SelfCheckGPT
Code for our paper “SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models”, https://arxiv.org/abs/2303.08896
More information can be found on our project page: https://github.com/potsawee/selfcheckgpt
Installation
pip install selfcheckgpt
SelfCheckGPT Usage
See more details in Jupyter Notebook: https://github.com/potsawee/selfcheckgpt/blob/main/demo/SelfCheck_demo1.ipynb
from selfcheckgpt.modeling_selfcheck import SelfCheckMQAG, SelfCheckBERTScore
selfcheck_mqag = SelfCheckMQAG()
selfcheck_bertscore = SelfCheckBERTScore()
sent_scores_mqag = selfcheck_mqag.predict(
sentences,
passage,
[sample1, sample2, sample3],
num_questions_per_sent = 5,
scoring_method = 'bayes_with_alpha',
beta1 = 0.8, beta2 = 0.8,
)
sent_scores_bertscore = selfcheck_bertscore.predict(
sentences,
[sample1, sample2, sample3],
)MQAG Usage
See more details in Jupyter Notebook: https://github.com/potsawee/selfcheckgpt/blob/main/demo/MQAG_demo1.ipynb
from selfcheckgpt.modeling_mqag import MQAG
mqag_model = MQAG()1 maintainer
Metadata
1 maintainer
Release files for selfcheckgpt 0.1.7
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| selfcheckgpt-0.1.7.tar.gz | 16.7 kB | Without provenance | Details for selfcheckgpt-0.1.7.tar.gz |
Release files / selfcheckgpt-0.1.7.tar.gz
| Download URL | selfcheckgpt-0.1.7.tar.gz |
|---|---|
| Size | 16.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
38568c38d9398c61976a2739e752e780c759189175f5a1f62c5b58a2d761c706
|
|
BLAKE2b-256 checksum How to use checksums |
f8cbb4c3d96b5df9dfff6bb938d0690011a337880708be20c82f87e4ba7a093d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.8.13
|
Security for selfcheckgpt 0.1.7
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
