This systematic survey organizes prompt engineering into a taxonomy of 58 LLM techniques and 40 others, supplies a shared vocabulary, and offers guidelines for state-of-the-art models.
arXiv preprint arXiv:2303.13809 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CL 3representative citing papers
LLMs show strong position bias when scoring model outputs, allowing easy manipulation of rankings, but calibration with multiple evidence, position balancing, and selective human input reduces this bias to better match human judgments.
A reference-free proxy scoring framework combined with GIRB calibration produces better-aligned evaluation metrics for summarization and outperforms baselines across seven datasets.
citing papers explorer
-
The Prompt Report: A Systematic Survey of Prompt Engineering Techniques
This systematic survey organizes prompt engineering into a taxonomy of 58 LLM techniques and 40 others, supplies a shared vocabulary, and offers guidelines for state-of-the-art models.
-
Large Language Models are not Fair Evaluators
LLMs show strong position bias when scoring model outputs, allowing easy manipulation of rankings, but calibration with multiple evidence, position balancing, and selective human input reduces this bias to better match human judgments.
-
Calibrating Model-Based Evaluation Metrics for Summarization
A reference-free proxy scoring framework combined with GIRB calibration produces better-aligned evaluation metrics for summarization and outperforms baselines across seven datasets.