# Hugging Face — LAVE: Zero-shot VQA Evaluation on Docmatix with LLMs - Do We Still Need Fine-Tuning?

- Company: Hugging Face (huggingface.co)
- Announced: 2024-07-25T00:00:00+00:00
- Category: research-paper
- Subject: Platform
- Source: https://huggingface.co/blog/zero-shot-vqa-docmatix
- Record: https://forck.live/items/1848-lave-zero-shot-vqa-evaluation-on-docmatix-with-llms-do-we-still-need-fine-tuning

Hugging Face researchers introduce LAVE, an LLM-assisted evaluation metric for zero-shot VQA on the Docmatix dataset, questioning whether fine-tuning is necessary for accurate evaluation.

## Evidence

Verbatim from https://huggingface.co/blog/zero-shot-vqa-docmatix:

> In this post, we consider the LAVE (LLM-Assisted VQA Evaluation) metric to better assess generalization on this unseen but semantically similar dataset.

---

Record: https://forck.live/items/1848-lave-zero-shot-vqa-evaluation-on-docmatix-with-llms-do-we-still-need-fine-tuning
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md