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

• URL: http://arxiv.org/abs/2410.11163v1
• Date: Tue, 15 Oct 2024 00:59:17 GMT
• Title: Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
• Authors: Shangbin Feng, Zifeng Wang, Yike Wang, Sayna Ebrahimi, Hamid Palangi, Lesly Miculicich, Achin Kulshrestha, Nathalie Rauschmayr, Yejin Choi, Yulia Tsvetkov, Chen-Yu Lee, Tomas Pfister,
• Abstract summary: We propose Model Swarms, a collaborative search algorithm to adapt LLMs via swarm intelligence. We show that Model Swarms could flexibly adapt LLM experts to a single task, multi-task domains, reward models, as well as diverse human interests.
• Score: 90.91152752062546
• License:
• Abstract: 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.

Related papers

• Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems [102.36545569092777]
  We propose Heterogeneous Swarms, an algorithm to design multi-LLM systems by jointly optimizing model roles and weights. Experiments demonstrate that Heterogeneous Swarms outperforms 15 role- and/or weight-based baselines by 18.5% on average across 12 tasks.
  arXiv  Detail & Related papers  (2025-02-06T21:27:11Z)
• MALT: Improving Reasoning with Multi-Agent LLM Training [64.13803241218886]
  We present a first step toward "Multi-agent LLM training" (MALT) on reasoning problems. Our approach employs a sequential multi-agent setup with heterogeneous LLMs assigned specialized roles. We evaluate our approach across MATH, GSM8k, and CQA, where MALT on Llama 3.1 8B models achieves relative improvements of 14.14%, 7.12%, and 9.40% respectively.
  arXiv  Detail & Related papers  (2024-12-02T19:30:36Z)
• Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild [84.57103623507082]
  This paper introduces Model-GLUE, a holistic Large Language Models scaling guideline. We benchmark existing scaling techniques, especially selective merging, and variants of mixture. We then formulate an optimal strategy for the selection and aggregation of a heterogeneous model zoo. Our methodology involves the clustering of mergeable models and optimal merging strategy selection, and the integration of clusters.
  arXiv  Detail & Related papers  (2024-10-07T15:55:55Z)
• Pooling And Attention: What Are Effective Designs For LLM-Based Embedding Models? [18.990655668481075]
  We propose a new pooling strategy, Multi-Layers Trainable Pooling, which transforms the outputs of all hidden layers, rather than just the last layer, using a cross-attention network. This paper sheds light on effective training strategies for LLM-based embedding models.
  arXiv  Detail & Related papers  (2024-09-04T14:01:48Z)
• EMR-Merging: Tuning-Free High-Performance Model Merging [55.03509900949149]
  We show that Elect, Mask & Rescale-Merging (EMR-Merging) shows outstanding performance compared to existing merging methods. EMR-Merging is tuning-free, thus requiring no data availability or any additional training while showing impressive performance.
  arXiv  Detail & Related papers  (2024-05-23T05:25:45Z)
• Weak-to-Strong Extrapolation Expedites Alignment [135.12769233630362]
  We propose a method called ExPO to boost models' alignment with human preference. We demonstrate that ExPO consistently improves off-the-shelf DPO/RLHF models. We shed light on the essence of ExPO amplifying the reward signal learned during alignment training.
  arXiv  Detail & Related papers  (2024-04-25T17:39:50Z)
• Learning to Decode Collaboratively with Multiple Language Models [37.31339648499042]
  We propose a method to teach multiple large language models (LLM) to collaborate by interleaving their generations at the token level. Token-level collaboration during decoding allows for a fusion of each model's expertise in a manner tailored to the specific task at hand.
  arXiv  Detail & Related papers  (2024-03-06T17:23:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.