Parameter-efficient fine-tuning (PEFT) (e.g. adapter modules, prompt tuning, sparse update methods, etc.) offers an alternative paradigm where a small set of parameters are trained to enable a model to perform the new task. In this paper, we rigorously compare few-shot ICL and PEFT and demonstrate that the latter offers better accuracy as well as dramatically lower computational costs. Along the way, we introduce a new PEFT method called (IA)$^3$ that scales activations by learned vectors, attaining stronger performance while only introducing a relatively tiny amount of new parameters. We also propose a simple recipe based on the T0 model called T-Few that can be applied to new tasks without task-specific tuning or modifications. We validate the effectiveness of T-Few on completely unseen tasks by applying it to the RAFT benchmark, attaining super-human performance for the first time and outperforming the state-of-the-art by 6% absolute. All of the code used in our experiments is publicly available.
Forward citations
Cited by 7 Pith papers
-
Can Gradient Descent Simulate Prompting?
A MAML-style meta-training objective makes a single gradient step on new text recover part of the performance that prompting achieves, on reversal-curse and passage-QA tasks.
-
From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Models
Frozen CogVideoX1.5, adapted with LoRA on 3 to 30 input-output videos, performs segmentation, pose estimation, and abstract reasoning (ARC-AGI 16.75%) with modest but real generalization.
-
Limited-Resource Adapters Are Regularizers, Not Linguists
Randomly initialized adapters match linguistically selected adapters in low-resource Creole MT, suggesting adapter gains here are regularization, not transfer.
-
Can Smaller LLMs do better? Unlocking Cross-Domain Potential through Parameter-Efficient Fine-Tuning for Text Summarization
PEFT adapters trained on high-resource summarization domains can improve Llama-3-8B's summaries on unseen domains, but the reported gains are weakened by test-set selection and missing significance tests.
-
LARA: Lightweight Adapters in the Residual Stream for Composable Adaptation and Alignment
Low-rank residual-stream adapters match LoRA at near-equal parameter counts on code fine-tuning and DPO, and support inference-time scaling plus per-token routing of seven behaviors on one frozen 1.5B model.
-
15,500 Seconds: Lean UAV Classification Using EfficientNet and Lightweight Fine-Tuning
On a private 3,100-clip, 31-class drone audio dataset, full fine-tuning of EfficientNet-B0 with three augmentations reached 95.95% validation accuracy, the best of all compared models and PEFT methods.
-
The Hitchhiker's Guide to Agentic AI: From Foundations to Systems
A survey-style reference book mapping the full agentic-AI stack from transformer internals to production deployment, with no new research result.
Discussion (0). Continue with ORCID to comment.