TruthfulQA
Truth detector
Evaluating model performance on human falsehoods in language models
TruthfulQA: Measuring How Models Imitate Human Falsehoods
631 stars
8 watching
74 forks
Language: Jupyter Notebook
last commit: almost 3 years agoRelated projects:
| Repository | Description | Stars |
|---|---|---|
 rowanz/grover | A framework for defending against neural fake news through both generation and detection of fake news articles. | 918 |
 findalexli/scigraphqa | A dataset and benchmarking framework for evaluating the performance of large language models on multi-turn question answering tasks for scientific graphs. | 38 |
 nyu-mll/bbq | A dataset and benchmarking framework to evaluate the performance of question answering models on detecting and mitigating social biases. | 92 |
 gair-nlp/factool | An open-source framework for detecting factual errors in AI-generated text | 839 |
 0x4d31/deception-as-detection | Maps deception detection techniques to the ATT&CK framework and provides documentation for security professionals | 287 |
 adoreste/truehunter | Detects encrypted files using a fast and memory efficient approach without external dependencies. | 30 |
 jiasenlu/hiecoattenvqa | A framework for training Hierarchical Co-Attention models for Visual Question Answering using preprocessed data and a specific image model. | 349 |
 strongqa/howitzer | A Ruby-based framework for acceptance testing with flexibility and scalability for different testing tools and cloud services. | 261 |
 yosefk/checkedthreads | A parallelism framework that detects and prevents race conditions in multithreaded code by automatically load balancing and using Valgrind-based instrumentation. | 290 |
 truera/trulens | A tool to evaluate and track the performance of large language model (LLM) experiments | 2,233 |
 masaiahhan/correlationqa | An investigation into the relationship between misleading images and hallucinations in large language models | 8 |
 rifkybujana/fnd | An AI-powered tool that detects whether news articles are fake or not | 8 |
 ai4risk/antifraud | Develops and evaluates machine learning models for detecting financial fraud | 195 |
 jagilley/fact-checker | A tool for fact-checking LLM outputs with self-ask using prompt chaining | 289 |
 yg-smile/rl_vvc_dataset | A collection of benchmarks and implementations for testing reinforcement learning-based Volt-VAR control algorithms | 20 |