arXiv AI
Select or Rewrite: Oracle-Guided Fine-Tuning for Generative ASR Post-Editing from N-Best Hypotheses
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
Sep 11
Larger Context Window, Fewer Overcorrections: Optimizing Prompts and Batching for Minimal-Edit Grammatical Error Correction
The paper presents a prompt-based method for minimal-edit grammatical error correction (GEC) that reduces overcorrection in large language models (LLMs). It introduces taxonomy-based instructions, batch prompting to regularize overcorrection, and LLM-assisted prompt optimization, achieving an $F_{0.5}$ score of 78.32 on BEA-2019 with Gemini 3.1-Pro. This approach narrows the performance gap to fine-tuned models while avoiding their infrastructure demands.
arXiv AI
Sep 15
Don't Count the Edits, Judge by the Outcome Alone: Reward-Based Evaluation for Grammatical Error Correction
arXiv:2609.15559v1 Announce Type: cross Abstract: Grammatical error correction (GEC) evaluation has traditionally relied on reference or edit overlap, which can penalize valid rewrites that differ fr...
arXiv AI
Jul 10
UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing
arXiv:2607. 08646v1 Announce Type: cross Abstract: As available training data approaches its physical limit, gains from Scaling Laws have begun to diminish.
arXiv Computation and Language
Sep 22
Diagnose, Then Repair: A Two-Stage MQM-Guided Post-Editing Framework for Domain-Specific Machine Translation
arXiv:2609.22793v1 Announce Type: new Abstract: LLM-based machine translation evaluation can closely match human judgments, but in practice it remains largely diagnostic, with the signals rarely tran...
arXiv Machine Learning
1d ago
Causal Edit Serialization
Causal Edit Serialization (CES) is a framework that enables autoregressive language models to perform revisions—such as insertion, deletion, replacement, copying, and movement—within the same causal token stream. CES uses special pointer tokens paired with predicted source addresses, a lightweight localization head, and dual-index rotary position encoding to localize edits while preserving standard causal attention. Experiments show that CES models can execute complete edits with only a modest increase in clean-text bits per byte, and that post‑training with supervised or reinforcement learning can produce beneficial grammatical error corrections.
arXiv AI
Oct 5
Improving Atomic-Fact Recall via Focused Views in Unstructured Knowledge Editing
The paper introduces FOVEATED, a plug‑and‑play framework that improves atomic‑fact recall in unstructured knowledge editing (UKE) for large language models. By randomly shifting Rotary Position Embedding (RoPE) positions during editing, FOVEATED creates focused views of each sentence, counteracting the context‑reliance problem where edited LLMs reproduce passages but fail to recall individual facts. Experiments show consistent gains across five editors, two LLM backbones, and three benchmarks.