Pinned Loading

1. naver/gdc naver/gdc Public

   Code accompanying our papers on the "Generative Distributional Control" framework

   Python 118 20

2. ThinkPRM ThinkPRM Public

   [TMLR] Process Reward Models That Think

   Python 89 9

3. GRACE GRACE Public

   [EMNLP '23] Discriminator-Guided Chain-of-Thought Reasoning

   Python 50 2

4. intrinsic-source-citation intrinsic-source-citation Public

   [COLM '24] Source-Aware Training Enables Knowledge Attribution in Language Models

   Python 19

5. zohaib-khan5040/Countdown-Code zohaib-khan5040/Countdown-Code Public

   A testbed for studying the emergence and generalization of reward hacking

   Python 9 4

6. xlm-roberta-ner xlm-roberta-ner Public

   Named Entity Recognition with Pretrained XLM-RoBERTa

   Python 93 28