MultiWOZ 2.2
PulseAugur coverage of MultiWOZ 2.2 — every cluster mentioning MultiWOZ 2.2 across labs, papers, and developer communities, ranked by signal.
-
LLM dialogue agents improve safety with new prompting strategy · 2 sources tracked
A new research paper explores a lightweight prompting strategy to improve the safety of large language models in task-oriented dialogue when database interactions fail. The proposed "Guided-Retry" method aims to reduce …
-
New AI framework MORE boosts e-commerce dialogue conversion
Researchers have developed a new adaptive multi-objective reinforcement learning framework called MORE, designed to optimize both reasoning accuracy and linguistic naturalness in e-commerce dialogue systems. This approa…
-
GEM framework boosts dialogue state tracking with graph-enhanced experts and ReAct agents
Researchers have developed GEM, a novel framework for Dialogue State Tracking that combines graph-enhanced mixture-of-experts with ReAct agents. This approach dynamically routes between specialized experts, including a …
-
New model makes dialogue systems more proactive by predicting user intent
Researchers have developed a new method to make dialogue models more proactive by predicting user intents. This approach uses a lightweight intent-transition prior, instantiated with a Temporal Bayesian Network (T-BN), …