Think Inside the Chunk: RegulaRAG for Regulation-Compliant Scenario Generation using LLMs: A Case Study of UN Regulation No. 152

Optimizing Context and Cost in LLM ‐Based Unit Test Generation: A Study on External Dependency Retrieval Strategies

While Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, their effectiveness in unit testing is often constrained by insufficient context regarding external dependencies. This limitation is particularly pronounced in industrial settings, where proprietary code remains opaque to the model. To address this challenge, we present a systematic empirical study of multiple strategies for context enrichment and optimization in LLM‐based unit test generation, conducted on seven diverse projects (three open‐source and four proprietary industrial systems), encompassing 261 distinct methods. By evaluating seven implementations (ranging from basic prompts to optimized context reduction strategies) across 10 independent runs, we analysed a total of 28,710 test suites. Our results demonstrate that combining prompt engineering with external dependency retrieval achieves an average branch coverage increase of 11.52 percentage points on industrial software over the baseline, with statistically significant improvements across all competing implementations. Beyond coverage, richer context substantially reduces generation‐repair iterations, cutting median execution time by 51.3% in industrial projects. We further show that reducing external dependencies to method signatures alone decreases input token consumption by up to 46.6% (25.4% in industrial projects) while fully preserving the coverage and efficiency gains of the complete retrieval approach. To confirm that these benefits are not tied to a specific model, we replicate the core comparison across three LLM backends from different families, obtaining a consistent, statistically significant coverage improvement on industrial code in every case. These findings establish this optimized context strategy as a cost‐effective solution for scalable, industrial‐grade automated test generation.

Multimodal Language Models Benchmarked Against the NRC Reactor Operator Licensing Examination: Fine-Tuning and Retrieval Strategies

Competence claims for a language model in a safety-critical domain are credible when measured against a standard the domain already enforces. We evaluate an open-weight 31-billion-parameter multimodal model (Gemma 4 31B-IT) on the U.S. Nuclear Regulatory Commission Reactor Operator Generic Fundamentals Examination (GFE), scoring it paper by paper against the 80% criterion applied to every human candidate, with no rounding up. The evaluation set is a census of every GFE administered at the March sitting from 2015 to 2021, giving seven pressurized water reactor (PWR) and seven boiling water reactor (BWR) papers and 697 scored items. Eight configurations cross three model states, the base model, supervised fine-tuning (SFT) on distilled chain-of-thought rationales and retrieval-augmented fine-tuning (RAFT), with three retrieval conditions, none and BM25 retrieval over the Department of Energy Fundamentals Handbooks under fixed-size and structure-aware chunking. Out of the box it answers 51.94% correctly and passes no paper. SFT with fixed-size chunking retrieval passes 8 of 14, reaching 80.23% on PWR items and 79.77% pooled, with a Wilson interval spanning the threshold. The preferred chunking granularity reverses with training state, structure-aware before fine-tuning and fixed-size after, so chunking optimized against a base model cannot be inherited by its fine-tuned descendant. RAFT trails SFT by 2.2 to 2.3 percentage points overall, and the deficit holds in all four reactor-type and chunking strata. The pipeline runs on one workstation with no network access at run time, and the result approaches operator-level command of engineering fundamentals without reliably achieving it.

Capacity vs. architecture: an evaluation of SLMs for automated docstring generation

Comparative Analysis of Context-Extension and Question-Matching RAG Architectures: A Case Study on German Regulatory Documentation

Retrieval-Augmented Generation (RAG) grounds Large Language Models (LLMs) in domain-specific knowledge, yet systematic comparisons of RAG architectures in non-English regulatory domains remain limited. We present a comparative study of context-window extension and Question-to-question Inverted Index Matching (QuIM-RAG), evaluated on the German Core energy market data register (Marktstammdatenregister). Both approaches are implemented in a fully local, privacy-compliant setup using open-source LLMs and assessed through parameter optimization, architectural comparison, and expert validation. QuIM-RAG achieves slightly higher factual correctness (F1: 0.56 vs. 0.54) in automatic evaluation. Expert evaluation shows that 65% of responses are factually correct and only 3% are incorrect. Our results further demonstrate that automated LLM-based metrics systematically underestimate performance and provide less interpretable outcomes compared to domain experts. The study contributes a systematic comparison of RAG strategies for German regulatory contexts, introduces an evaluation framework tailored to accuracy-critical domains, and outlines guidelines for privacy-compliant deployment of RAG systems in high-stakes settings.

SpanUQ: Span-Level Uncertainty Quantification for Large Language Model Generation

Uncertainty estimation is essential not only for the trustworthy deployment of large language models (LLMs) but also as a foundation for self-refinement in LLM generation. However, existing approaches operate at suboptimal granularities: token-level scores lack semantic coherence, while sequence-level scores fail to localize errors. We formalize Span-Level Uncertainty Estimation (SLUE), a new task that targets the natural granularity for uncertainty: semantically coherent text spans, each conveying a single assessable unit of meaning. To address this task, we introduce SPANUQ, a lightweight probe that distills the uncertainty knowledge from expensive multi-sample inference into a single forward pass over LLM hidden states. SPANUQ employs a DETR-style span decoder to simultaneously detect spans and estimate their uncertainty via a Mixture of Beta distribution, trained with a principled combination of Beta NLL regression and contrastive ranking objectives. We construct SPANUQ-BENCH, the first span-level uncertainty benchmark comprising 20K prompts, 293K annotated spans, and continuous soft labels derived from multi-sample claim verification. Experiments on five LLM backbones show that SPANUQ consistently achieves the best span-level uncertainty quality, outperforming the strongest probe baseline and all sampling-based methods while being 10-20x faster. Its DETR-based span detector attains 0.910 F1, surpassing the best heuristic by 39.4%, enabling precise error localization that sequence-level methods cannot provide. The framework generalizes across five LLMs spanning two model families.

HiRoute: Hierarchical Routed Prompt Tuning for Safety Alignment of Large Language Models

Experiments across three instruction-tuned models show that HiRoute achieves high safety rates across multiple safety benchmarks while preserving safe-response helpfulness, reducing over-refusal, and maintaining competitive performance on general-purpose tasks.