README.md

metadata

tags:
  - text-generation-inference
  - English
  - llama
datasets:
  - pminervini/HaluEval
language: en
license: mit

Untruthful-Llama2-7B

We induce hallucinations from the original Llama2-7B by finetuning it on selected samples from HaluEval. We then use it in our ICD method for improve factuality of LLMs and evaluate the effectiveness on TruthfulQA. More details are provided in our Github and Paper.