Thanos: Enhancing Conversational Agents with Skill-of-Mind-Infused Large Language Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Young-Jun, Lee, Dokyong, Youn, Junyoung, Oh, Kyeongjin, Choi, Ho-Jin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913573265997824
author Lee, Young-Jun
Lee, Dokyong
Youn, Junyoung
Oh, Kyeongjin
Choi, Ho-Jin
author_facet Lee, Young-Jun
Lee, Dokyong
Youn, Junyoung
Oh, Kyeongjin
Choi, Ho-Jin
contents To increase social bonding with interlocutors, humans naturally acquire the ability to respond appropriately in a given situation by considering which conversational skill is most suitable for the response - a process we call skill-of-mind. For large language model (LLM)-based conversational agents, planning appropriate conversational skills, as humans do, is challenging due to the complexity of social dialogue, especially in interactive scenarios. To address this, we propose a skill-of-mind-annotated conversation dataset, named Multifaceted Skill-of-Mind, which includes multi-turn and multifaceted conversational skills across various interactive scenarios (e.g., long-term, counseling, task-oriented), grounded in diverse social contexts (e.g., demographics, persona, rules of thumb). This dataset consists of roughly 100K conversations. Using this dataset, we introduce a new family of skill-of-mind-infused LLMs, named Thanos, with model sizes of 1B, 3B, and 8B parameters. With extensive experiments, these models successfully demonstrate the skill-of-mind process and exhibit strong generalizability in inferring multifaceted skills across a variety of domains. Moreover, we show that Thanos significantly enhances the quality of responses generated by LLM-based conversational agents and promotes prosocial behavior in human evaluations.
format Preprint
id arxiv_https___arxiv_org_abs_2411_04496
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Thanos: Enhancing Conversational Agents with Skill-of-Mind-Infused Large Language Model
Lee, Young-Jun
Lee, Dokyong
Youn, Junyoung
Oh, Kyeongjin
Choi, Ho-Jin
Computation and Language
To increase social bonding with interlocutors, humans naturally acquire the ability to respond appropriately in a given situation by considering which conversational skill is most suitable for the response - a process we call skill-of-mind. For large language model (LLM)-based conversational agents, planning appropriate conversational skills, as humans do, is challenging due to the complexity of social dialogue, especially in interactive scenarios. To address this, we propose a skill-of-mind-annotated conversation dataset, named Multifaceted Skill-of-Mind, which includes multi-turn and multifaceted conversational skills across various interactive scenarios (e.g., long-term, counseling, task-oriented), grounded in diverse social contexts (e.g., demographics, persona, rules of thumb). This dataset consists of roughly 100K conversations. Using this dataset, we introduce a new family of skill-of-mind-infused LLMs, named Thanos, with model sizes of 1B, 3B, and 8B parameters. With extensive experiments, these models successfully demonstrate the skill-of-mind process and exhibit strong generalizability in inferring multifaceted skills across a variety of domains. Moreover, we show that Thanos significantly enhances the quality of responses generated by LLM-based conversational agents and promotes prosocial behavior in human evaluations.
title Thanos: Enhancing Conversational Agents with Skill-of-Mind-Infused Large Language Model
topic Computation and Language
url https://arxiv.org/abs/2411.04496