- Add SelfCheckGPT LLM-Prompt with OpenAI API in addition to using open-source model that has already been supported
0.1.6
Add SelfCheckGPT with LLM prompting using an open-source model (e.g., Mistral, Llama)
0.1.4
- Add SelfCheck-NLI (based on DeBERTa-v3 fine-tuned to Multi-NLI), which shows good results - Add `rescale_with_baseline` (default=True) to SelfCheck-BERTScore
0.1.3
- add SelfCheck-Ngram module into the selfcheckgpt package
0.1.2
Refactor and Add MQAG features - refactor code into SelfCheck (both SelfCheckMQAG and SelfCheckBERTScore) and MQAG - add MQAG as many functions of MQAG are used by SelfCheckMQAG - fix max_length of T5 model (there is no length limit) - add version.py
0.1.1
Currently, SelfCheckGPT includes the two variants: (1) SelfCheckGPT-MQAG and (2) SelfCheckGPT-BERTScore as described in our preprint on arxiv (dated 15 March 2023)