MORTAR uses dialogue-level perturbations and metamorphic relations to reveal context-dependent bugs in multi-turn LLM dialogue systems without an LLM judge.
A review of dialogue systems: current trends and future directions,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
MORTAR: Multi-turn Metamorphic Testing for LLM-based Dialogue Systems
MORTAR uses dialogue-level perturbations and metamorphic relations to reveal context-dependent bugs in multi-turn LLM dialogue systems without an LLM judge.