conftrace_

pairwise accuracy

4 papers

Explore in graph

Also known as

PA

Co-occurring keywords · papers mentioning both

human evaluation (3) evaluation metric (3) statistical significance (2) machine translation (2) score magnitude (1) automatic metric (1) instruction-tuned llm (1) instruction-tuned language model (1) kendall tau (1) correlation metric (1)

Papers

How Reliable Are Automatic Evaluation Methods for Instruction-Tuned LLMs? EMNLP 2024 Improving Statistical Significance in Human Evaluation of Automatic Metrics via Soft Pairwise Accuracy EMNLP 2024 Navigating the Metrics Maze: Reconciling Score Magnitudes and Accuracies ACL 2024 Ties Matter: Meta-Evaluating Modern Metrics with Pairwise Accuracy and Tie Calibration EMNLP 2023