matt-seb-ho / WikiWhyLinks
WikiWhy is a new benchmark for evaluating LLMs' ability to explain between cause-effect relationships. It is a QA dataset containing 9000+ "why" question-answer-rationale triplets.
☆47Updated last year
Alternatives and similar repositories for WikiWhy
Users that are interested in WikiWhy are comparing it to the libraries listed below
Sorting:
- ☆28Updated last year
- ☆87Updated 2 years ago
- First explanation metric (diagnostic report) for text generation evaluation☆62Updated 3 months ago
- Github repository for "FELM: Benchmarking Factuality Evaluation of Large Language Models" (NeurIPS 2023)☆59Updated last year
- ☆41Updated last year
- Official implementation of the ACL 2023 paper: "Zero-shot Faithful Factual Error Correction"☆17Updated last year
- This repository contains the dataset and code for "WiCE: Real-World Entailment for Claims in Wikipedia" in EMNLP 2023.