Optimizing Model Selection for Compound AI Systems
- URL: http://arxiv.org/abs/2502.14815v1
- Date: Thu, 20 Feb 2025 18:36:25 GMT
- Title: Optimizing Model Selection for Compound AI Systems
- Authors: Lingjiao Chen, Jared Quincy Davis, Boris Hanin, Peter Bailis, Matei Zaharia, James Zou, Ion Stoica,
- Abstract summary: We propose an efficient framework for model selection in compound systems.
It iteratively selects one module and allocates to it the model with the highest module-wise performance.
It confers 5%-70% accuracy gains compared to using the same LLM for all modules.
- Score: 76.69936664916061
- License:
- Abstract: Compound AI systems that combine multiple LLM calls, such as self-refine and multi-agent-debate, achieve strong performance on many AI tasks. We address a core question in optimizing compound systems: for each LLM call or module in the system, how should one decide which LLM to use? We show that these LLM choices have a large effect on quality, but the search space is exponential. We propose LLMSelector, an efficient framework for model selection in compound systems, which leverages two key empirical insights: (i) end-to-end performance is often monotonic in how well each module performs, with all other modules held fixed, and (ii) per-module performance can be estimated accurately by an LLM. Building upon these insights, LLMSelector iteratively selects one module and allocates to it the model with the highest module-wise performance, as estimated by an LLM, until no further gain is possible. LLMSelector is applicable to any compound system with a bounded number of modules, and its number of API calls scales linearly with the number of modules, achieving high-quality model allocation both empirically and theoretically. Experiments with popular compound systems such as multi-agent debate and self-refine using LLMs such as GPT-4o, Claude 3.5 Sonnet and Gemini 1.5 show that LLMSelector confers 5%-70% accuracy gains compared to using the same LLM for all modules.
Related papers
- PickLLM: Context-Aware RL-Assisted Large Language Model Routing [0.5325390073522079]
PickLLM is a lightweight framework that relies on Reinforcement Learning (RL) to route on-the-fly queries to available models.
We demonstrate the speed of convergence for different learning rates and improvement in hard metrics such as cost per querying session and overall response latency.
arXiv Detail & Related papers (2024-12-12T06:27:12Z) - LLM-based Optimization of Compound AI Systems: A Survey [64.39860384538338]
In a compound AI system, components such as an LLM call, a retriever, a code interpreter, or tools are interconnected.
Recent advancements enable end-to-end optimization of these parameters using an LLM.
This paper presents a survey of the principles and emerging trends in LLM-based optimization of compound AI systems.
arXiv Detail & Related papers (2024-10-21T18:06:25Z) - ELMS: Elasticized Large Language Models On Mobile Devices [5.689405542579458]
On-device Large Language Models (LLMs) are revolutionizing mobile AI, enabling applications such as UI automation while addressing privacy concerns.
We introduce ELMS, an on-device LLM service designed to provide elasticity in both the model and prompt dimensions.
A one-time reorder neuroning technique, which utilizes the inherent permutation consistency within transformer models to create high-quality, elastic sub-models.
A dual-head compact language model, which efficiently refines prompts and coordinates the elastic adaptation between the model prompt.
arXiv Detail & Related papers (2024-09-08T06:32:08Z) - SelectLLM: Query-Aware Efficient Selection Algorithm for Large Language Models [8.558834738072363]
Large language models (LLMs) have seen widespread adoption due to their remarkable performance across various applications.
These individual LLMs show limitations in generalization and performance on complex tasks due to inherent training biases, model size constraints, and the quality or diversity of pre-training datasets.
We introduce SelectLLM, which efficiently directs input queries to the most suitable subset of LLMs from a large pool.
arXiv Detail & Related papers (2024-08-16T06:11:21Z) - SoupLM: Model Integration in Large Language and Multi-Modal Models [51.12227693121004]
Training large language models (LLMs) requires significant computing resources.
Existing publicly available LLMs are typically pre-trained on diverse, privately curated datasets spanning various tasks.
arXiv Detail & Related papers (2024-07-11T05:38:15Z) - Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems [76.69936664916061]
We study how the number of LM calls affects the performance of Vote and Filter-Vote.
We find, surprisingly, that across multiple language tasks, the performance of both Vote and Filter-Vote can first increase but then decrease as a function of the number of LM calls.
arXiv Detail & Related papers (2024-03-04T19:12:48Z) - A Framework to Implement 1+N Multi-task Fine-tuning Pattern in LLMs
Using the CGC-LORA Algorithm [7.521690071464451]
We propose a unified framework that implements a 1 + N mutli-task fine-tuning pattern in large language models (LLMs)
Our work aims to take an advantage of both MTL (i.e., CGC) and PEFT (i.e., LoRA) scheme.
arXiv Detail & Related papers (2024-01-22T07:58:31Z) - Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and
Text Integration [50.94902442781148]
We propose a novel multi-modal large language model (LLM) that seamlessly integrates visual, audio, and textual information.
Macaw-LLM consists of three main components: a modality module for encoding multi-modal data, a cognitive module for harnessing pretrained LLMs, and an alignment module for harmonizing diverse representations.
We construct a large-scale multi-modal instruction dataset in terms of multi-turn dialogue, including 69K image instances and 50K video instances.
arXiv Detail & Related papers (2023-06-15T12:45:25Z) - LLM-Pruner: On the Structural Pruning of Large Language Models [65.02607075556742]
Large language models (LLMs) have shown remarkable capabilities in language understanding and generation.
We tackle the compression of LLMs within the bound of two constraints: being task-agnostic and minimizing the reliance on the original training dataset.
Our method, named LLM-Pruner, adopts structural pruning that selectively removes non-critical coupled structures.
arXiv Detail & Related papers (2023-05-19T12:10:53Z)
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.