From 19228600f14eea433c54e17c164c4efe3a029d77 Mon Sep 17 00:00:00 2001 From: haoyuren <13851610112@163.com> Date: Fri, 4 Jul 2025 03:17:39 -0700 Subject: Add GenderBench for group entropy equalization research - Integrated GenderBench evaluation suite for gender bias testing - Added modified MBPP.py for enhanced code evaluation - Setup complete for implementing gender debiasing through entropy minimization --- genderbench/docs/source/index.rst | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) create mode 100644 genderbench/docs/source/index.rst (limited to 'genderbench/docs/source/index.rst') diff --git a/genderbench/docs/source/index.rst b/genderbench/docs/source/index.rst new file mode 100644 index 0000000..2d5220c --- /dev/null +++ b/genderbench/docs/source/index.rst @@ -0,0 +1,34 @@ +.. GenderBench documentation master file, created by + sphinx-quickstart on Thu Jan 16 20:18:05 2025. + You can adapt this file completely to your liking, but it should at least + contain the root `toctree` directive. + +GenderBench Documentation +========================= + +This is the documentation for `GenderBench `_ +project. `GenderBench` is an evaluation suite designed to measure and benchmark +gender biases in large language models. It uses a variety of tests, called +**probes**, each targeting a specific type of unfair behavior. Our goal is to +cover as many types of unfair behavior as possible. + +This project has two purposes: + +1. **To publish the results we measured for various LLMs.** Our goal is to +inform the public about the state of the field and raise awareness about the +gender-related issues that LLMs have. + +2. **To allow researchers to run the benchmark on their own LLMs.** Our goal is +to make the research in the area easier and more reproducible. `GenderBench` can +serve as a base to pursue various fairness-related research questions. + +.. toctree:: + :caption: Table of Contents + :maxdepth: 2 + + quickstart + developing_probes + reports + probes + api + -- cgit v1.2.3