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.
Intent classification is a core component of task-oriented dialogue systems, yet practitioners have limited systematic guidance for selecting deployable open-weight language models under compute, latency, and robustness constraints. We present a systematic zero-shot evaluation of 41 open-weight language models spanning 15 families and the 135M--9B parameter range across eight English single-label intent-classification datasets. A ninth dataset, ATIS, uses five labeled demonstrations and is reported as an auxiliary five-shot result. The evaluation includes standard benchmarks, a large-scale voice-assistant corpus, and production-derived e-commerce datasets. Beyond exact-match accuracy, we analyze confidence calibration, robustness to realistic input perturbations, statistical reliability of model rankings, deployment efficiency, and benchmark saturation. Our results show that instruction-tuned 3B models can outperform several evaluated 7B base models, that differences among leading models on MASSIVE are statistically indistinguishable under pairwise McNemar tests, and that widely used benchmarks such as SNIPS have become saturated and no longer meaningfully discriminate among current open-weight models. Instruction tuning's effect on confidence calibration is inconsistent rather than uniformly harmful. These findings provide practical guidance for selecting and evaluating open-weight language models for intent classification.
Parishruthi Ganesh, Gerry V. Dozier, Cheryl D. Seals· 0 citations
Generating regulation-compliant test scenarios is essential for validating safety-critical automotive systems, yet Large Language Models (LLMs) struggle to ground outputs in long, hierarchical standards. We present RegulaRAG, a Retrieval-Augmented Generation (RAG) pipeline that couples SmartChunking, reference-aware enrichment of paragraphs and tables via graph traversal, with Smart Retrieve&Rerank over these enriched units. To test our system, we evaluate on a manually curated dataset covering all scenarios in UN Regulation No. 152 (AEBS). Our study comprises: (i) a three-step progressive search that identifies near-optimal retrieval parameters without exhaustive grid search; (ii) head-to-head comparisons against five baseline RAG systems; and (iii) a robustness stress test that scales the source corpus with distractor content. Outputs are evaluated using a customized penalized scoring metric. Across all experiments, RegulaRAG achieves the highest average Meta-Score (82.99), outperforming the next-best system by 43% (NoRAG: 57.94), while operating at 14k-25k tokens per query versus up to 500k for graphcentric baselines. It maintains strong performance, remaining stable even as the number of regulatory sources grows, whereas competing RAG systems degrade sharply in both quality and robustness.
Vahid Zolfaghari, Nenad Petrovic, André Schamschurko et al.· 0 citations
Large Language Models (LLM) have become valuable tools for automatic text simplification, yet their output quality is highly sensitive to inference-time parameters such as temperature, repetition penalty, top-p, and top-k. These parameters are typically set heuristically rather than systematically optimized. In this work, we apply Covariance Matrix Adaptation Evolution Strategy (CMA-ES) to identify high-performing inference configurations for an instruction-tuned Large Language Model (LLM) fine-tuned for Spanish Text Simplification (TS) on the Financial Education Corpus IN SpAnish (FEINA) benchmark. Using System output Against References and against the Input sentence (SARI) as the optimization objective and Sentence Bidirectional Encoder Representations from Transformers (SBERT) as a monitoring metric, CMA-ES converges in 9 of 25 generations, improving test-set SARI from 36.57 (default) to 38.87 (+6.3%) while increasing SBERT from 0.85 to 0.88. Grid search analysis reveals that repetition penalty and temperature are the dominant factors influencing simplification quality, while top-k and maximum tokens have negligible effects. The strong positive correlation between SARI and SBERT across all 2,500 evaluated configurations provides empirical support for the single-objective approach within the studied setting. Our framework offers a replicable methodology for inference parameter optimization applicable to Spanish and other under-resourced languages in Latin American Natural Language Processing (NLP) contexts.
Nelson Pérez-Rojas, Danny Xie-Li, M. Solís et al.· Proceedings of the Genetic a...· 0 citations
Legal information processing spans retrieval, entailment and judgment prediction problems, requiring text matching, reasoning and robust generalisation with limited supervision. We report Team DU's participation in all five tasks of COLIEE 2026, using open-weight systems for legal case retrieval, case entailment, statute retrieval and entailment, and legal judgment prediction. For Tasks 3 and 4, all models predate the 15 July 2025 cutoff required by the rules. For Task 4 (statute entailment), a cross-architecture ensemble of nine models from three families achieves 96.3% accuracy, placing first among 33 submissions from 11 teams. For the Pilot Task (tort prediction and rationale extraction), a multi-view system combining five claim-level models and refining the verdict using features derived from the claim predictions achieves 73.1% TP accuracy and 68.2% RE F1 as an unofficial submission, scoring above all official entries on TP and matching the highest on RE. For Task 2 (legal case entailment), changing only the prompt from single- to multi-selection raises F1 from 0.343 to 0.555 in post-competition evaluation on released gold labels, exceeding the best official submission (F1 = 0.490). For Task 3 (statute retrieval and entailment), replacing the entailment model with Qwen3-235B and a structured legal reasoning prompt raises accuracy from 79.3% to 91.5% in post-competition analysis. For Task 1 (legal case retrieval), a learning-to-rank system combining lexical and semantic retrieval with structural, citation authority, and temporal features (34 in total) achieves F1 = 0.314 (rank 11 of 54 submissions from 22 teams). Overall, legal information processing benefits from different inductive biases across tasks, with cross-architecture ensembling, feature-based reranking and retrieval-augmented prompting each proving most effective in different settings.
Amal Saad Alshehri, N. Bencomo, Amir Atapour-Abarghouei· 0 citations
Retrieval-augmented fine-tuning (RAFT) can improve small language models (sLMs) on retrieval-grounded question answering, but the synthetic training data produced by commercial large language models (LLMs) vary in quality. This paper contributes a quality-aware selection protocol—rather than a new RAFT or QLoRA method—that scores LLM-generated alternatives along four embedding-based dimensions (question relevance, answer faithfulness, QA coherence, and semantic similarity) and selects one alternative per task before parameter-efficient fine-tuning. Under pre-specified paired-bootstrap contrasts with Holm correction, the parameter-free faithfulness-based selector only-AF significantly exceeds random selection on Gemma-2-9B-IT (ΔF1 = +0.106, 95% CI [+0.043, +0.174], Holm-corrected p = 0.019), and its pre-specified weighted companion af-70 (wAF = 0.70) shows the same confirmed pattern (Holm-corrected p = 0.002). Both effects persist under a Korean character-level F1 that removes particles and punctuation (Holm-corrected p = 0.004 and p = 0.042), indicating robustness to the choice of lexical metric. Relative to training on the full 150-row augmented pool, the quality-selected 50-row sets are statistically indistinguishable while using one third of the training data, which we interpret as data efficiency rather than superiority. Across six instruction-tuned models (2B–27B), a significant selector-by-model interaction indicates that the optimal quality axis is model-dependent, and the two smallest models show no benefit from selection. The study’s confirmatory contrasts use a small controlled Korean corpus under a transductive design; two pre-registered validation experiments probe external validity. On an independent five-fold larger corpus with a passage-level train/test split, fine-tuning transfers strongly and the selected one-third subsets show no significant difference from the full pool, while the advantage over random selection is directionally positive but small and not significant; under controlled corruption of 35% of the pool, the metrics detect the damaged rows, and for the score-sum selector the selection-versus-random benefit is significantly larger than on the clean pool (difference-in-differences p = 0.0014; directionally consistent but not significant for the faithfulness selectors). Within this scope, quality-aware selection is a promising, data-efficient safeguard for synthetic RAFT data—performing comparably to full-pool training at one third of the cost, with growing value as pool quality degrades—and larger-scale external validation remains future work.
Large language models routinely produce fluent answers to single-shot prompts, yet deploying them as reliable components of a domain decision system is substantially harder. Closing this gap is the work of harness engineering: the deliberate composition of deterministic scaffolding (symbolic filters, retrieval, schema-typed I/O, LLM-as-judge loops, HITL gates, persistent state, audit trails) around an LLM core. We present a case study in academic supervision, a domain combining high-stakes recommendation, longitudinal accountability, and structured operational workflows. We compare a baseline Academic Supervision Assistant (ASA), a GPT-5 chatbot with no scaffolding, against a multi-module system, Academic Supervision System (ASuS) that wraps the much smaller GPT-4o-mini in a LangGraph harness with symbolic semantic retrieval, schema-validated outputs, LLM-as-judge with bounded retry, HITL gates, deterministic weighted risk scoring with LLM narration, and a per-node SQLite audit trail. The evaluation rubric is retargeted at six harness-mechanism dimensions (grounding, explainability, consistency, process integrity, cognitive load, constraint adherence). A blind ten-rater hybrid evaluation, supplemented by a 2 x 2 model-harness ablation, finds that ASuS, despite using a much smaller base model, outscores ASA on every dimension. Across ten raters the pooled mean for ASuS is 4.08 versus 1.23 for ASA, and 8 of 10 raters reject the null at alpha = 0.05 on a paired Wilcoxon test; full numbers are in Sections 6.4 and 6.7. The ablation confirms that the structural contributions of the harness are largely model-invariant. We extract seven recurring harness-engineering patterns and argue that where reliability, traceability, and institutional consistency matter more than open-ended fluency, harness engineering challenges the prevailing'bigger model is better'intuition.