A research work utilizes sparse auto-encoders (SAEs) to enhance the usage of both contextual and parametric knowledge in Large Language Models. This work uses Exact Match as a metric and is evaluated on the NQSwap and Macnoise datasets.

Authors

• Person: Not available Organization: GitHub
  EdinburghNLP/awesome-hallucination-detection - GitHub

Sources

• EdinburghNLP/awesome-hallucination-detection - GitHub github.com GitHub via serper

Referenced by nodes (1)

• Large Language Models concept