task-oriented-dialogue

Tag

Cards List
#task-oriented-dialogue

Candidate Attended Dialogue State Tracking Using BERT

arXiv cs.CL · 2026-07-20 Cached

The paper presents a scalable framework for multi-domain dialogue state tracking using BERT, achieving zero-shot generalization and improving performance on the SGD dataset.

0 favorites 0 likes
#task-oriented-dialogue

Towards Detecting Inconsistencies in End-to-end Generated TODs

arXiv cs.CL · 2026-07-13 Cached

This paper proposes a method for automatically detecting inconsistencies in end-to-end generated task-oriented dialogues by modeling them as a Constraint Satisfaction Problem (CSP), achieving high accuracy in identifying hallucinated or inconsistent responses.

0 favorites 0 likes
#task-oriented-dialogue

TRACER: Early Failure Detection for Task-Oriented Dialogue

arXiv cs.CL · 2026-07-07 Cached

TRACER predicts whether a task-oriented dialogue will fail by analyzing partial conversations using belief-state changes and text representations, enabling early warning before full breakdown.

0 favorites 0 likes
#task-oriented-dialogue

When the Database Fails: Prompting LLM Dialogue Agents for Safe Recovery in Task-Oriented Dialogue

arXiv cs.CL · 2026-07-01 Cached

This paper studies a lightweight prompting-based recovery approach for LLM dialogue agents when backend database calls fail, showing that the Guided-Retry strategy reduces hallucination by 50% on MultiWOZ and 42% on SGD across six model families.

0 favorites 0 likes
#task-oriented-dialogue

GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems

Hugging Face Daily Papers · 2026-06-26 Cached

Proposes Gradient-Based Connections (GBC), a method that models multi-agent LLM systems as computational graphs and uses gradient signals to attribute errors to specific agents, enabling better system-level optimization.

0 favorites 0 likes
#task-oriented-dialogue

ReacTOD: Bounded Neuro-Symbolic Agentic NLU for Zero-Shot Dialogue State Tracking

arXiv cs.CL · 2026-05-20 Cached

ReacTOD proposes a bounded neuro-symbolic architecture for zero-shot dialogue state tracking, using a self-correcting ReAct loop with deterministic validation. It achieves state-of-the-art results on MultiWOZ and Schema-Guided Dialogue benchmarks, improving joint goal accuracy by up to 14 percentage points.

0 favorites 0 likes
← Back to home

Submit Feedback