This dataset comprises synthetic news descriptions in French, generated from real newspaper headlines using a controlled Small Language Models (SLM) pipeline. The generation process follows three distinct configurations: Retrieval-Augmented Generation (RAG) and generation without external context (NO RAG) and QLoRA-bas...
Ayman Abdellaoui, Jose Manuel García-Campos· Zenodo (CERN European Organi...· 0 citations
This registration is retrospective. It records a systematic appraisal that was completed between 24 September and 1 November 2026. The protocol, the search strategy and the eligibility criteria were finalised in writing before data extraction began; the appraisal itself, however, was finished before this registration w...
An object detector for small smart cameras and mobile robots must fit within the resources of an onboard computer that it shares with other tasks. On a Raspberry Pi 5 with a budget of two inference threads, we study how the frame rate, latency, accuracy and heating of the YOLO11n detector are affected by the following...
Alla N. Lavrenyuk, Олександр Вікторович Коломієць, Sergii Lavreniuk· Kyiv Academic University· 0 citations
Linear probes are increasingly read as evidence that language models represent whether they are being evaluated. Content-matched designs, which hold a task fixed and switch one cue at a time, are meant to make that evidence strong. The assumption is that a probe separating the two versions has detected the model recogn...
Karan Singh· Zenodo (CERN European Organi...· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This preprint develops an end-to-end causal account of how information acquires behavioral control in language models. Across a coordinated series of mechanistic studies, we trace the computation from distributed relational and typed representations, through task- and recipient-dependent qualification, contextual multi...
This Zenodo record is a permanently preserved version of a PREreview. You can view the complete PREreview at https://prereview.org/reviews/23177620. ## Summary Routing papers usually optimize proxy costs — parameter counts, API prices, model counts. This one measures the thing itself: per-query GPU energy. The authors...
Karmendra Pandey· Zenodo (CERN European Organi...· 0 citations
Auto-regressive sequence generation in modern transformer language models is severely memory-bandwidth bound, yielding low arithmetic intensity on resource-constrained edge devices. While speculative decoding mitigates this bottleneck by utilizing a compact draft model to propose candidates verified concurrently by a t...
Benedict Baah· Zenodo (CERN European Organi...· 0 citations
This dataset accompanies the study “Correcting or Confirming? A Pilot Study of LLM Responses to Simulated Student Pressure in Higher Education”. The workbook documents 60 conversations and 120 model responses collected from ChatGPT, Gemini, and Claude. The protocol comprises ten English-language academic scenarios, two...
Georgios Roussos, Georgios Alexandridis· Zenodo (CERN European Organi...· 0 citations
Background Chinese large language models (LLMs) are increasingly used for HIV/AIDS health information, yet their multidimensional performance remains unevaluated. This study systematically assessed five mainstream Chinese LLMs across accuracy, caring, completeness, understandability, and actionability. Methods A cross-...
Jinhao Gu, Jianwei Liu, Yunrong Liu et al.· Frontiers in Public Health· 0 citations
When it comes to understanding the human mind and behaviour, theory is often generated from and tested via samples that are not representative of the population as a whole. Over twenty years ago, this problem was brought into sharp focus with a number of authors calling for research in the cognitive and psychological s...
Kenny R. Coventry· Frontiers in Psychology· 0 citations
Misinformation embedded in humor on social media can be difficult to detect and mitigate. This study investigates the effectiveness of traditional machine learning (ML) models, pre-trained neural language models, and large language models (LLMs) in identifying humor-laden misinformation related to COVID-19 vaccines o...
Emily McKinley, Si-Jia Qian, M. E. Rasul et al.· Scientific Reports· 0 citations
