SeDT recovers up to 37.7% of lost performance in multi-turn conversations by annotating history with relevance scores from semantic, lexical, and positional signals without training or data changes.
arXiv preprint arXiv:2406.01633
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.CL 4verdicts
UNVERDICTED 4roles
background 2polarities
background 2representative citing papers
LLMs corrupt an average of 25% of document content during long delegated editing workflows across 52 domains, even frontier models, and agentic tools do not mitigate the issue.
LLMs drop 39% in performance during multi-turn conversations due to premature assumptions and inability to recover from early errors.
Fine-tuned simulators grounded in real human data produce LLM assistants that win more often against real users than those trained against role-playing simulators.
citing papers explorer
-
SeDT: Sentence-Transformer Decision-Transformer Conditioning for Multi-Turn Conversation Reliability
SeDT recovers up to 37.7% of lost performance in multi-turn conversations by annotating history with relevance scores from semantic, lexical, and positional signals without training or data changes.
-
LLMs Corrupt Your Documents When You Delegate
LLMs corrupt an average of 25% of document content during long delegated editing workflows across 52 domains, even frontier models, and agentic tools do not mitigate the issue.
-
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.
-
Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants
Fine-tuned simulators grounded in real human data produce LLM assistants that win more often against real users than those trained against role-playing simulators.