4 papers · 1 filter
VIABLE: A Visually Impaired Assistance Benchmark for VLM-as-a-Judge Evaluation
Yi Zhao, Siqi Wang, Zhe Hu +2
AI-based Visually Impaired Assistance (VIA) remains challenging, largely due to the high cost of human evaluation. The VLM-as-a-Judge paradigm may offer a promising alternative, al…
Language Bias in LVLMs: From In-Depth Analysis to Simple and Effective Mitigation
Yangneng Chen, Jing Li
Large Vision-Language Models (LVLMs) extend large language models with visual understanding, but remain vulnerable to hallucination, where outputs are fluent yet inconsistent with…
LaF-GRPO: In-Situ Navigation Instruction Generation for the Visually Impaired via GRPO with LLM-as-Follower Reward
Yi Zhao, Siqi Wang, Jing Li
Navigation instruction generation for visually impaired (VI) individuals (NIG-VI) is critical yet relatively underexplored. This study focuses on generating precise, in-situ, step-…
CAP: Data Contamination Detection via Consistency Amplification
Yi Zhao, Jing Li, Linyi Yang
Large language models (LLMs) are widely used, but concerns about data contamination challenge the reliability of LLM evaluations. Existing contamination detection methods are often…