The paper evaluates whether breaking down evaluation tasks into simpler sub‑tasks improves the LLM-as-a-judge (LLMaJ) framework for reference‑free NLG assessment. Systematic comparisons across multiple datasets show no performance advantage for LLMaJ methods that use task decomposition over a fair baseline that does not. The authors attribute previously reported gains to the use of human labels for training rather than to decomposition itself, and note that LLMaJ without decomposition can match human annotators when such labels are available.
The LLM-as-a-judge (LLMaJ) framework has emerged as a promising solution for cheap, reproducible, reference-free Natural Language Generation (NLG) evaluation. Prior work seeks to improve LLMaJ by deco...
The paper introduces Active Testing, a framework that selects the most informative test samples for annotation in NLP, aiming to reduce human effort while accurately estimating model performance. Experiments across 18 datasets and 4 embedding strategies show up to 95% annotation savings with less than 1% loss in performance estimation accuracy. The authors also propose an adaptive stopping criterion to determine the optimal number of samples without a predefined budget.
arXiv:2606. 02837v1 Announce Type: cross Abstract: Accurate translation from Natural Language to First-Order Logic (NL-to-FOL) underpins neurosymbolic AI systems and Natural Language Inference (NLI), making the quality of NL-to-FOL benchmarks essential -- yet these datasets have never been rigorously audited.
arXiv:2604. 09497v2 Announce Type: replace-cross Abstract: Accurate evaluation is central to the large language model (LLM) ecosystem, guiding model selection and downstream adoption across diverse use cases.
The paper introduces BASSE, a multilingual meta‑evaluation dataset containing 2,040 human‑rated abstractive summaries produced manually or by five LLMs with four prompts. Annotators scored each summary on coherence, consistency, fluency, relevance, and 5W1H using a 5‑point Likert scale. Benchmarking shows proprietary LLM‑judge models best align with human judgments, followed by criteria‑specific automatic metrics, while open‑source judge LLMs perform poorly.
arXiv:2606. 02255v1 Announce Type: cross Abstract: Human annotation is the empirical foundation of much NLP research, from dataset construction to model evaluation, but papers often leave unclear who produced the annotations and how the annotation process was controlled.
arXiv:2503.06868v2 Announce Type: replace-cross Abstract: Existing long-text generation methods produce lengthy outputs from short inputs, leaving long-input-to-long-output generation underexplored....
The paper introduces TextQ‑German, a dataset suite for evaluating German natural language generation (NLG) from a Quality of Experience (QoE) perspective, covering tasks such as summarization and machine translation. Human ratings collected via crowdsourcing identify perceptual quality dimensions, and the authors develop automatic QoE prediction models—including transformer‑based, linguistic feature‑based, and hybrid approaches—showing that hybrid models outperform pure transformers and that linguistic features alone can rival fine‑tuned language models. The dataset is further enriched with large language model (LLM) outputs annotated with overall QoE scores, and validation on held‑out data demonstrates generalization to unseen data. "whyItMatters":"The resource provides a publicly accessible benchmark and baseline models for human‑centered NLG evaluation, enabling the development of systems that better align with human quality perception."
The paper introduces a register-aware framework to evaluate how human-like large language models (LLMs) are, focusing on linguistic feature distributions rather than factual correctness. It uses Maximum Mean Discrepancy (MMD) and 67 Biber lexico‑grammatical features to compare LLM‑generated texts with human reference corpora across different registers. Experiments on seven instruction‑tuned, open‑source models across five English datasets show that all LLMs deviate from human baselines, with closeness to human language varying by register and not by model size.
The paper introduces LongJudgeBench, a benchmark designed to evaluate large language models (LLMs) acting as judges for long-form text generation. It highlights that long-form evaluation requires complex, document-level assessments beyond simple length, such as organization, coverage, depth, consistency, and scenario-specific quality. Experiments show a significant reliability gap among current LLM judges, indicating instability across scenarios and limited effectiveness of rubrics or references.
arXiv:2606. 27226v1 Announce Type: new Abstract: Evaluating LLM outputs remains a major bottleneck in NLP: human evaluation is expensive and slow, lexical metrics correlate poorly with human judgments on open-ended generation, and holistic LLM judges often produce opaque scores that are hard to debug.
The paper introduces Iterative MBR Distillation for Error Span Detection (ESD) in machine translation, a self‑evolution framework that replaces human annotations with pseudo‑labels generated by a large language model. By iteratively applying Minimum Bayes Risk decoding, the method produces high‑quality error spans without costly human effort. Experiments on WMT Metrics Shared Task datasets show that models trained solely on these pseudo‑labels outperform both unadapted baselines and supervised models trained on human data at system and span levels, while keeping sentence‑level performance competitive.