Skip to content

Prompt Learning

Definition
AI-generated

Prompt learning (often overlapping with prompt tuning or prefix tuning) trains learnable prompt parameters—continuous vectors prepended or inserted into the model input—so that a frozen or lightly updated large model adapts to a task without full fine-tuning of all weights.

Topics
LLM and Agents
Synonyms
Prompt tuning (closely related)
Related
Foundation Model In-Context Learning Large Language Model (LLM)

Why it matters in GWAS

Parameter-efficient adaptation may be used to specialize general biomedical or coding LLMs on ontology mapping, methods extraction, or structured report generation with smaller labeled sets; like any learned component, trained prompts should be versioned, evaluated on held-out curated examples, and documented alongside base model checkpoints.

Example usage

"A replication analysis checks whether assumptions tied to Prompt Learning hold across cohorts."

Foundation Model In-Context Learning Large Language Model (LLM) Prompt Prompt Engineering
Related-term network

Click any node to open that term page.

Node order. The current term is first. Next come every page linked from Related terms, in the same top-to-bottom order as that list. Then new terms appear in two-hop layers: for each of those direct neighbors (in that same order), their related terms are appended if not already listed. A third pass does the same for two-hop nodes. The walk stops when a fixed maximum number of nodes is reached.

References

  • Liu P, et al. (2023). Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. ACM Comput Surv.
  • Lester B, Al-Rfou R, Constant N. (2021). The power of scale for parameter-efficient prompt tuning. arXiv:2104.08691.
← Prompt Engineering Properly paired reads →

Last updated (UTC · Git history)