AIBullisharXiv – CS AI · 15h ago6/10
🧠
SeDT: Sentence-Transformer Decision-Transformer Conditioning for Multi-Turn Conversation Reliability
Researchers present SeDT, a training-free method that improves large language model performance in multi-turn conversations by annotating conversation history with relevance scores, addressing a documented 39% performance drop when tasks are revealed incrementally across multiple turns.