The paper introduces behavioral correctness assumptions as a new framework for evaluating reference-based automatic evaluation methods in natural language generation. It defines a taxonomy of correctness-preserving and correctness-altering assumptions and operationalizes them through controlled response transformations to specify expected scoring behaviors. The authors evaluate a range of lexical, character-level, semantic, LLM-based, and hybrid evaluators, analyzing their behavior across multiple dimensions and finding that no evaluator satisfies all assumptions, revealing distinct behavioral trade-offs not evident from aggregate scores.
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.
Reference-based text evaluation metrics, which are widely used to assess natural language generation systems, score a candidate response by comparing it with a reference response. The reliability of an evaluation metric is usually judged by its statistical correlation with human ratings.
CriticGen introduces a generation‑aware evaluation framework that generates sample‑specific evaluation dimensions and scoring criteria across categories such as subjective, objective, and self‑derived constraints. These dynamic rubrics produce a score, reason, executable refinement suggestion, and a refined answer, enabling models to diagnose and target flaws in their responses. Experiments show significant gains in rubric quality, score correlation, and actionable feedback, with 73.17% of answers improved and a 93.28% non‑degradation rate.
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.
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.
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.
iFlip is an iterative refinement method for generating counterfactual examples using large language models. It incorporates three feedback types—model confidence, feature attribution, and natural language—to guide successive edits. Experiments show iFlip outperforms five state‑of‑the‑art baselines, achieving a 57.8% higher validity rate and improving model performance through counterfactual data augmentation.
The paper introduces UPHELD, a large benchmark of human-to-human dialogues written by professional script writers, featuring realistic turn densities and over 36,000 per-turn human annotations. It evaluates existing automatic metrics and LLM-as-a-judge methods, finding them unreliable against expert human judgment. Using UPHELD, the authors develop a Mixture-of-Judges framework that improves correlation with human assessments by about 30%.
The paper examines LLM-as-a-Judge systems used to assess AI-generated text, questioning the assumption that judgments are derived from reasoning over responses and rubrics. It finds that classifiers trained solely on rubric text can predict judge outputs, indicating that rubrics contain recoverable evaluative signals independent of the responses. Counterfactual experiments show judges often fail to adjust decisions when either the response or rubric criterion is reversed, raising doubts about the reliability of rubric-based LLM evaluation.
arXiv:2608. 01423v1 Announce Type: cross Abstract: Reference-based text evaluation metrics, which are widely used to assess natural language generation systems, score a candidate response by comparing it with a reference response.
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. We propose BINEVAL, a framework that decomposes evaluation criteria into atomic binary questions and aggregates the resulting verdicts into interpretable, multi-dimensional scores.
arXiv:2609.15561v1 Announce Type: new Abstract: Evaluating the factual correctness of large language models (LLMs) is vital for many applications. But are our evaluation tools themselves trustworthy?...