Are Large Language Models All You Need for Task-Oriented Dialogue?

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10476275" target="_blank" >RIV/00216208:11320/23:10476275 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Are Large Language Models All You Need for Task-Oriented Dialogue?

Original language description

Instruction-finetuned large language models (LLMs) gained a huge popularity recently, 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 in explicit belief state tracking, LLMs underperform compared to specialized task-specific models. Nevertheless, they show some ability to guide the dialogue to a successful ending through their generated responses if they are provided with correct slot values. Furthermore, this ability improves with few-shot in-domain examples.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/LM2023062" target="_blank" >LM2023062: Digital Research Infrastructure for Language Technologies, Arts and Humanities</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Publication year

2023

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the 24th Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)

ISBN

979-8-89176-028-8

ISSN

—

e-ISSN

—

Number of pages

13

Pages from-to

216-228

Publisher name

Association for Computational Linguistics

Place of publication

Stroudsubrgh, PA, USA

Event location

Prague, Czechia

Event date

Sep 13, 2023

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—