Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Wenyuan, Nie, Shuaiyi, Sheng, Jiawei, Zhang, Zefeng, Zhang, Xinghua, He, Yongquan, Liu, Tingwen
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2409.11726
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908371608666112
author Zhang, Wenyuan
Nie, Shuaiyi
Sheng, Jiawei
Zhang, Zefeng
Zhang, Xinghua
He, Yongquan
Liu, Tingwen
author_facet Zhang, Wenyuan
Nie, Shuaiyi
Sheng, Jiawei
Zhang, Zefeng
Zhang, Xinghua
He, Yongquan
Liu, Tingwen
contents Large language model (LLM) role-playing has gained widespread attention. Authentic character knowledge is crucial for constructing realistic LLM role-playing agents. However, existing works usually overlook the exploration of LLMs' ability to detect characters' known knowledge errors (KKE) and unknown knowledge errors (UKE) while playing roles, which would lead to low-quality automatic construction of character trainable corpus. In this paper, we propose RoleKE-Bench to evaluate LLMs' ability to detect errors in KKE and UKE. The results indicate that even the latest LLMs struggle to detect these two types of errors effectively, especially when it comes to familiar knowledge. We experimented with various reasoning strategies and propose an agent-based reasoning method, Self-Recollection and Self-Doubt (S$^2$RD), to explore further the potential for improving error detection capabilities. Experiments show that our method effectively improves the LLMs' ability to detect error character knowledge, but it remains an issue that requires ongoing attention.
format Preprint
id arxiv_https___arxiv_org_abs_2409_11726
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-Playing
Zhang, Wenyuan
Nie, Shuaiyi
Sheng, Jiawei
Zhang, Zefeng
Zhang, Xinghua
He, Yongquan
Liu, Tingwen
Computation and Language
Human-Computer Interaction
Large language model (LLM) role-playing has gained widespread attention. Authentic character knowledge is crucial for constructing realistic LLM role-playing agents. However, existing works usually overlook the exploration of LLMs' ability to detect characters' known knowledge errors (KKE) and unknown knowledge errors (UKE) while playing roles, which would lead to low-quality automatic construction of character trainable corpus. In this paper, we propose RoleKE-Bench to evaluate LLMs' ability to detect errors in KKE and UKE. The results indicate that even the latest LLMs struggle to detect these two types of errors effectively, especially when it comes to familiar knowledge. We experimented with various reasoning strategies and propose an agent-based reasoning method, Self-Recollection and Self-Doubt (S$^2$RD), to explore further the potential for improving error detection capabilities. Experiments show that our method effectively improves the LLMs' ability to detect error character knowledge, but it remains an issue that requires ongoing attention.
title Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-Playing
topic Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/2409.11726