# IchthyoNoma: Nomenclature and Context Sensitivity of Zero-Shot Biological Vision--Language Models for Bangladeshi Freshwater Fish Recognition

arXiv: https://arxiv.org/abs/2609.03985 · HTML: https://mlsanity.com/paper/2609.03985/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agricultural vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 3 Sep 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Agricultural vision-language models](https://mlsanity.com/mllm/agricultural-vision-language-models/)

## Builds on (most cited first, 11 of 11)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Noise or Signal: The Role of Image Backgrounds in Object Recognition](https://mlsanity.com/paper/2006.09994/) (2020)
- [BioCLIP: A Vision Foundation Model for the Tree of Life](https://mlsanity.com/paper/2311.18803/) (2023)
- [BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning](https://mlsanity.com/paper/2505.23883/) (2025)
- [jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images](https://mlsanity.com/paper/2412.08802/) (2024)
- [TaxaBind: A Unified Embedding Space for Ecological Applications](https://mlsanity.com/paper/2411.00683/) (2024)
- [Improving deep neural network generalization and robustness to background bias via layer-wise relevance propagation optimization](https://mlsanity.com/paper/2202.00232/) (2022)
- [Prompting Scientific Names for Zero-Shot Species Recognition](https://mlsanity.com/paper/2310.09929/) (2023)
- [Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representations](https://mlsanity.com/paper/2306.08658/) (2023)
- [uCLIP: Parameter-Efficient Multilingual Extension of Vision-Language Models with Unpaired Data](https://mlsanity.com/paper/2511.13036/) (2025)

## Abstract (arXiv)

Zero-shot vision-language models (VLMs) are increasingly used as training-free species recognizers, but reported accuracy can reflect more than visual species knowledge. We audit CLIP, BioCLIP, BioCLIP2, and a multilingual Jina CLIP v2 control on seven freshwater-fish categories from two Bangladeshi sources (10,321 images). BioCLIP2 reaches 72.36% on BFF-15 with English common names and 68.91% on SylFishBD with scientific names, versus 25.15% and 14.40% for generic CLIP. BioCLIP2 Bengali prompts are near chance in balanced accuracy (14.22-14.29%); Jina partially recovers Bengali discrimination to 21.89% and 16.36%, but bare Bengali names return to 14.29% on both sources. Paired SylFishBD interventions show no significant weak-blur effect, modest losses from stronger blur/gray masking, a larger white-mask artifact, and strong species dependence. Zero-shot biological VLM scores therefore jointly reflect biological specialization, multilingual alignment, nomenclature, prompt formulation, and context.