#language-priors News & Analysis

2 articles tagged with #language-priors. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

2 articles

AIBullisharXiv – CS AI · Apr 157/10

🧠

Decoding by Perturbation: Mitigating MLLM Hallucinations via Dynamic Textual Perturbation

Researchers introduce Decoding by Perturbation (DeP), a training-free method that reduces hallucinations in multimodal large language models by applying controlled textual perturbations during decoding. The approach addresses the core issue where language priors override visual evidence, achieving improvements across multiple benchmarks without requiring model retraining or visual manipulation.

AIBearisharXiv – CS AI · 3d ago6/10

🧠

Reading or Guessing? Visual Grounding Failures of Vision-Language Models for OCR in Ancient Greek Editions

Researchers demonstrate that Vision-Language Models (VLMs) used for optical character recognition produce fluent but visually unsupported text, relying heavily on language priors rather than actual image content. Testing on Ancient Greek critical editions reveals VLMs generate plausible errors while traditional OCR produces local noise, with token-level grounding analysis showing model-specific vulnerabilities to hallucination.