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:2602.07338
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Trace mutations are a class of context failures in LLM conversations consisting of utterance effacement and genitive dissociation that distort the shared record while resisting ordinary repair.
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.
-
Trace Mutation in Human-LLM Dialogue: The Transcript as Forensic and Mitigation Surface
Trace mutations are a class of context failures in LLM conversations consisting of utterance effacement and genitive dissociation that distort the shared record while resisting ordinary repair.