Large language models are increasingly used to solve educational physics problems, but their accuracy remains inconsistent. This study investigates whether prompt formulation can improve the performance of language models on school-level physics problems in Russian and English. In total 21 language models were tested o...
Sergei Mironichev, Igor Obolensky· Zenodo (CERN European Organi...· 0 citations
Detecting text synthesized by frontier large language models (LLMs) remains a critical requirement for academic integrity, digital forensics, and media authenticity. Existing zero-shot detectors exhibit severe real-world failure modes: token-curvature methods (DetectGPT, Fast-DetectGPT) require inaccessible white-box m...
Debdip Bandyopadhyay· Zenodo (CERN European Organi...· 0 citations
The serving of autoregressive Large Language Models (LLMs) is severely constrained by the computational and memory capacity limits of the Key-Value (KV) cache, commonly referred to as the Memory Wall. While dynamic context pruning algorithms mitigate memory expansion by discarding tokens of low attention mass, conventi...
A. Emre Cetin· Zenodo (CERN European Organi...· 0 citations
The Steered Contextual AI Framework for Orchestrating Learning Dialogue (SCAFFOLD), a layered reliability architecture that surrounds LLM-generated text and speech with external verification, targeted repair, and safe fallback, while preserving data privacy, is proposed.
Olga Muss, L. M. Leisten, Charles Edouard Bardyn· Scientific Reports· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Although individual studies have examined the capabilities of generative AI in annotation, coding, item construction, thematic analysis, and data simulation, there has so far been no cross-paradigm framework that systematically integrates technical performance, methodological validity, institutional embedding, and the...
Giovanni Vindigni· American Journal of Multidis...· 0 citations
Modern multi-agent architectures predominantly treat autonomous agents driven by Large Language Models (LLMs) as unmanaged application-level loops interacting through stateless, unbounded prompts. In long-running computing environments, this abstraction mismatch induces severe system-level pathologies, including nondet...
Hai Nguyen· Zenodo (CERN European Organi...· 0 citations
Sign language's importance comes from its vital role in improving the lifestyle of deaf and hearing-impaired people.Despite the importance of Arabic Sign Language (ArSL) in playing this vital role in the Arab world, ArSL recognition researches are still limited.This limitation is largely due to the lack of high-quality...
Hadeer A. Esam-Eldin, Mostafa Elgendy, Eman K. Elsayed· International journal of int...· 0 citations
Large language models offer unprecedented analytical capability, but their knowledge is frozen at the last training
date — rendering them unusable for organizations whose mission depends on emerging, timely information [1]. This paper
argues that retrieval-augmented generation is the missing mechanism that converts LLM...
Sohail Sayed, Nauman Sayed· International Journal of Inn...· 0 citations
Whether stigmatizing input language biases large language model (LLM) triage prioritization against acutely ill patients is unknown. In a controlled, outcome-grounded experiment at two academic emergency departments, Emergency Severity Index-matched pairs (one deteriorating within 6 h, one not) were evaluated by three...
Philip Jarrett, Peter Yun, Emmanuel Ohuabunwa et al.· npj Digital Medicine· 0 citations
This artifact accompanies the paper “Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache,” accepted at the 2027 IEEE Symposium on Security and Privacy.
Ye Yu, Yifan Zhou, Yi Chen et al.· Zenodo (CERN European Organi...· 0 citations
Abstract Large language models write code fluently, yet the programs they produce carry defect rates that ordinary functional evaluation seldom exposes, and detection systems that could catch these faults act too late to shape the generation that created them. This paper argues that generation and detection should be o...
Large language model (LLM) agents are typically optimized to achieve given objectives, but real-world objectives are often incomplete, ambiguous, or misaligned with underlying needs. This paper proposes a structured architecture for meta-objective reframing—the process of critically examining and reorganizing objective...
Masanao Ishikawa· Zenodo (CERN European Organi...· 0 citations
StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduOct 8, 2026
