LLMs drop 39% in performance during multi-turn conversations due to premature assumptions and inability to recover from early errors.
Advances in Neural Information Processing Systems, 37:109894– 109921
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 2years
2025 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
RLAAR applies competence-gated curriculum RL with mixed accuracy and abstention rewards to reduce Lost-in-Conversation degradation, raising benchmark accuracy from 62.6% to 75.1% and calibrated abstention from 33.5% to 73.4%.
citing papers explorer
-
LLMs Get Lost In Multi-Turn Conversation
LLMs drop 39% in performance during multi-turn conversations due to premature assumptions and inability to recover from early errors.
-
Mitigating Lost in Multi-turn Conversation via Curriculum RL with Verifiable Accuracy and Abstention Rewards
RLAAR applies competence-gated curriculum RL with mixed accuracy and abstention rewards to reduce Lost-in-Conversation degradation, raising benchmark accuracy from 62.6% to 75.1% and calibrated abstention from 33.5% to 73.4%.