kmorhun/model-faithfulness

stars

commits

Python

primary language

Dec 15, 2023

updated

README

model-faithfulness

This is an NLP research project testing if GPT-4 is faithful to its explanations on classification tasks. It contains all the code, inputs, outputs, and a results analysis document.

Contributors

zackdui

39 commits

kmorhun

28 commits

bstankovits

5 commits

Similar repos

vasilisvyth/Reasoning-for-text-retrieval

christopheradriankusuma/detectgpt

bamaxi/agreement-probing

trestad/Factual-Recall-Mechanism

The code for paper Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language…

IdaCy/CoTFaithChecker

AnMaJ/LASR-Analysing-Faithfulness-of-Reasoning-to-Internal-Concepts

Repo for LASR project with Noah on Analysing Faithfulness of Reasoning to Internal Concepts

ouhenio/llms-overstimate-profoundness

salvatorpes/zero-shot-llm-detection

Code for the AI vs Human generated text Detection task using zero-shot approaches under the Deep…

Languages

Python

100.0%