Proactive conversational agents in the post-ChatGPT world

ChatGPT and similar large language model (LLM) based conversational agents have brought shock waves to the research world. Although astonished by their human-like performance, we find they share a significant weakness with many other existing conversational agents in that they all take a passive app...

Full description

Saved in:
Bibliographic Details
Main Authors: LIAO, Lizi, YANG, Grace Hui, SHAH, Chirag
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2023
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/8146
https://ink.library.smu.edu.sg/context/sis_research/article/9149/viewcontent/3539618.3594250_pvoa.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-9149
record_format dspace
spelling sg-smu-ink.sis_research-91492024-11-19T05:20:45Z Proactive conversational agents in the post-ChatGPT world LIAO, Lizi YANG, Grace Hui SHAH, Chirag ChatGPT and similar large language model (LLM) based conversational agents have brought shock waves to the research world. Although astonished by their human-like performance, we find they share a significant weakness with many other existing conversational agents in that they all take a passive approach in responding to user queries. This limits their capacity to understand the users and the task better and to offer recommendations based on a broader context than a given conversation. Proactiveness is still missing in these agents, including their ability to initiate a conversation, shift topics, or offer recommendations that take into account a more extensive context. To address this limitation, this tutorial reviews methods for equipping conversational agents with proactive interaction abilities.The full-day tutorial is divided into four parts, including multiple interactive exercises. We will begin the tutorial with an interactive exercise and cover the design of existing conversational systems architecture and challenges. The content includes coverage of LLM-based recent advancements such as ChatGPT and Bard, along with reinforcement learning with human feedback (RLHF) technique. Then we will introduce the concept of proactive conversation agents and preset recent advancements in proactiveness of conversational agents, including actively driving conversations by asking questions, topic shifting, and methods that support strategic planning of conversation. Next, we will discuss important issues in conversational responses' quality control, including safety, appropriateness, language detoxication, hallucination, and alignment. Lastly, we will launch another interactive exercise and discussion with the audience to arrive at concluding remarks, prospecting open challenges and new directions. By exploring new techniques for enhancing conversational agents' proactive behavior to improve user engagement, this tutorial aims to help researchers and practitioners develop more effective conversational agents that can better understand and respond to user needs proactively and safely. 2023-07-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8146 info:doi/10.1145/3539618.3594250 https://ink.library.smu.edu.sg/context/sis_research/article/9149/viewcontent/3539618.3594250_pvoa.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Proactive conversation conversational AI conversational search Artificial Intelligence and Robotics Higher Education
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Proactive conversation
conversational AI
conversational search
Artificial Intelligence and Robotics
Higher Education
spellingShingle Proactive conversation
conversational AI
conversational search
Artificial Intelligence and Robotics
Higher Education
LIAO, Lizi
YANG, Grace Hui
SHAH, Chirag
Proactive conversational agents in the post-ChatGPT world
description ChatGPT and similar large language model (LLM) based conversational agents have brought shock waves to the research world. Although astonished by their human-like performance, we find they share a significant weakness with many other existing conversational agents in that they all take a passive approach in responding to user queries. This limits their capacity to understand the users and the task better and to offer recommendations based on a broader context than a given conversation. Proactiveness is still missing in these agents, including their ability to initiate a conversation, shift topics, or offer recommendations that take into account a more extensive context. To address this limitation, this tutorial reviews methods for equipping conversational agents with proactive interaction abilities.The full-day tutorial is divided into four parts, including multiple interactive exercises. We will begin the tutorial with an interactive exercise and cover the design of existing conversational systems architecture and challenges. The content includes coverage of LLM-based recent advancements such as ChatGPT and Bard, along with reinforcement learning with human feedback (RLHF) technique. Then we will introduce the concept of proactive conversation agents and preset recent advancements in proactiveness of conversational agents, including actively driving conversations by asking questions, topic shifting, and methods that support strategic planning of conversation. Next, we will discuss important issues in conversational responses' quality control, including safety, appropriateness, language detoxication, hallucination, and alignment. Lastly, we will launch another interactive exercise and discussion with the audience to arrive at concluding remarks, prospecting open challenges and new directions. By exploring new techniques for enhancing conversational agents' proactive behavior to improve user engagement, this tutorial aims to help researchers and practitioners develop more effective conversational agents that can better understand and respond to user needs proactively and safely.
format text
author LIAO, Lizi
YANG, Grace Hui
SHAH, Chirag
author_facet LIAO, Lizi
YANG, Grace Hui
SHAH, Chirag
author_sort LIAO, Lizi
title Proactive conversational agents in the post-ChatGPT world
title_short Proactive conversational agents in the post-ChatGPT world
title_full Proactive conversational agents in the post-ChatGPT world
title_fullStr Proactive conversational agents in the post-ChatGPT world
title_full_unstemmed Proactive conversational agents in the post-ChatGPT world
title_sort proactive conversational agents in the post-chatgpt world
publisher Institutional Knowledge at Singapore Management University
publishDate 2023
url https://ink.library.smu.edu.sg/sis_research/8146
https://ink.library.smu.edu.sg/context/sis_research/article/9149/viewcontent/3539618.3594250_pvoa.pdf
_version_ 1816859164748546048