Educational data filters have become a practical way to improve language-model pre-training, but most filters treat educational value as a single scalar property. This may be too broad for some applications, especially if the data set already features a high density of educational material. Useful learning material nee...
Oliver G. B. Garrod, Robin A. A. Ince, Meng Liu et al.· 0 citations
Retrieval-augmented generation (RAG) grounds a language model in retrieved documents, which reduces hallucination but creates a new attack surface: if retrieved text is tampered with, the model may repeat the falsehood. We study how much a small quantized model, Llama 3.1 8B, degrades when a fraction of its retrieved c...
Research Attention Prediction (RAP), a rolling benchmark covering 278 AI/ML fields and 1,390 episodes, is introduced, a rolling benchmark covering 278 AI/ML fields and 1,390 episodes for large language models to track shifts in research attention.
Ying-Qian Wu, Jingcong Liang, Si-Yuan Wang et al.· 0 citations
Retrieval-Augmented Generation (RAG) combines information retrieval with language generation to improve the grounding of generated answers in a source document, addressing a central weakness of purely parametric large language models: the tendency to produce fluent but unsupported statements. This study designs, implem...
Dileep Choudhary· Zenodo (CERN European Organi...· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
We present a computational framework for multi‑dimensional value assessment, designed to address a structural problem shared by historical evaluation and AI value alignment: how to adjudicate among incommensurable values without collapsing them into a single score. Mainstream approaches to value aggregation seek a corr...
Wei Wan· Zenodo (CERN European Organi...· 0 citations
We introduce Grouped-Query Latent Sparse Attention (GQLSA), a novel attention mechanism that integrates latent compression, grouped-query sharing, and block-sparse attention into a unified hardware-native architecture. GQLSA achieves linear O(T) complexity in sequence length, a 3.8x speedup over multi-head attention at...
Fardin Sabid· Zenodo (CERN European Organi...· 0 citations
Research artifact of the paper Not All 4-bit Quantizers Are Equal: Deployment-Time Mitigation of PII Leakage in Fine-Tuned Small Language Models, published at SBSeg 2026 Main Track (full paper). Artifact evaluation (CTA/SBSeg 2026): this artifact was awarded all four seals: Available Artifacts (SeloD), Functional Artif...
Cristhian Kapelinski, Diego Kreutz· Zenodo (CERN European Organi...· 0 citations
This Zenodo record is a permanently preserved version of a Structured PREreview. You can view the complete PREreview at https://prereview.org/reviews/22662419. Does the introduction explain the objective of the research presented in the preprint? Yes The introduction explains the objective by setting up a gap and then...
Sneh Pankajbhai Vora· Zenodo (CERN European Organi...· 0 citations
Large language models are now routinely asked to grade other large language models, a delegation of judgment that has become the default way organizations track progress on open-ended generation tasks where no single reference answer exists. The convenience of this arrangement is undeniable, but it does not remove the...
Shashwat Pandey· Journal of Information Syste...· 0 citations
Struct and unstructured FHIR data provided the computable phenotypes using an LLM with sufficient clinical information for myocarditis feature identification and outcome determination and enhanced CQL had excellent feature identification performance across most domains.
Fraser W. Gaspar, Seth Roberts, Francis Campion et al.· Frontiers in Digital Health· 0 citations
Model checkpoints used by the artifact's second claim: the fine-tuned Qwen 0.5B checkpoint (wave 1, seed 42) and its AWQ 4-bit quantization. With these, a reviewer replays the claim instead of retraining. Data component of the research artifact of the paper Not All 4-bit Quantizers Are Equal: Deployment-Time Mitigation...
Cristhian Kapelinski, Diego Kreutz· Zenodo (CERN European Organi...· 0 citations
This Zenodo record is a permanently preserved version of a PREreview. You can view the complete PREreview at https://prereview.org/reviews/22662611. Review of "Training Large Language Models for Small-Molecule Design with Synthetic Task Scaling" Summary This preprint asks whether LLMs can be post-trained for expensive,...
Sneh Pankajbhai Vora· Zenodo (CERN European Organi...· 0 citations
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Microsoft Research Blog· microsoft.comOct 15, 2026
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
