Pinned Loading
Repositories
Showing 10 of 83 repositories
- XTX Public
[ICLR 2022 Spotlight] Multi-Stage Episodic Control for Strategic Exploration in Text Games
- unintentional-unalignment Public
[ICLR 2025] Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
- impersona Public
- Edge-Pruning Public
[NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".
- ShortcutGrammar Public
EMNLP 2022: Finding Dataset Shortcuts with Grammar Induction https://arxiv.org/abs/2210.11560