Evaluating In-Context Learning and Retrieval Strategies for Devanagari Post-OCR Correction
CharBM25 is established as an effective, GPU-free retrieval strategy that matches or exceeds dense retrieval at negligible computational cost, and combining it with a general-purpose LLM of 12B+ parameters delivers reliable, training-free Devanagari post-OCR correction without task-specific fine-tuning.
Abhishek Bhandari, Gaurav Harit
· 0 citations