A thesis that combines self-learning from dialog logs, schema-guided prompting, and self-aligned factuality to build task bots with minimal human intervention.
Are LLMs All You Need for Task-Oriented Dialogue?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Instructions-tuned Large Language Models (LLMs) gained recently huge popularity thanks to their ability to interact with users through conversation. In this work we aim to evaluate their ability to complete multi-turn tasks and interact with external databases in the context of established task-oriented dialogue benchmarks. We show that for explicit belief state tracking, LLMs underperform compared to specialized task-specific models. Nevertheless, they show ability to guide the dialogue to successful ending if given correct slot values. Furthermore this ability improves with access to true belief state distribution or in-domain examples.
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Building Task Bots with Self-learning for Enhanced Adaptability, Extensibility, and Factuality
A thesis that combines self-learning from dialog logs, schema-guided prompting, and self-aligned factuality to build task bots with minimal human intervention.