paper-with-me

Papers

Edit-level Majority Voting Mitigates Over-Correction in LLM-based Grammatical Error Correction

2026-05-13 · Takumi Goto, Yusuke Sakai, Taro Watanabe arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.13624

Code (0)

등록된 구현이 없습니다.

Tasks

Grammatical Error Correction

Similar Papers 제목 키워드 기반

Efficient Test-Time Retrieval Augmented Generation

2025-11-02 · Hailong Yin, Bin Zhu, Jingjing Chen, Chong-Wah Ngo arxiv

Although Large Language Models (LLMs) demonstrate significant capabilities, their reliance on parametric knowledge often leads to inaccuracies. Retrieval Augmented Generation (RAG) mitigates this by incorporating externa…

Open-Domain Question AnsweringRecipe GenerationImage Captioning

Beyond Majority Voting: Towards Fine-grained and More Reliable Reward Signal for Test-Time Reinforcement Learning

2025-12-17 · Weiqin Wang, Yile Wang, Kehao Chen, Hui Huang arxiv

Test-time reinforcement learning mitigates the reliance on annotated data by using majority voting results as pseudo-labels, emerging as a complementary direction to reinforcement learning with verifiable rewards (RLVR) …

Reinforcement Learning

Semantic Voting: Execution-Grounded Consensus for LLM Code Generation

2026-05-09 · Shan Jiang, Zijian Yi, Chenguang Zhu arxiv

LLM code-generation pipelines often sample multiple candidates and select one final answer without access to a complete oracle. Existing pipelines mix textual voting, ranking, and execution-based agreement, but the relat…

Code Generation

Sparse Signal Recovery for Binary Compressed Sensing by Majority Voting Neural Networks

2016-10-29 · Daisuke Ito, Tadashi Wadayama

In this paper, we propose majority voting neural networks for sparse signal recovery in binary compressed sensing. The majority voting neural network is composed of several independently trained feedforward neural networ…

compressed sensing

Regularized Data Programming with Automated Bayesian Prior Selection

2022-10-17 · Jacqueline R. M. A. Maasch, Hao Zhang, Qian Yang, Fei Wang 외

The cost of manual data labeling can be a significant obstacle in supervised learning. Data programming (DP) offers a weakly supervised solution for training dataset creation, wherein the outputs of user-defined programm…