@inproceedings{bian-etal-2025-ptoco,
title = "{PT}oco: Prefix-based Token-level Collaboration Enhances Reasoning for Multi-{LLM}s",
author = "Bian, Yuang and
Lin, Yupian and
Liu, Jingping and
Ruan, Tong",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.556/",
pages = "8326--8335",
abstract = "Collaboration between multiple Large Language Models (LLMs) has attracted significant attention for its potential to mitigate hallucinations and enhance reasoning capabilities. Previous approaches, such as multi-agent debate and decoding-time integration, either rely on highly capable models with strong self-reflection abilities or are limited to models sharing the same tokenizer. To address these limitations, we introduce PToco (Prefix-based Token-level Collaboration), a novel mechanism that enables effective collaboration among less capable LLMs, independent of tokenizer differences. PToco uses a prefix-grouping method to extract consensus among tokens with varying levels of granularity, ensuring coherent and robust token generation across multiple models. Experimental results on a series of reasoning tasks demonstrate that PToco significantly improves performance over individual models. Furthermore, this approach generalizes well across different quantities and sizes of participating models, providing a more flexible and efficient solution for multi-LLM ensembles."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bian-etal-2025-ptoco">
<titleInfo>
<title>PToco: Prefix-based Token-level Collaboration Enhances Reasoning for Multi-LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuang</namePart>
<namePart type="family">Bian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yupian</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingping</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Ruan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Collaboration between multiple Large Language Models (LLMs) has attracted significant attention for its potential to mitigate hallucinations and enhance reasoning capabilities. Previous approaches, such as multi-agent debate and decoding-time integration, either rely on highly capable models with strong self-reflection abilities or are limited to models sharing the same tokenizer. To address these limitations, we introduce PToco (Prefix-based Token-level Collaboration), a novel mechanism that enables effective collaboration among less capable LLMs, independent of tokenizer differences. PToco uses a prefix-grouping method to extract consensus among tokens with varying levels of granularity, ensuring coherent and robust token generation across multiple models. Experimental results on a series of reasoning tasks demonstrate that PToco significantly improves performance over individual models. Furthermore, this approach generalizes well across different quantities and sizes of participating models, providing a more flexible and efficient solution for multi-LLM ensembles.</abstract>
<identifier type="citekey">bian-etal-2025-ptoco</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.556/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>8326</start>
<end>8335</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PToco: Prefix-based Token-level Collaboration Enhances Reasoning for Multi-LLMs
%A Bian, Yuang
%A Lin, Yupian
%A Liu, Jingping
%A Ruan, Tong
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F bian-etal-2025-ptoco
%X Collaboration between multiple Large Language Models (LLMs) has attracted significant attention for its potential to mitigate hallucinations and enhance reasoning capabilities. Previous approaches, such as multi-agent debate and decoding-time integration, either rely on highly capable models with strong self-reflection abilities or are limited to models sharing the same tokenizer. To address these limitations, we introduce PToco (Prefix-based Token-level Collaboration), a novel mechanism that enables effective collaboration among less capable LLMs, independent of tokenizer differences. PToco uses a prefix-grouping method to extract consensus among tokens with varying levels of granularity, ensuring coherent and robust token generation across multiple models. Experimental results on a series of reasoning tasks demonstrate that PToco significantly improves performance over individual models. Furthermore, this approach generalizes well across different quantities and sizes of participating models, providing a more flexible and efficient solution for multi-LLM ensembles.
%U https://aclanthology.org/2025.coling-main.556/
%P 8326-8335
Markdown (Informal)
[PToco: Prefix-based Token-level Collaboration Enhances Reasoning for Multi-LLMs](https://aclanthology.org/2025.coling-main.556/) (Bian et al., COLING 2025)
ACL