potsawee/selfcheckgpt issues and pull requests

#32 - Could you provide a example of showing the AUC-PR of your own methods(i.e. the selfcheckgpt) just like the probability-based-baselines?

Issue - State: open - Opened by goatyu3 3 months ago - 2 comments

#31 - Add support for Groq's API

Pull Request - State: closed - Opened by WladimirLct 4 months ago

#30 - Added demo notebook to detect hallucination score for a given query and LLM

Pull Request - State: closed - Opened by Kirushikesh 4 months ago

#29 - What are these 2 numbers means in the example result

Issue - State: open - Opened by orriduck 5 months ago - 3 comments

#28 - Question about random baseline

Issue - State: closed - Opened by WWWonderer 5 months ago - 2 comments

#27 - Add SelfCheckGPT-prompt with OpenAI API

Pull Request - State: closed - Opened by potsawee 6 months ago

#26 - Possible annotation errors?

Issue - State: open - Opened by pramitchoudhary 7 months ago - 1 comment

#25 - Feedback: Adding Notebook for R and S generation by LLM

Issue - State: closed - Opened by Kirushikesh 7 months ago - 3 comments

#24 - Questions about the SelfCheckGPT-NLI and SelfCheckGPT-Prompt

Issue - State: closed - Opened by hbr690188270 7 months ago - 3 comments

#23 - merge LLM prompt implementation

Pull Request - State: closed - Opened by potsawee 7 months ago

#22 - can't find wiki_bio_test_idx indices in the original wikibio test set

Issue - State: closed - Opened by tuvllms 9 months ago - 3 comments

#21 - about passage-level human annotations

Issue - State: closed - Opened by 141forever 9 months ago - 3 comments

#20 - Which version of LLaMA model is used?

Issue - State: closed - Opened by Moximixi 10 months ago - 1 comment

#19 - When I run the latest version of 'probability-baselines.ipynb', there is an error. Could you please provide the full version number of the experimental environment?

Issue - State: closed - Opened by Moximixi 10 months ago - 3 comments

#18 - Can you provide the datasets in the probability-baselines.ipynb file?

Issue - State: closed - Opened by Moximixi 10 months ago - 2 comments

#17 - Contradiction Threshold for NLI Approach

Issue - State: closed - Opened by ktangri 12 months ago - 2 comments

#16 - Could you provide an example of using ngram to predict the factuality of a sentence?

Issue - State: open - Opened by Amano-Aki about 1 year ago - 1 comment

#15 - How to combine the three variants of selfcheckgpt in your paper?

Issue - State: open - Opened by dhx20150812 about 1 year ago - 6 comments

#14 - Open Question: Fact Checking LLM

Issue - State: closed - Opened by GvdDool about 1 year ago - 4 comments

#13 - Is this method actually useful in the real world?

Issue - State: closed - Opened by YooSungHyun about 1 year ago - 3 comments

#12 - How long would it usually take to run all three score?

Issue - State: closed - Opened by yihan-zhou about 1 year ago - 2 comments

#11 - What's the meaning of β in Appendix B?

Issue - State: closed - Opened by coderlemon17 about 1 year ago - 4 comments

#10 - range of selfcheck_bertscore

Issue - State: closed - Opened by EngSalem about 1 year ago - 2 comments

#9 - Can you provide the name list that is used for creating the dataset.

Issue - State: closed - Opened by soap117 about 1 year ago - 1 comment

#8 - Update README.md

Pull Request - State: closed - Opened by adianliusie over 1 year ago

#7 - ngram experiment

Pull Request - State: closed - Opened by potsawee over 1 year ago

#6 - code for selfcheck n-gram

Issue - State: closed - Opened by potsawee over 1 year ago

#5 - code for proxy model

Issue - State: closed - Opened by zthang over 1 year ago - 2 comments

#4 - Update README.md