Can Small VLMs Translate Sign Language to Spoken Language?

ACL ARR 2025 July Submission1146 Authors

Abstract: Vision-Language Models (VLMs) have shown strong generalization across multimodal tasks, but their capacity to handle \textit{sign language translation (SLT)}-which requires fine-grained spatiotemporal reasoning and linguistic understanding-remains unclear. In this study, we evaluate whether \textit{small-scale VLMs} ($\leq$3B parameters) can perform SLT effectively. We conduct supervised fine-tuning using multilingual sign language datasets—DGS, ASL, and ISL—adopting parameter-efficient LoRA tuning applied to the language decoder, while keeping the vision encoder frozen and allowing the connector to be trainable. To evaluate translation quality, we propose entity- and semantics-aware metrics tailored for SLT. We highlight the data imbalance issues present in the above widely used SLT datasets. Our analysis highlights the limitations in applying general-purpose VLMs to SLT, unlike their applicability in other tasks, and provides insights to inform future development of VLMs for SLP, which is essential for building inclusive AI applications.

Paper Type: Long

Research Area: Multimodality and Language Grounding to Vision, Robotics and Beyond

Research Area Keywords: Cross-modal machine translation, video processing

Contribution Types: Model analysis & interpretability, Approaches to low-resource settings

Languages Studied: German Sign Language, American Sign Language, Indian Sign Language

Reassignment Request Area Chair: This is not a resubmission

Reassignment Request Reviewers: This is not a resubmission

A1 Limitations Section: This paper has a limitations section.

A2 Potential Risks: N/A

B Use Or Create Scientific Artifacts: Yes

B1 Cite Creators Of Artifacts: Yes

B1 Elaboration: Section 3.2, 4.1, 4.2, 4.3

B2 Discuss The License For Artifacts: N/A

B3 Artifact Use Consistent With Intended Use: N/A

B4 Data Contains Personally Identifying Info Or Offensive Content: N/A

B5 Documentation Of Artifacts: Yes

B5 Elaboration: Section 4.1

B6 Statistics For Data: Yes

B6 Elaboration: Section 4.1

C Computational Experiments: Yes

C1 Model Size And Budget: Yes

C1 Elaboration: Section 4.3

C2 Experimental Setup And Hyperparameters: Yes

C2 Elaboration: Section 4.3

C3 Descriptive Statistics: Yes

C3 Elaboration: Section 4.4

C4 Parameters For Packages: Yes

C4 Elaboration: Section 4.2

D Human Subjects Including Annotators: No

D1 Instructions Given To Participants: N/A

D2 Recruitment And Payment: N/A

D3 Data Consent: N/A

D4 Ethics Review Board Approval: N/A

D5 Characteristics Of Annotators: N/A

E Ai Assistants In Research Or Writing: Yes

E1 Information About Use Of Ai Assistants: Yes

E1 Elaboration: Acknowledgments

Author Submission Checklist: yes

Submission Number: 1146