arXiv:2608.29517v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as essay graders in learning analytics, evaluated almost exclusively with agreement statistics. Educ...
arXiv:2608.30373v1 Announce Type: new Abstract: Multi-Agent Debate (MAD) has been widely adopted to improve LLM-based evaluation by prompting multiple agents to negotiate and reach a consensus. Howev...
Multi-Agent Debate (MAD) has been widely adopted to improve LLM-based evaluation by prompting multiple agents to negotiate and reach a consensus. However, for subjective rubric-based scoring, inter-ag...
The paper introduces a two‑dimensional construct validity framework for evaluating large language models (LLMs) as judges, defining invariance (S) and sensitivity (R) to construct‑preserving and construct‑changing edits. Experiments across seven judges and four domains reveal high invariance (average S = 0.945) but low sensitivity (average R = 0.319), with sensitivity varying by edit type. Audits of public label sets show that surface‑only predictors can reproduce a substantial portion of labels, underscoring that high agreement does not guarantee construct validity.
arXiv:2608.22432v1 Announce Type: cross Abstract: Multilingual LLM judges produce different evaluator-backbone rankings depending on the prompt language: on an eight-language Agent-as-a-Judge benchma...
arXiv:2606. 13221v2 Announce Type: replace Abstract: Evaluating new large language models typically requires costly human annotation campaigns at scale.
IndicQE-APE is a consolidated benchmark that unifies quality estimation (QE) and automatic post‑editing (APE) data for nine Indic language pairs, comprising 126,754 instances with multiple aligned labels such as direct assessment, human post‑edit, word‑level OK/BAD tags, and error explanations. The dataset includes a stratified test set across four difficulty axes and supports training and evaluation of six prompted large language models, three COMET metrics, and three APE systems. Experiments reveal that segments with conflicting holistic and token‑level quality signals are consistently ranked lower, while annotator disagreement shows no effect when controlled for score distribution. whyItMatters":"The benchmark provides a unified resource for training and evaluating QE and APE across Indic languages, enabling consistent comparison of models and metrics on a shared dataset."
The paper introduces a dual‑judge evaluation protocol for vision‑language models in legally grounded tasks, pairing a 0‑10 quality judge with a strict binary semantic‑equivalence judge. Using a controlled UK traffic‑sign interpretation task, the authors analyze 4,680 evaluations across visibility and occlusion conditions, finding moderate association between judges and an asymmetric Type II error pattern that is most pronounced under heavy occlusion. The protocol requires only one additional LLM call and reveals quality‑trustworthiness signals that single‑judge methods miss.
arXiv:2609.00088v1 Announce Type: cross Abstract: LLM judges, models that score another system's output, can be gamed by the systems they score. Recent work identifies one defence that works: the jud...
arXiv:2605. 25240v2 Announce Type: replace-cross Abstract: Two methodologies dominate current practices of benchmarking: rubric-based scoring evaluates items against predefined criteria, whereas comparative judgment elicits pairwise preferences between outputs.
arXiv:2606. 13685v1 Announce Type: cross Abstract: LLM-as-a-Judge is now widely used to rank model outputs, train reward models, and populate public leaderboards, but its run-to-run reliability remains under-characterized.
arXiv:2602. 20629v3 Announce Type: replace Abstract: As Large Language Models (LLMs) saturate elementary benchmarks, the research frontier has shifted from generation to the reliability of automated evaluation.