A diverse range of large language models (LLMs), e.g., ChatGPT, and visual question answering (VQA) models, e.g., BLIP, have been developed for solving textual and visual question answering tasks. However, both LLMs and VQA models encounter challenges when applied to task-specific datasets. Fine-tuning these models is either difficult, as it requires access via APIs, rendering them as black-boxes, or costly due to the need of tuning a large number of parameters. To address this, we introduce InfoSel, a data-efficient and lightweight ensemble method that learns to dynamically pick the winner from existing black-box models for predictions on both textual and multimodal visual question answering tasks. Unlike traditional ensemble models, InfoSel does not rely on prediction probabilities or confidences, which typically are not available in black-box models. Experimental results on four datasets demonstrate that our approach achieves an absolute increase of up to +5.27% in the F1-score compared to standalone LLMs. Remarkably, this improvement is achieved by utilizing only 1K training instances and 110M model parameters for training task-specific ensemble models.

We propose an ensembling framework that uses diverse open-sourced Large Language Models (LLMs) to achieve high response quality while maintaining cost efficiency. We formulate a bi-objective optimization problem to represent the quality-cost tradeoff and then introduce an additional budget constraint that reduces the problem to a straightforward 0/1 knapsack problem. We empirically demonstrate that our framework outperforms the existing ensembling approaches in response quality while significantly reducing costs. Large Language Models (LLMs) excel in traditional NLP problems (OpenAI (2023)), but their high inference costs hinder deployment in high-throughput applications (Anonymous (2023a)). Meanwhile, opensource models are less performant than their closed-source counterparts (Beeching et al. (2023)), but they typically offer lower inference costs (Kaplan et al. (2020)).