Cluster 654511

5 repos

Python · 2

personality ·68

politics ·68

social bias ·68

gender bias ·68

AI safety ·68

alignment ·0

text ·0

Related clusters

NCSOFT/offsetbias

Dataset Card for OffsetBias

5 commits

ZDCSlab/ripd-dataset

Overview

18 commits

ZDCSlab/Rubrics-as-an-Attack-Surface

This repository contains code for the paper "Rubrics as an Attack Surface: Stealthy Preference…

Python

20 commits

ncsoft/offsetbias

Official implementation of "OffsetBias: Leveraging Debiased Data for Tuning Evaluators"

Python

6 commits

Anthropic/model-written-evals

Model-Written Evaluation Datasets

3 commits