# Context-Enhanced Granular Edit Representation for Efficient and Accurate ASR Post-editing

arXiv: https://arxiv.org/abs/2509.14263 · HTML: https://mlsanity.com/paper/2509.14263/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 22 references that are in the map.
- First posted on arXiv 13 Sep 2025.

## Builds on (most cited first, 18 of 18)

- [Visual In-Context Learning for Large Vision-Language Models](https://mlsanity.com/paper/2402.11574/) (2024)
- [Improving Medical Large Vision-Language Models with Abnormal-Aware Feedback](https://mlsanity.com/paper/2501.01377/) (2025)
- [Knowledge Graph Enhanced Large Language Model Editing](https://mlsanity.com/paper/2402.13593/) (2024)
- [MemoryMamba: Memory-Augmented State Space Model for Defect Recognition](https://mlsanity.com/paper/2405.03673/) (2024)
- [ASR Error Correction using Large Language Models](https://mlsanity.com/paper/2409.09554/) (2024)
- [Knowledge Updating? No More Model Editing! Just Selective Contextual Reasoning](https://mlsanity.com/paper/2503.05212/) (2025)
- [ASR-GLUE: A New Multi-task Benchmark for ASR-Robust Natural Language Understanding](https://mlsanity.com/paper/2108.13048/) (2021)
- [How Good are Commercial Large Language Models on African Languages?](https://mlsanity.com/paper/2305.06530/) (2023)
- [ASR-EC Benchmark: Evaluating Large Language Models on Chinese ASR Error Correction](https://mlsanity.com/paper/2412.03075/) (2024)
- [CoEdPilot: Recommending Code Edits with Learned Prior Edit Relevance, Project-wise Awareness, and Interactive Nature](https://mlsanity.com/paper/2408.01733/) (2024)
- [ReSpace: Text-Driven Autoregressive 3D Indoor Scene Synthesis and Editing](https://mlsanity.com/paper/2506.02459/) (2025)
- [Diacritic Recognition Performance in Arabic ASR](https://mlsanity.com/paper/2302.14022/) (2023)
- [Full-text Error Correction for Chinese Speech Recognition with Large Language Model](https://mlsanity.com/paper/2409.07790/) (2024)
- [Assessing Human Editing Effort on LLM-Generated Texts via Compression-Based Edit Distance](https://mlsanity.com/paper/2412.17321/) (2024)
- [Correction Focused Language Model Training for Speech Recognition](https://mlsanity.com/paper/2310.11003/) (2023)
- [Large Vocabulary Spontaneous Speech Recognition for Tigrigna](https://mlsanity.com/paper/2402.04254/) (2023)
- [Advancing Semi-Supervised Learning for Automatic Post-Editing: Data-Synthesis by Mask-Infilling with Erroneous Terms](https://mlsanity.com/paper/2204.03896/) (2022)
- [Predicting Compact Phrasal Rewrites with Large Language Models for ASR Post Editing](https://mlsanity.com/paper/2501.13831/) (2025)

## Abstract (arXiv)

Despite ASR technology being full-scale adopted by industry and for large portions of the population, ASR systems often have errors that require editors to post-edit text quality. While LLMs are powerful post-editing tools, baseline full rewrite models have inference inefficiencies because they often generate the same redundant text over and over again. Compact edit representations have existed but often lack the efficacy and context required for optimal accuracy. This paper introduces CEGER (Context-Enhanced Granular Edit Representation), a compact edit representation that was generated for highly accurate, efficient ASR post-editing. CEGER allows LLMs to generate a sequence of structured, fine-grained, contextually rich commands to modify the original ASR output. A separate expansion module deterministically reconstructs the corrected text based on the commands. Extensive experiments on the LibriSpeech dataset that were conducted, CEGER achieves state-of-the-art accuracy, achieving the lowest word error rate (WER) versus full rewrite and prior compact representations.