Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2510.25183v2 Announce Type: replace-cross Abstract: Energy-efficient AI should be evaluated across the full application pipeline, not only by lowest error or shortest training time. We study th...
arXiv:2511.09801v3 Announce Type: replace-cross Abstract: This work extends the recently introduced Alpha-Procrustes family of Riemannian metrics for symmetric positive definite (SPD) matrices by inc...
arXiv:2605.13214v3 Announce Type: replace-cross Abstract: Recent cryptographic results establish that neural networks can be backdoored such that no efficient algorithm can distinguish them from a cl...
arXiv:2609.09554v1 Announce Type: new Abstract: We introduce BuzzASR, a collection of language-specialized fine-tuned Whisper models adapted for automatic speech recognition (ASR) in 102 languages. L...
arXiv:2609.09999v1 Announce Type: new Abstract: Terminology-aware translation asks for more than a correct translation: the output must use the exact terms a glossary prescribes. The standard recipe,...
arXiv:2609.10153v1 Announce Type: new Abstract: Arabic morphology remains challenging for large language models, since fluent generation does not guarantee accurate morphosyntactic control. Existing...
arXiv:2609.10266v1 Announce Type: new Abstract: LLM serving systems already reuse KV caches, but only when the reused text sits at the very start of the prompt. Two growing workloads break this condi...
arXiv:2609.10293v1 Announce Type: new Abstract: In high-stakes domains such as legal practice, a language-model answer is only useful to the extent that a reader can verify each claim against the sou...
arXiv:2609.10445v1 Announce Type: new Abstract: Reasoning language models have made substantial advances on a variety of complex tasks, yet their capabilities remain overwhelmingly English-centric: m...
arXiv:2609.10494v1 Announce Type: new Abstract: Enterprises deploy systems, not checkpoints. Usable capability depends jointly on weights, serving route, precision, output contract, and harness, yet...
arXiv:2609.09372v1 Announce Type: cross Abstract: Although MMLU is widely adopted as a benchmark for calibrating general AI capabilities, we psychometrically demonstrate that its aggregate score prim...
arXiv:2609.09735v1 Announce Type: cross Abstract: Healthcare systems, mental health, and public well-being are increasingly affected by cyberbullying and harmful online interactions. This paper prese...
arXiv:2607.00890v2 Announce Type: replace Abstract: Open web-scale pre-training corpora remain concentrated in English, limiting multilingual LLM development. We introduce MultiSynt/MT, an open synth...
arXiv:2605.16023v3 Announce Type: replace Abstract: LLM-as-a-judge has become the dominant paradigm for grading model outputs at scale, yet the same model assigns systematically different scores when...
arXiv:2605.29791v2 Announce Type: replace Abstract: While Large Language Models (LLMs) can convincingly simulate personas in explicit self-reports, they often deviate in implicit behavioral decisions...
arXiv:2606.03027v2 Announce Type: replace Abstract: Text embeddings are fundamental to many downstream applications, making robustness important for real-world NLP. However, most recent state-of-the-...
arXiv:2606.13945v2 Announce Type: replace Abstract: Rare diseases affect over $300$ million patients across more than $7{,}000$ conditions, yet no single hospital encounters enough cases of any one c...
arXiv:2604.23036v2 Announce Type: replace-cross Abstract: Despite MoE models leading many benchmarks, supervised fine-tuning (SFT) for the MoE architectures remains difficult because its router layer...
arXiv:2609.09417v1 Announce Type: new Abstract: Vision-language models (VLMs) show promise for agricultural classification, but zero-shot performance on disease, pest, damage, quality, and species id...
arXiv:2609.09394v1 Announce Type: new Abstract: Recovering metric 3D geometry from monocular images is a fundamental computer vision task, yet current methods remain heavily fragmented by fixed camer...