jiazhengli/Rationale_MCTS
Viewer
•
Updated
•
8.71k
•
31
•
1
MCTS with Preference Optimisation
Resources for EMNLP 2024 Paper: Calibrating LLMs with Preference Optimization on Thought Trees for Generating Rationale in Science Question Scoring
-
-
jiazhengli/Synthetic_Rationale
Viewer • Updated • 32.9k • 42 -
jiazhengli/deberta-v3-large-Rationale-to-Score
Text Classification • Updated • 8 -
jiazhengli/Meta-Llama-3-8B-QLoRA-Assessment-Rationale-sft
Updated • 3 -
jiazhengli/Meta-Llama-3-8B-QLoRA-Assessment-Rationale-dpo
Updated • 8 -
jiazhengli/Mixtral-8x7B-Instruct-v0.1-QLoRA-Assessment-Rationale-sft
Updated • 4 -
jiazhengli/Mixtral-8x7B-Instruct-v0.1-QLoRA-Assessment-Rationale-dpo
Updated • 2 -
Calibrating LLMs with Preference Optimization on Thought Trees for Generating Rationale in Science Question Scoring
Paper • 2406.19949 • Published • 1