gzone0111/AutoGraphR1-musique_hotpotqa_train-qwen2.5-7b-graph-retriever-grpo
8B
•
Updated
•
9
AutoGraph-R1
Directly Optimizing Knowledge Graph Construction for RAG using Reinforcement Learning
Note Finetuned the Knowledge Graph Constructor using the Qwen/Qwen2.5-7B-Instruct model with a Knowledge Carrying Reward.
gzone0111/AutoGraphR1-musique_hotpotqa_train-qwen2.5-7b-text-retriever-grpo
8B • Updated • 8Note Finetuned the Knowledge Graph Constructor using the Qwen/Qwen2.5-7B-Instruct model with a Knowledge Indexing Reward.
gzone0111/AutoGraphR1-musique_hotpotqa_train-qwen2.5-3b-graph-retriever-grpo
3B • Updated • 7Note Finetuned the Knowledge Graph Constructor using the Qwen/Qwen2.5-3B-Instruct model with a Knowledge Carrying Reward.
gzone0111/AutoGraphR1-musique_hotpotqa_train-qwen2.5-3b-text-retriever-grpo
3B • Updated • 9Note Finetuned the Knowledge Graph Constructor using the Qwen/Qwen2.5-3B-Instruct model with a Knowledge Indexing Reward.
gzone0111/AutoGraphR1-musique_hotpotqa_train-llama3.2-3b-graph-retriever-grpo-repetition-penalty
4B • Updated • 10Note Finetuned the Knowledge Graph Constructor using the meta-llama/Llama-3.2-3B-Instruct model with a Knowledge Carrying Reward and triples repetition penalty.
gzone0111/AutoGraphR1-musique_hotpotqa_train-llama3.2-3b-text-retriever-grpo-repetition-penalty
4B • Updated • 10Note Finetuned the Knowledge Graph Constructor using the meta-llama/Llama-3.2-3B-Instruct model with a Knowledge Indexing Reward and triples repetition penalty.
gzone0111/AutoGraphR1-musique_hotpotqa_train-llama3.2-1b-graph-retriever-grpo-repetition-penalty
1B • Updated • 9Note Finetuned the Knowledge Graph Constructor using the meta-llama/Llama-3.2-1B-Instruct model with a Knowledge Carrying Reward and triples repetition penalty.
gzone0111/AutoGraphR1-musique_hotpotqa_train-llama3.2-1b-text-retriever-grpo-repetition-penalty
1B • Updated • 10Note Finetuned the Knowledge Graph Constructor using the meta-llama/Llama-3.2-1B-Instruct model with a Knowledge Indexing Reward and triples repetition penalty.
gzone0111/musique_hotpotqa_graph_retriever
Viewer • Updated • 44.7k • 7Note Dataset for training graph retriever
gzone0111/musique_hotpotqa_graph_text_retriever
Viewer • Updated • 44.7k • 25Note Dataset for training graph-based text retriever
-
AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction
Paper • 2510.15339 • Published