Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Feng, Shangbin, Wang, Zifeng, Wang, Yike, Ebrahimi, Sayna, Palangi, Hamid, Miculicich, Lesly, Kulshrestha, Achin, Rauschmayr, Nathalie, Choi, Yejin, Tsvetkov, Yulia, Lee, Chen-Yu, Pfister, Tomas
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912407091150848
author Feng, Shangbin
Wang, Zifeng
Wang, Yike
Ebrahimi, Sayna
Palangi, Hamid
Miculicich, Lesly
Kulshrestha, Achin
Rauschmayr, Nathalie
Choi, Yejin
Tsvetkov, Yulia
Lee, Chen-Yu
Pfister, Tomas
author_facet Feng, Shangbin
Wang, Zifeng
Wang, Yike
Ebrahimi, Sayna
Palangi, Hamid
Miculicich, Lesly
Kulshrestha, Achin
Rauschmayr, Nathalie
Choi, Yejin
Tsvetkov, Yulia
Lee, Chen-Yu
Pfister, Tomas
contents We propose Model Swarms, a collaborative search algorithm to adapt LLMs via swarm intelligence, the collective behavior guiding individual systems. Specifically, Model Swarms starts with a pool of LLM experts and a utility function. Guided by the best-found checkpoints across models, diverse LLM experts collaboratively move in the weight space and optimize a utility function representing model adaptation objectives. Compared to existing model composition approaches, Model Swarms offers tuning-free model adaptation, works in low-data regimes with as few as 200 examples, and does not require assumptions about specific experts in the swarm or how they should be composed. Extensive experiments demonstrate that Model Swarms could flexibly adapt LLM experts to a single task, multi-task domains, reward models, as well as diverse human interests, improving over 12 model composition baselines by up to 21.0% across tasks and contexts. Further analysis reveals that LLM experts discover previously unseen capabilities in initial checkpoints and that Model Swarms enable the weak-to-strong transition of experts through the collaborative search process.
format Preprint
id arxiv_https___arxiv_org_abs_2410_11163
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
Feng, Shangbin
Wang, Zifeng
Wang, Yike
Ebrahimi, Sayna
Palangi, Hamid
Miculicich, Lesly
Kulshrestha, Achin
Rauschmayr, Nathalie
Choi, Yejin
Tsvetkov, Yulia
Lee, Chen-Yu
Pfister, Tomas
Computation and Language
We propose Model Swarms, a collaborative search algorithm to adapt LLMs via swarm intelligence, the collective behavior guiding individual systems. Specifically, Model Swarms starts with a pool of LLM experts and a utility function. Guided by the best-found checkpoints across models, diverse LLM experts collaboratively move in the weight space and optimize a utility function representing model adaptation objectives. Compared to existing model composition approaches, Model Swarms offers tuning-free model adaptation, works in low-data regimes with as few as 200 examples, and does not require assumptions about specific experts in the swarm or how they should be composed. Extensive experiments demonstrate that Model Swarms could flexibly adapt LLM experts to a single task, multi-task domains, reward models, as well as diverse human interests, improving over 12 model composition baselines by up to 21.0% across tasks and contexts. Further analysis reveals that LLM experts discover previously unseen capabilities in initial checkpoints and that Model Swarms enable the weak-to-strong transition of experts through the collaborative search process.
title Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
topic Computation and Language
url https://arxiv.org/abs/2410.11163