protologue

Multi-Turn Degradation

Also called lost in conversation, multi-turn performance drop.

Multi-turn degradation is the drop in model performance when a task's requirements are revealed across several conversation turns instead of all at once, because models commit to early assumptions and fail to recover.

Description

A large 2025 study found that models that performed well on fully specified single-turn instructions did markedly worse in multi-turn settings, mainly through increased unreliability rather than a loss of capability. The practical advice is to consolidate requirements into a fresh prompt when a conversation goes off track.

Sources

  1. Laban et al. (2025). LLMs Get Lost In Multi-Turn Conversation.

Cite this entry

Protologue. (2026). Multi-Turn Degradation. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0174). https://protologue.com/t/multi-turn-degradation/

BibTeX
@misc{protologue_multi_turn_degradation,
  title = {Multi-Turn Degradation},
  author = {{Protologue}},
  year = {2026},
  howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.4.0},
  note = {Entry PTL-0174},
  url = {https://protologue.com/t/multi-turn-degradation/}
}

Markdown JSON