feat: initial CompanionGuard-RL framework

Browse Source

Two-module pipeline for AI companion safety:
- Module B: context-aware risk detector with CrossAttention fusion
- Module C: PPO-based adaptive intervention policy

Includes CompanionRisk Taxonomy (10 primary + 14 fine-grained labels),
dataset generation/annotation pipeline, training scripts, and eval suite.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

...

This commit is contained in:

wangyu

2026-05-09 17:21:11 +08:00

commit 7d4345c29d

29 changed files with 3317 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

0

experiments/.gitkeep Normal file