ChatR1: Reinforcement Learning for Conversational Reasoning and Retrieval Augmented Question Answering
Paper • 2510.13312 • Published • 1
ChatR1
[Main ACL 2026] Corpus, Index, and dataset to train ChatR1.
-
-
slupart/topiocqa-e5-index
Updated • 35 -
slupart/topiocqa-collection
Viewer • Updated • 25.7M • 28 -
slupart/qrecc-e5-index
Updated • 26 -
slupart/multidoc2dial-e5-index
Updated • 31 -
slupart/inscit-e5-index
Updated • 27 -
slupart/multidoc2dial-collection
Viewer • Updated • 10.2k • 26 -
slupart/inscit-collection
Viewer • Updated • 49.2M • 24 -
slupart/qrecc-passages
Viewer • Updated • 54.6M • 426 • 2 -
PeterJinGo/wiki-18-e5-index
Updated • 7.11k • 2 -
PeterJinGo/wiki-18-corpus
Updated • 2.77k -
slupart/ChatR1-qrecc-qwen2.5-3b-it-ppo
3B • Updated • 25 -
slupart/ChatR1-qrecc-qwen2.5-7b-it-ppo
8B • Updated • 12 -
slupart/ChatR1-topiocqa-qwen2.5-3b-it-ppo
3B • Updated • 17 -
slupart/ChatR1-topiocqa-qwen2.5-7b-it-ppo
8B • Updated • 14 -
slupart/chatr1-convqa-all
Viewer • Updated • 176k • 82 • 1