Larger Context Window, Fewer Overcorrections: Optimizing Prompts and Batching for Minimal-Edit Grammatical Error Correction

• URL: http://arxiv.org/abs/2609.10810v1
• Date: Wed, 09 Sep 2026 20:24:48 GMT
• Title: Larger Context Window, Fewer Overcorrections: Optimizing Prompts and Batching for Minimal-Edit Grammatical Error Correction
• Abstract summary: Minimal-edit Grammatical Error Correction (GEC) is a challenging task for zero-shot and few-shot prompted Large Language Models (LLMs)<n>We introduce a prompt-based approach that closes the gap to fine-tuned models through three advances in GEC prompting methodology.<n> powered by Gemini 3.1Pro, our prompt $F_0.5=78.32$ achieves a new prompt-based SOTA while shrinking the gap to finetuned single-model SOTA to a mere $0.38$ points.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Minimal-edit Grammatical Error Correction (GEC) is a challenging task for zero- and few-shot prompted Large Language Models (LLMs), which systematically overcorrect and degrade $F_{0.5}$ by rewriting well-formed spans. While fine-tuning provides an effective solution, it imposes substantial infrastructure demands. We introduce a prompt-based approach that closes the gap to fine-tuned models through three advances in GEC prompting methodology. First, we introduce taxonomy-based instructions to enforce minimal-edit constraints with a comprehensive list of grammatical error rules, equipping the LLM with a bounded, metric-aligned scope of correctable edits, which benefits the strongest models while remaining model-dependent overall. Second, we show that batching multiple uncorrected sentences into a single input context acts as a targeted regularizer against overcorrection, systematically reducing the edit rate across diverse LLM families; we hypothesize this arises from attention dilution effect induced by the bounded capacity of self-attention scores. Finally, LLM-assisted Prompt Optimization refines these instructions. Powered by Gemini 3.1-Pro, our prompt achieves $F_{0.5}=78.32$ on the BEA-2019 test set - establishing a new prompt-based SOTA while shrinking the gap to the fine-tuned single-model SOTA (Staruch et al., 2025) to a mere $0.38$ points. Code, prompts, and outputs are publicly available.

Related papers

• Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization [18.737087162461563]
  Test-time compute scaling has become a powerful lever for improving large language model performance.<n>Yet deploying these techniques under finite inference budgets requires a decision that current systems largely ignore.<n>We formalize this as a constrained optimization problem (maximize expected accuracy subject to an average compute budget) and solve it with a two-stage Solve-then-Learn pipeline.
  arXiv  Detail & Related papers  (2026-04-16T10:39:22Z)
• POaaS: Minimal-Edit Prompt Optimization as a Service to Lift Accuracy and Cut Hallucinations on On-Device sLLMs [2.2406645586052925]
  Small language models (sLLMs) are increasingly deployed on-device, where imperfect user prompts can trigger factual errors and hallucinations.<n>We propose PO, a minimal-edit prompt optimization layer that routes each query to lightweight specialists.
  arXiv  Detail & Related papers  (2026-03-17T01:05:39Z)
• $\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space [71.23672814629448]
  $nabla$-Reasoner is an iterative generation framework that integrates differentiable optimization over token logits into the decoding loop.<n>$nabla$-Reasoner achieves over 20% accuracy improvement on a challenging mathematical reasoning benchmark.
  arXiv  Detail & Related papers  (2026-03-05T08:42:54Z)
• Robust LLM-based Column Type Annotation via Prompt Augmentation with LoRA Tuning [0.749377967268953]
  Column Type.<n>CTA is a fundamental step towards enabling schema alignment and semantic understanding.<n>Existing encoder-only language models achieve high accuracy when fine-tuned on labeled columns.<n>We present a parameter-efficient framework for CTA that trains models over prompt-augmented data.
  arXiv  Detail & Related papers  (2025-12-28T02:04:17Z)
• Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Sampling [90.86991492288487]
  evaluating constraint on every token can be prohibitively expensive.<n> LCD can distort the global distribution over strings, sampling tokens based only on local information.<n>We show that our approach is superior to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-04-07T18:30:18Z)
• Teaching Your Models to Understand Code via Focal Preference Alignment [70.71693365502212]
  In existing approaches, a set of n candidate solutions is evaluated based on test case success rates.<n>Because this approach aligns entire failing code blocks rather than pinpointing specific errors, it lacks the granularity necessary to capture meaningful error-correction relationships.<n>We propose Target-DPO, a new preference alignment framework that mimics human iterative debug to refine Code LLMs.
  arXiv  Detail & Related papers  (2025-03-04T16:56:34Z)
• Rethinking the Residual Distribution of Locate-then-Editing Methods in Model Editing [14.958557185068]
  Model editing enables targeted updates to the knowledge of large language models.<n> locate-then-edit methods first identify critical layers, then compute residuals at the final critical layer based on the target edit.<n> residual distribution, a core mechanism in these methods, introduces weight shift errors that undermine editing precision.<n>We propose the BLUE strategy to enhance locate-then-edit methods.
  arXiv  Detail & Related papers  (2025-02-06T03:20:17Z)
• Subtle Errors in Reasoning: Preference Learning via Error-injected Self-editing [59.405145971637204]
  We propose a novel preference learning framework called eRror-Injected Self-Editing (RISE)<n>RISE injects predefined subtle errors into pivotal tokens in reasoning or steps to construct hard pairs for error mitigation.<n>Experiments validate the effectiveness of RISE, with preference learning on Qwen2-7B-Instruct yielding notable improvements of 3.0% on GSM8K and 7.9% on MATH with only 4.5K training samples.
  arXiv  Detail & Related papers  (2024-10-09T07:43:38Z)
• Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization [78.82586283794886]
  $chi2$-Preference Optimization ($chi$PO) is an efficient offline alignment algorithm provably robust to overoptimization.<n>$chi$PO implements the principle of pessimism in the face of uncertainty via regularization.<n>$chi$PO's simplicity and strong guarantees make it the first practical and general-purpose offline alignment algorithm provably robust to overoptimization.
  arXiv  Detail & Related papers  (2024-07-18T11:08:40Z)
• LM-Combiner: A Contextual Rewriting Model for Chinese Grammatical Error Correction [49.0746090186582]
  Over-correction is a critical problem in Chinese grammatical error correction (CGEC) task. Recent work using model ensemble methods can effectively mitigate over-correction and improve the precision of the GEC system. We propose the LM-Combiner, a rewriting model that can directly modify the over-correction of GEC system outputs without a model ensemble.
  arXiv  Detail & Related papers  (2024-03-26T06:12:21Z)
• Factual Error Correction for Abstractive Summaries Using Entity Retrieval [57.01193722520597]
  We propose an efficient factual error correction system RFEC based on entities retrieval post-editing process. RFEC retrieves the evidence sentences from the original document by comparing the sentences with the target summary. Next, RFEC detects the entity-level errors in the summaries by considering the evidence sentences and substitutes the wrong entities with the accurate entities from the evidence sentences.
  arXiv  Detail & Related papers  (2022-04-18T11:35:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.