paper-with-me

홈 › Papers

Beyond the Mean: Within-Model Reliable Change Detection for LLM Evaluation

2026-04-30 · Jon-Paul Cacioli arxiv

We adapted the Reliable Change Index (RCI; Jacobson and Truax, 1991) from clinical psychology to item-level LLM version comparison on 2,000 MMLU-Pro items (K=10 samples at T=0.7). Two within-family pairs were tested: Llama 3 to 3.1 (+1.6 points) and Qwen 2.5 to 3 (+2.8 points). On the full benchmark, most items showed no reliable change (79% and 72%). However, over half the items were floor/ceiling. Among analysable items, change was bidirectional with large effect sizes: 34% improved and 28% deteriorated for Llama; 47% improved and 39% deteriorated for Qwen (median |delta p| = 0.50 and 0.90). Churn was asymmetric by difficulty: low-accuracy items improved, high-accuracy items deteriorated. Domain-level decomposition revealed family-specific reversals: Llama lost physics while Qwen lost law. Greedy single-shot evaluation missed 42% of reliably changed items and falsely flagged 25% of unchanged items. The aggregate accuracy gain is the net residual of opposing item-level movements. We recommend reporting churn rate alongside aggregate accuracy.

📄 PDF Abstract BibTeX arXiv:2604.27405

Code (0)

등록된 구현이 없습니다.

Tasks

Change Detection

Similar Papers 제목 키워드 기반

Lexical Semantic Change Discovery

2021-06-06 · ACL 2021 5 · Sinan Kurtyigit, Maike Park, Dominik Schlechtweg, Jonas Kuhn 외

While there is a large amount of research in the field of Lexical Semantic Change Detection, only few approaches go beyond a standard benchmark evaluation of existing models. In this paper, we propose a shift of focus fr…

Change Detection

Transformer-based Multimodal Change Detection with Multitask Consistency Constraints

2023-10-13 · BiYuan Liu, HuaiXin Chen, Kun Li, Michael Ying Yang

Change detection plays a fundamental role in Earth observation for analyzing temporal iterations over time. However, recent studies have largely neglected the utilization of multimodal data that presents significant prac…

Change DetectionEarth Observation

Beyond Segmentation: An Oil Spill Change Detection Framework Using Synthetic SAR Imagery

2026-01-05 · Chenyang Lai, Shuaiyu Chen, Tianjin Huang, Siyang Song 외 arxiv

Marine oil spills are urgent environmental hazards that demand rapid and reliable detection to minimise ecological and economic damage. While Synthetic Aperture Radar (SAR) imagery has become a key tool for large-scale o…

Change Detection

Robust Fuzzy corner detector

2014-05-21 · Erik Cuevas, Daniel Zaldivar, Marco Perez, Edgar Sanchez 외

Reliable corner detection is an important task in determining the shape of different regions within an image. Real-life image data are always imprecise due to inherent uncertainties that may arise from the imaging proces…

Reliable and Interpretable Drift Detection in Streams of Short Texts

2023-05-28 · Ella Rabinovich, Matan Vetzler, Samuel Ackerman, Ateret Anaby-Tavor

Data drift is the change in model input data that is one of the key factors leading to machine learning models performance degradation over time. Monitoring drift helps detecting these issues and preventing their harmful…

Change Point DetectionDrift Detectionintent-classificationIntent Classification