Saved in:
Bibliographic Details
Main Authors: Xia, Yuxi, Zaporojets, Kilm, Roth, Benjamin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.12841
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915068210315264
author Xia, Yuxi
Zaporojets, Kilm
Roth, Benjamin
author_facet Xia, Yuxi
Zaporojets, Kilm
Roth, Benjamin
contents 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, 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 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 +5.19\% in the F1-score compared to standalone LLMs using only 1K training instances.
format Preprint
id arxiv_https___arxiv_org_abs_2407_12841
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Black-box Model Ensembling for Textual and Visual Question Answering via Information Fusion
Xia, Yuxi
Zaporojets, Kilm
Roth, Benjamin
Computation and Language
Artificial Intelligence
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, 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 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 +5.19\% in the F1-score compared to standalone LLMs using only 1K training instances.
title Black-box Model Ensembling for Textual and Visual Question Answering via Information Fusion
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2407.12841