reference
The paper 'Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources' uses Exact Match as an evaluation metric and evaluates performance on the FEVER and Adversarial HotpotQA datasets.
Authors
Sources
- EdinburghNLP/awesome-hallucination-detection - GitHub github.com via serper
Referenced by nodes (2)
- fever concept
- Exact Match concept