A framework combining goal-adaptive supervised fine-tuning and click-based reinforcement learning improves proactive guidance quality and speed in an industrial search assistant.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Proactive Guidance of Multi-Turn Conversation in Industrial Search
A framework combining goal-adaptive supervised fine-tuning and click-based reinforcement learning improves proactive guidance quality and speed in an industrial search assistant.