Back to the Barn with LLAMAs: Evolving Pretrained LLM Backbones in Finetuning Vision Language Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Horawalavithana, Sameera, Phillips, Lauren, Stewart, Ian, Munikoti, Sai, Pazdernik, Karl
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913025342046208
author Horawalavithana, Sameera
Phillips, Lauren
Stewart, Ian
Munikoti, Sai
Pazdernik, Karl
author_facet Horawalavithana, Sameera
Phillips, Lauren
Stewart, Ian
Munikoti, Sai
Pazdernik, Karl
contents Vision-Language Models (VLMs) have rapidly advanced by leveraging powerful pre-trained Large Language Models (LLMs) as core reasoning backbones. As new and more capable LLMs emerge with improved reasoning, instruction-following, and generalization, there is a pressing need to efficiently update existing VLMs to incorporate these advancements. However, the integration of new LLMs into VLMs, particularly how the evolving LLMs contribute to multimodal reasoning, alignment, and task-specific performance remains underexplored. Addressing this gap is important for VLM development, given the rapid evolution of pretrained LLM backbones. This study presents a controlled and systematic investigation of how changes in the pretrained LLM backbone affect downstream VLM task performance. By having the vision encoder, training data, and post-training algorithm remain same across LLAMA-1, LLAMA-2, and LLAMA-3 based VLMs, we find that newer LLM backbones do not always lead to better VLMs, but the performance depends on the downstream VLM task. For example, in visual question and answering tasks, newer LLM backbones tend to solve different questions rather than just more questions, and our analysis shows this is driven by differences in how the models process information, including better calibrated confidence and more stable internal representations. We also find that some VLM capabilities appear only in the newest LLM generation, while tasks that depend mainly on visual understanding see little benefit from a newer LLM backbone.
format Preprint
id arxiv_https___arxiv_org_abs_2604_10985
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Back to the Barn with LLAMAs: Evolving Pretrained LLM Backbones in Finetuning Vision Language Models
Horawalavithana, Sameera
Phillips, Lauren
Stewart, Ian
Munikoti, Sai
Pazdernik, Karl
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
Vision-Language Models (VLMs) have rapidly advanced by leveraging powerful pre-trained Large Language Models (LLMs) as core reasoning backbones. As new and more capable LLMs emerge with improved reasoning, instruction-following, and generalization, there is a pressing need to efficiently update existing VLMs to incorporate these advancements. However, the integration of new LLMs into VLMs, particularly how the evolving LLMs contribute to multimodal reasoning, alignment, and task-specific performance remains underexplored. Addressing this gap is important for VLM development, given the rapid evolution of pretrained LLM backbones. This study presents a controlled and systematic investigation of how changes in the pretrained LLM backbone affect downstream VLM task performance. By having the vision encoder, training data, and post-training algorithm remain same across LLAMA-1, LLAMA-2, and LLAMA-3 based VLMs, we find that newer LLM backbones do not always lead to better VLMs, but the performance depends on the downstream VLM task. For example, in visual question and answering tasks, newer LLM backbones tend to solve different questions rather than just more questions, and our analysis shows this is driven by differences in how the models process information, including better calibrated confidence and more stable internal representations. We also find that some VLM capabilities appear only in the newest LLM generation, while tasks that depend mainly on visual understanding see little benefit from a newer LLM backbone.
title Back to the Barn with LLAMAs: Evolving Pretrained LLM Backbones in Finetuning Vision Language Models
topic Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.10985