small language model

Toward scalable generative AI: efficient language model distillation via zero-shot rationales

Results indicate that near-optimal performance can be achieved even when rationales are provided for only a subset of the training data, and that shorter explanations are often sufficient.

Digital Language Laboratories in Indian Secondary Education: Effectiveness, Pedagogical Integration, Implementation Challenges and Policy Alignment

Digital language laboratories have re-emerged in Indian school-education discussions as networked environments for listening, speaking, pronunciation, multimedia practice, formative feedback and digitally mediated interaction. Their educational value, however, cannot be inferred from the presence of computers, headsets...

Don’t Look up: Evaluating the Tradeoff Between Performance and Sustainability of Text Classification Using Open LLMs

The increasing adoption of Large Language Models (LLMs) as a text analysis method in social science presents a critical yet under-examined trade-off between model performance and environmental sustainability. This research provides a systematic evaluation comparing the performance, energy consumption, processing time...

Conservative Proxy Prompting for Reliable Frozen Vision–Language Models with Missing Modalities

Editorial: Advances in neurocritical care

Neurocritical care focuses on patients with actual or impending organ dysfunction that arises from, or accompanies, primary or secondary neurological injury and necessitates intensive care (1). As a subspecialty, neurocritical care continues to face unresolved and controversial questions in both clinical practice and r...

Leakage-Aware Cross-Dataset Evaluation of Prompt Injection Detection Using Classical Machine Learning and Transformer Models

A leak-aware cross-dataset evaluation framework is presented to examine the robustness of classical machine learning and Transformer-based prompt injection detection models in the face of data source changes, and shows that internal validation results are not enough for prompt injection detection.

HIPPOGRID evidence pack for the preliminary results (2026)

HIPPOGRID — evidence pack for the preliminary results (2026) Raw result files and figures behind the preliminary results cited in the MSCA-PF proposal HIPPOGRID (SEP-211387371, call HORIZON-MSCA-2026-PF-01). Researcher: Álvaro González-Redondo (University of Granada). Each bundle below backs one claim of the proposal;...

A Conflict Is Constructed Before It Is Measured: Seven Design Choices That Set Which Way a Language Model Bends, and Why the Context-Memory Results Do Not Compare

(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. The literature on how language models behave when retrieved context contradicts parametric memory contains a flat contradiction, and neither of its two surveys resolves it. One body of results reports over-reliance on memorised information; another reports that mod...

Modelometry: Classification of Flagship AI Model Families Based on Inter-Model Stylometry

Working paper and open data. Studies that measure the output of more than one AI language model consistently find that the models write differently, in the same manner that human authors have different writing styles. We coin the term **modelometry** for the measurement and attribution of the inter-model writing style...

HIPPOGRID evidence pack for the preliminary results (2026)

HIPPOGRID — evidence pack for the preliminary results (2026) Raw result files and figures behind the preliminary results cited in the MSCA-PF proposal HIPPOGRID (SEP-211387371, call HORIZON-MSCA-2026-PF-01). Researcher: Álvaro González-Redondo (University of Granada). Each bundle below backs one claim of the proposal;...

Modelometry: Classification of Flagship AI Model Families Based on Inter-Model Stylometry

Working paper and open data. Studies that measure the output of more than one AI language model consistently find that the models write differently, in the same manner that human authors have different writing styles. We coin the term **modelometry** for the measurement and attribution of the inter-model writing style...

A Conflict Is Constructed Before It Is Measured: Seven Design Choices That Set Which Way a Language Model Bends, and Why the Context-Memory Results Do Not Compare

(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. The literature on how language models behave when retrieved context contradicts parametric memory contains a flat contradiction, and neither of its two surveys resolves it. One body of results reports over-reliance on memorised information; another reports that mod...