Towards Harnessing Large Language Models for Comprehension of Conversational Grounding

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jokinen, Kristiina, Schneider, Phillip, Mori, Taiga
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929371727527936
author Jokinen, Kristiina
Schneider, Phillip
Mori, Taiga
author_facet Jokinen, Kristiina
Schneider, Phillip
Mori, Taiga
contents Conversational grounding is a collaborative mechanism for establishing mutual knowledge among participants engaged in a dialogue. This experimental study analyzes information-seeking conversations to investigate the capabilities of large language models in classifying dialogue turns related to explicit or implicit grounding and predicting grounded knowledge elements. Our experimental results reveal challenges encountered by large language models in the two tasks and discuss ongoing research efforts to enhance large language model-based conversational grounding comprehension through pipeline architectures and knowledge bases. These initiatives aim to develop more effective dialogue systems that are better equipped to handle the intricacies of grounded knowledge in conversations.
format Preprint
id arxiv_https___arxiv_org_abs_2406_01749
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Harnessing Large Language Models for Comprehension of Conversational Grounding
Jokinen, Kristiina
Schneider, Phillip
Mori, Taiga
Computation and Language
Conversational grounding is a collaborative mechanism for establishing mutual knowledge among participants engaged in a dialogue. This experimental study analyzes information-seeking conversations to investigate the capabilities of large language models in classifying dialogue turns related to explicit or implicit grounding and predicting grounded knowledge elements. Our experimental results reveal challenges encountered by large language models in the two tasks and discuss ongoing research efforts to enhance large language model-based conversational grounding comprehension through pipeline architectures and knowledge bases. These initiatives aim to develop more effective dialogue systems that are better equipped to handle the intricacies of grounded knowledge in conversations.
title Towards Harnessing Large Language Models for Comprehension of Conversational Grounding
topic Computation and Language
url https://arxiv.org/abs/2406.01749