# Prompting with Sign Parameters for Low-resource Sign Language Instruction Generation

arXiv: https://arxiv.org/abs/2508.16076 · HTML: https://mlsanity.com/paper/2508.16076/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 28 references that are in the map.
- First posted on arXiv 22 Aug 2025.

## Builds on (most cited first, 10 of 10)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [Task Contamination: Language Models May Not Be Few-Shot Anymore](https://mlsanity.com/paper/2312.16337/) (2023)
- [Video Transformers: A Survey](https://mlsanity.com/paper/2201.05991/) (2022)
- [From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities](https://mlsanity.com/paper/2311.00308/) (2023)
- [Systemic Biases in Sign Language AI Research: A Deaf-Led Call to Reevaluate Research Agendas](https://mlsanity.com/paper/2403.02563/) (2024)
- [BdSLW60: A Word-Level Bangla Sign Language Dataset](https://mlsanity.com/paper/2402.08635/) (2024)
- [Generating Signed Language Instructions in Large-Scale Dialogue Systems](https://mlsanity.com/paper/2410.14026/) (2024)

## Built on by (most cited first, 1 of 1)

- [Bangla Sign Language Translation: Dataset Creation Challenges, Benchmarking and Prospects](https://mlsanity.com/paper/2511.21533/) (2025)

## Abstract (arXiv)

Sign Language (SL) enables two-way communication for the deaf and hard-of-hearing community, yet many sign languages remain under-resourced in the AI space. Sign Language Instruction Generation (SLIG) produces step-by-step textual instructions that enable non-SL users to imitate and learn SL gestures, promoting two-way interaction. We introduce BdSLIG, the first Bengali SLIG dataset, used to evaluate Vision Language Models (VLMs) (i) on under-resourced SLIG tasks, and (ii) on long-tail visual concepts, as Bengali SL is unlikely to appear in the VLM pre-training data. To enhance zero-shot performance, we introduce Sign Parameter-Infused (SPI) prompting, which integrates standard SL parameters, like hand shape, motion, and orientation, directly into the textual prompts. Subsuming standard sign parameters into the prompt makes the instructions more structured and reproducible than free-form natural text from vanilla prompting. We envision that our work would promote inclusivity and advancement in SL learning systems for the under-resourced communities.