Edit-level Majority Voting Mitigates Over-Correction in LLM-based Grammatical Error Correction
It addresses the over-correction problem in LLM-based grammatical error correction for multilingual settings, offering a simple, training-free improvement.
The paper proposes a training-free inference method using edit-level majority voting to reduce over-correction in LLM-based grammatical error correction, outperforming greedy and MBR decoding across nine benchmarks in seven languages.
Grammatical error correction using large language models often suffers from the over-correction issue. To mitigate this, we propose a training-free inference method that performs edit-level majority voting over multiple candidates generated by a single model, without requiring model modifications or additional training. Across nine benchmarks covering English, Czech, German, Ukrainian, Korean, Hindi, and Romanian, the proposed method outperforms both greedy and MBR decoding in most cases. Moreover, it yields stable correction quality regardless of the instruction prompts used. We release two repository supporting GEC datasets loading and LLM inference.