# Aligning MAGMA by Few-Shot Learning and Finetuning

Source: [Aligning MAGMA by Few-Shot Learning and Finetuning](<https://www.sota2.com/research/paper/68fa6dbb1e209131cea3ba9d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:41:22.038Z

Authors: Jean-Charles Layoun, Alexis Roger, Irina Rish

Published: 2022-10-18T22:20:47.000Z

## Abstract

The goal of vision-language modeling is to allow models to tie language understanding with visual inputs. The aim of this paper is to evaluate and align the Visual Language Model (VLM) called Multimodal Augmentation of Generative Models through Adapter-based finetuning (MAGMA) with human values. MAGMA is a VLM that is capable of image captioning and visual question-answering. We will evaluate its alignment in three different scenarios. To begin, we assess MAGMA's out-of-the-box alignment through the checkpoint provided by Hugging Face. Then, we measure if few-shot learning manages to improve the results. Finally, we finetune the model on aligned examples and evaluate its behavior.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2210.14161>)

[PDF](<https://arxiv.org/pdf/2210.14161.pdf>)
