arXiv:2606. 03305v1 Announce Type: new Abstract: Benchmark contamination, where evaluation examples appear in a model's training data, threatens the validity of LLM assessment.
arXiv:2605. 30188v2 Announce Type: replace-cross Abstract: Reliable probability estimates are critical in many machine learning applications, yet modern classifiers are often poorly calibrated.
The paper demonstrates that layer dropout, also known as stochastic depth, can be effectively used in state‑of‑the‑art large language model (LLM) training. By optimizing the layer distribution, schedule, and optimizer settings, the authors show that layer dropout can reduce training loss while saving up to 25 % of training FLOPs. Additionally, layer dropout enables post‑training optimizations such as early exit and self‑speculative decoding, achieving up to 1.5× inference speedup with negligible accuracy loss across models ranging from 271 M to 8.2 B parameters and datasets up to 160 B tokens.
arXiv:2606. 28551v1 Announce Type: cross Abstract: Building performant Vision-Language Models (VLMs) requires carefully curating large-scale training datasets, yet the community lacks systematic benchmarks for evaluating such curation strategies.
arXiv:2601. 07965v2 Announce Type: replace Abstract: When a model knows when it does not know, many possibilities emerge.
AMLworld-Compact introduces an importance‑weighted downsampling protocol for evaluating large language models on AMLworld’s test splits, retaining all illicit transactions while sampling benign ones from supervised‑score strata. The HT‑Coreset method reduces evaluation targets by 271× on HI‑Small and 611× on LI‑Small, providing unbiased confusion‑count estimates with exact recall and ratio estimates for precision and F1. Experiments with boosted‑tree strata and Graph Feature Preprocessor features show lower F1 RMSE compared to uniform sampling, and audit tools reveal that lexical checks do not reliably indicate correctness of model outputs.
arXiv:2607. 20465v1 Announce Type: new Abstract: The quality of training data fundamentally determines the capabilities of large language models (LLMs), yet no unified benchmark exists to measure how well LLMs, agents, and data-centric workflows actually prepare training data end to end.
arXiv:2609.37169v1 Announce Type: cross Abstract: Mid-training equips pretrained large language models with specialized and reasoning capabilities, but the returns of this stage are bounded since add...
INCONVENIENT is a new benchmark that evaluates how machine‑learning models, especially large language models, generalize when trained on convenience samples that bias feature–target relationships. Unlike prior distribution‑shift tests that rely on natural domain splits, INCONVENIENT explicitly perturbs these relationships while keeping the deployment population unchanged, allowing controlled study of shift severity and direction. The benchmark covers 200 tabular classification and regression datasets and produces about 15,500 shifted training distributions, revealing significant performance degradation.
arXiv:2608.30731v1 Announce Type: cross Abstract: Assessing claim check-worthiness is an essential first step in automated fact-checking pipelines. This work is motivated by a real deployment challen...
arXiv:2602. 14161v2 Announce Type: replace Abstract: Detecting prompt injection, jailbreak attacks, and harmful requests is critical for deploying LLM-based agents safely, yet current evaluation practices in this literature overestimate generalization.
MarkTune is a model‑embedded watermarking framework that improves the trade‑off between generation quality and detectability. By regularizing toward a high‑quality reference distribution, it decouples quality preservation from proximity to the base model and uses the GaussMark detection statistic as a reward during on‑policy fine‑tuning. Empirical results show that MarkTune enhances the quality‑detectability frontier, maintains downstream task performance, and remains robust against text‑editing and open‑weight attacks across diverse datasets.