# HKUNLP/critic-rl

<https://repo.masters-masters.com/en/repos/HKUNLP/critic-rl>

[Home](https://repo.masters-masters.com/en) › [HKUNLP](https://repo.masters-masters.com/en/owners/HKUNLP) › [critic-rl](https://repo.masters-masters.com/en/repos/HKUNLP/critic-rl)

HKUNLP/critic-rl has 125 stars on GitHub. Its RepoMasters card: Prototype tier. \[ICML 2025\] Teaching Language Models to Critique via Reinforcement Learning

| Field | Value |
| --- | --- |
| Owner | [HKUNLP](https://repo.masters-masters.com/en/owners/HKUNLP) |
| Stars | 125 |
| Forks | 7 |
| Language | [Python](https://repo.masters-masters.com/en/languages/python) |
| License | Apache-2.0 |
| Created | 2025 |
| Tier | [Prototype (100 to 249 ★)](https://repo.masters-masters.com/en/ranks/rush) |
| View on GitHub | [HKUNLP/critic-rl](https://github.com/HKUNLP/critic-rl) |

## Repository

\[ICML 2025\] Teaching Language Models to Critique via Reinforcement Learning

The tier for repos with 100 to 249 ★. Published odds per card pulled: 70%. Rarity: Common.

## More repos by HKUNLP

- [HKUNLP/ChunkLlama · ★ 451 · Python · Alpha](https://repo.masters-masters.com/en/repos/HKUNLP/ChunkLlama)
- [HKUNLP/DiffuLLaMA · ★ 407 · Python · Alpha](https://repo.masters-masters.com/en/repos/HKUNLP/DiffuLLaMA)
- [HKUNLP/diffusion-of-thoughts · ★ 213 · Python · Prototype](https://repo.masters-masters.com/en/repos/HKUNLP/diffusion-of-thoughts)
- [HKUNLP/HumanPrompt · ★ 130 · Python · Prototype](https://repo.masters-masters.com/en/repos/HKUNLP/HumanPrompt)
- [HKUNLP/reparam-discrete-diffusion · ★ 108 · Python · Prototype](https://repo.masters-masters.com/en/repos/HKUNLP/reparam-discrete-diffusion)
- [HKUNLP/icl-ceil · ★ 105 · Python · Prototype](https://repo.masters-masters.com/en/repos/HKUNLP/icl-ceil)

## Nearby in Python

- [yuzushi-dev/hermes-seo · ★ 125 · Python · Prototype](https://repo.masters-masters.com/en/repos/yuzushi-dev/hermes-seo)
- [ilAoC/mcd-gacha-collector · ★ 125 · Python · Prototype](https://repo.masters-masters.com/en/repos/ilAoC/mcd-gacha-collector)
- [adhiprib/humanizer-indonesia · ★ 125 · Python · Prototype](https://repo.masters-masters.com/en/repos/adhiprib/humanizer-indonesia)
- [dokterbob/django-agenda · ★ 125 · Python · Prototype](https://repo.masters-masters.com/en/repos/dokterbob/django-agenda)
- [garethr/django-project-templates · ★ 125 · Python · Prototype](https://repo.masters-masters.com/en/repos/garethr/django-project-templates)
- [jezdez/django-staticfiles · ★ 125 · Python · Prototype](https://repo.masters-masters.com/en/repos/jezdez/django-staticfiles)

---
Data: GitHub · Illustration drawn by RepoMasters from the repo’s ID and its language color.