On the essence and prospect: An investigation of alignment approaches for big models

X Wang, S Duan, X Yi, J Yao, S Zhou, Z Wei… - arXiv preprint arXiv …, 2024 - arxiv.org
Big models have achieved revolutionary breakthroughs in the field of AI, but they might also
pose potential concerns. Addressing such concerns, alignment technologies were …

The oscars of ai theater: A survey on role-playing with language models

N Chen, Y Wang, Y Deng, J Li - arXiv preprint arXiv:2407.11484, 2024 - arxiv.org
This survey explores the burgeoning field of role-playing with language models, focusing on
their development from early persona-based models to advanced character-driven …

Think Before You Speak: Cultivating Communication Skills of Large Language Models via Inner Monologue

J Zhou, L Pang, H Shen, X Cheng - arXiv preprint arXiv:2311.07445, 2023 - arxiv.org
The emergence of large language models (LLMs) further improves the capabilities of open-
domain dialogue systems and can generate fluent, coherent, and diverse responses …

RoleInteract: Evaluating the Social Interaction of Role-Playing Agents

H Chen, H Chen, M Yan, W Xu, X Gao, W Shen… - arXiv preprint arXiv …, 2024 - arxiv.org
Large language models (LLMs) have advanced the development of various AI
conversational agents, including role-playing conversational agents that mimic diverse …

mPLUG-Octopus: The Versatile Assistant Empowered by A Modularized End-to-End Multimodal LLM

Q Ye, H Xu, M Yan, C Zhao, J Wang, X Yang… - Proceedings of the 31st …, 2023 - dl.acm.org
Inspired by the recent developments of large language models (LLMs), we propose mPLUG-
Octopus, a versatile conversational assistant designed to provide users with coherent …

UDKAG: Augmenting Large Vision-Language Models with Up-to-Date Knowledge

C Li, Z Li, C Jing, S Liu, W Shao, Y Wu, P Luo… - arXiv preprint arXiv …, 2024 - arxiv.org
Large vision-language models (LVLMs) are ignorant of the up-to-date knowledge, such as
LLaVA series, because they cannot be updated frequently due to the large amount of …

SocialBench: Sociality Evaluation of Role-Playing Conversational Agents

H Chen, H Chen, M Yan, W Xu, G Xing… - Findings of the …, 2024 - aclanthology.org
Large language models (LLMs) have advanced the development of various AI
conversational agents, including role-playing agents that mimic diverse characters and …

REM: A Ranking-Based Automatic Evaluation Method for LLMs

J Yang, Y Tan, W Hu, Z Yang, X Zhou, Z Luo… - … Conference on Artificial …, 2024 - Springer
Abstract The emergence of Large Language Models (LLMs) has garnered attention due to
their remarkable comprehension and generation capabilities across various language tasks …