Towards Detecting Inconsistencies in End-to-end Generated TODs
Generative AI is profoundly transforming the core technologies behind conversational systems, shifting from component-based to end-to-end approaches. However, Large Language Models (LLMs) may still generate inconsistencies, a critical issue particularly in Task-Oriented Dialogues (TODs), where system responses must strictly adhere to information from a domain knowledge base (e.g., restaurants in a city). A single hallucination (e.g., suggesting a non-existent restaurant) can lead to severe task failures. We investigate a method for automatically detecting inconsistencies by conceptualizing TOD
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 49%NirDiamant/GenAI_Agents →
- PossiblePossibly related (embedding) · 49%bonigarcia/context-engineering →
- PossiblePossibly related (embedding) · 47%Xyntopia/taskyon →
- PossiblePossibly related (embedding) · 46%abhisadineni/ChatBot →
- PossiblePossibly related (embedding) · 46%AgustiPuigserver/opus-prompt-architect →
- LinkedLinked via arxiv author · 85%Tiziano Labruna →
“Towards Detecting Inconsistencies in End-to-end Generated TODs”
- LinkedLinked via arxiv author · 85%Giovanni Bonetta →
“Towards Detecting Inconsistencies in End-to-end Generated TODs”
- LinkedLinked via arxiv author · 85%Bernardo Magnini →
“Towards Detecting Inconsistencies in End-to-end Generated TODs”