Research
Enhancing Small Language Models for Power Outage Report Generation via Minimum Risk Training
arXiv:2609.27197v1 Announce Type: new Abstract: Minimum Risk Training (MRT) enables neural machine translation models to directly optimize sequence-level evaluation metrics instead of relying only on
arXiv:2609.27197v1 Announce Type: new 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
Related
- POTracker: Optimizing Large Language Models for Standard-Compliant Power Outage Report Generation
- LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs
- Extracting Small Translation Specialists from LLMs by Aggressively Pruning Experts
- DomainPilot: Domain-Level Loss-Guided Two-Stage Data Mixture Optimization for Efficient Language Model Fine-Tuning
- Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks
Source: arXiv cs.AI | 2026-09-24