This work applies MRT to power outage report generation for the Outage Data Initiative Nationwide (ODIN), transforming heterogeneous reports into standardized XML compliant with CIM IEC 61968-3.
Abstract
Minimum Risk Training (MRT) enables neural machine translation models to directly optimize sequence-level evaluation metrics instead of relying only on token- level maximum-likelihood objectives Shen et al. [2016]. Although introduced a decade ago, recent work shows renewed potential for risk-based optimization in modern language models Yang et al. [2024], Jinnai et al. [2025]. We apply MRT to power outage report generation for the Outage Data Initiative Nationwide (ODIN), transforming heterogeneous reports into standardized XML compliant with CIM IEC 61968-3. Our MRT approach improves Qwen2.5-7B-Instruct overall accuracy from 16.20% to 68.95%, demonstrating the effectiveness of sequence- level optimization for domain-specific structured generation
Results show that supervised models outperform LLMs on macro-F1 and precision, while newer LLM generations achieve competitive scores, suggesting that combining them with supervised models may be the best practice.
Christos Petridis, Z. Obradovic, M. Kezunović· 0 citations
The environmental cost of adapting Large Language Models (LLMs) is a growing concern in artificial intelligence research. We present a systematic comparison between gradient-based fine-tuning and a rule-based prompt optimization framework for financial tabular reasoning. Using the TAT-QA dataset, we demonstrate that ou...
Róbert Lakatos, Árpád Pándy, András Hajdu· 2026 IEEE 4th Conference on...· 0 citations
Results indicate that the proposed multi-stage post-training framework effectively improves LLM performance on real-world text-based fault diagnosis, and provides a practical and extensible solution for intelligent maintenance decision support in complex electromechanical systems.
Large language models (LLMs) can integrate multisource information and generate structured maintenance recommendations. However, their outputs may underestimate risk and fluctuate over time, reducing the practical executability of decisions. To address these issues, this study proposes a trustworthy LLM-based method fo...
Kai Wang, Meng Yan, Da-Qian Yu et al.· Machines· 0 citations
A modular correction framework that augments pretrained LLMs with Activated LoRA (aLoRA) adapters and a context-aware routing mechanism to eliminate harms from misaligned model responses is proposed, offering a lightweight and efficient path toward safer and more controllable LLM deployments.
Robert C. Campbell, Momin Abbas, Muneeza Azmat et al.· 0 citations
XREPOTEST is introduced, a multilingual repository-level benchmark for unit test generation spanning five underexplored languages: Rust, Go, Julia, PHP, and Ruby, and Invocation Rate is proposed to assess whether generated tests meaningfully exercise the intended functionality.
L. Dung, Dong Cao Van, Nam Le Hai et al.· 1 citation
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Microsoft Research Blog· microsoft.comOct 15, 2026
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
