@inproceedings{lu-etal-2024-large,
title = "Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment",
author = "Lu, Keming and
Yu, Bowen and
Zhou, Chang and
Zhou, Jingren",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.423",
doi = "10.18653/v1/2024.acl-long.423",
pages = "7828--7840",
abstract = "Considerable efforts have been invested in augmenting the role-playing proficiency of open-source large language models (LLMs) by emulating proprietary counterparts. Nevertheless, we posit that LLMs inherently harbor role-play capabilities, owing to the extensive knowledge of characters and potential dialogues ingrained in their vast training corpora. Thus, we introduce Ditto, the first self-alignment method for role-play, which encourages an instruction-following LLM to simulate role-play dialogues as a variant of reading comprehension, and creates a role-play training set comprising 4000 characters, surpassing the scale of currently available datasets by tenfold regarding the number of roles. Subsequently, we fine-tune the LLM using this self-generated dataset to augment its role-playing capabilities. Upon evaluating our meticulously constructed role-play benchmark and the roleplay subset of MT-Bench, Ditto, in various parameter scales, consistently maintains a consistent role identity and provides accurate role-specific knowledge in multi-turn role-play conversations, outperforming all open-source role-play baselines. Furthermore, we present the first cross-supervision role-play experiment, revealing that the role-play styles can be easily acquired, while the intrinsic capabilities of LLMs confine the knowledge within role-play.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lu-etal-2024-large">
<titleInfo>
<title>Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Keming</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bowen</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chang</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingren</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Considerable efforts have been invested in augmenting the role-playing proficiency of open-source large language models (LLMs) by emulating proprietary counterparts. Nevertheless, we posit that LLMs inherently harbor role-play capabilities, owing to the extensive knowledge of characters and potential dialogues ingrained in their vast training corpora. Thus, we introduce Ditto, the first self-alignment method for role-play, which encourages an instruction-following LLM to simulate role-play dialogues as a variant of reading comprehension, and creates a role-play training set comprising 4000 characters, surpassing the scale of currently available datasets by tenfold regarding the number of roles. Subsequently, we fine-tune the LLM using this self-generated dataset to augment its role-playing capabilities. Upon evaluating our meticulously constructed role-play benchmark and the roleplay subset of MT-Bench, Ditto, in various parameter scales, consistently maintains a consistent role identity and provides accurate role-specific knowledge in multi-turn role-play conversations, outperforming all open-source role-play baselines. Furthermore, we present the first cross-supervision role-play experiment, revealing that the role-play styles can be easily acquired, while the intrinsic capabilities of LLMs confine the knowledge within role-play.</abstract>
<identifier type="citekey">lu-etal-2024-large</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.423</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.423</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>7828</start>
<end>7840</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment
%A Lu, Keming
%A Yu, Bowen
%A Zhou, Chang
%A Zhou, Jingren
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F lu-etal-2024-large
%X Considerable efforts have been invested in augmenting the role-playing proficiency of open-source large language models (LLMs) by emulating proprietary counterparts. Nevertheless, we posit that LLMs inherently harbor role-play capabilities, owing to the extensive knowledge of characters and potential dialogues ingrained in their vast training corpora. Thus, we introduce Ditto, the first self-alignment method for role-play, which encourages an instruction-following LLM to simulate role-play dialogues as a variant of reading comprehension, and creates a role-play training set comprising 4000 characters, surpassing the scale of currently available datasets by tenfold regarding the number of roles. Subsequently, we fine-tune the LLM using this self-generated dataset to augment its role-playing capabilities. Upon evaluating our meticulously constructed role-play benchmark and the roleplay subset of MT-Bench, Ditto, in various parameter scales, consistently maintains a consistent role identity and provides accurate role-specific knowledge in multi-turn role-play conversations, outperforming all open-source role-play baselines. Furthermore, we present the first cross-supervision role-play experiment, revealing that the role-play styles can be easily acquired, while the intrinsic capabilities of LLMs confine the knowledge within role-play.
%R 10.18653/v1/2024.acl-long.423
%U https://aclanthology.org/2024.acl-long.423
%U https://doi.org/10.18653/v1/2024.acl-long.423
%P 7828-7840
Markdown (Informal)
[Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment](https://aclanthology.org/2024.acl-long.423) (Lu et al., ACL 2024)
ACL