small language model

Can Generative Large Language Models Serve as Raters for Test Development? A Systematic Evaluation Across Tasks, Models, and Inference Configurations

Overall, the findings suggest that LLMs can function as effective supplementary raters in test development and validation processes, although greater caution is warranted for certain rating tasks.

Morphological Hijacking in Frozen Language Models: A Contrastive, Symmetry-Regularized Projection Head for Algebraic Structure Recovery

Preprint. Not yet peer-reviewed. Abstract: Frozen autoregressive language models cluster surface-similar tokens together even when a stronger, task-relevant structure is available in the input. We construct an adversarial lexicon (LUXVAR Core-30) in which word meaning is defined by orbit membership under the finite alg...

Developing a Word Square Student Worksheet on Animal Classification to Foster the Conceptual Understanding of Grade X Students

The Word Square Student Worksheet on animal classification is suitable as an alternative teaching material in Biology, since it creates active and enjoyable learning, helps students recall scientific terms, and fosters conceptual understanding of animal classification.

Cognitive and Neural Preservation in Older Language Learners: The CNPOLL Framework

Hanna Pitkin's Wittgenstein

Hannah Pitkin’s Wittgenstein and Justice stimulated new approaches within social science. She did this not so much by offering a normative political reading of his philosophy, as some critics charge, but by drawing out the capacity for critique in his self-described ‘new style of thinking’. It is this critical style th...

Content-Addressed Recursive State: Resolving the DenseRetrieval Trade-o with a Cubic-Composition Readout

Recurrent architectures that compress history into a single state are cheap but have classically been unable to exactly retrieve far past key–value bindings, whereas attention content-addresses the whole past at quadratic cost. We show that the conflict between dense language modeling and long-range associative recall...

Epistemic Inventory and Taxonomy of Claims

Here we present four companion documents for the program corpus listed below. The Taxonomy of Claims lists the theory's claims and assigns each one a status. The claims are grouped in four tiers: Framework (the laws and constants, which the theory does not derive), Derived from Framework (quantities computed from the f...

Knowledge and utilization of family planning and safe abortion services among married women of reproductive age in the Raute community of Nepal: A census-based cross-sectional study

Abstract Indigenous and nomadic communities worldwide face disproportionate and persistent barriers to reproductive health services, including family planning and safe abortion. The Raute of Nepal — one of the country’s last nomadic hunter-gatherer groups represent a uniquely marginalized population for whom no prior p...

Multi-Access Speculative Inference: Uplink or Downlink?

A sum-token-goodput maximization problem that jointly accounts for mode selection, draft-length control, and power allocation is formulated, and a simple optimal structure is revealed that enables efficient search over the number of UL devices, with the corresponding transmit powers optimized accordingly.

HSMLog: Small Language Model-Assisted Hardware Security Module Log Anomaly Detection with Behavioral Analysis

HSMLog, a two-stage framework for HSM log anomaly detection with retrieval-grounded behavioral analysis, is presented, demonstrating effective anomaly alerting and incident triage in the studied setting.

Test-time Reinforcement Learning in Imperfect Information Games

This work extends the concept of gadget game, tabular technique for test-time search, to the reinforcement learning setting and formally proves that, unlike prior tabular algorithms, regularized policy-gradient algorithms limit possible strategy degradation caused by test-time reasoning, even without the gadget games.

VisLens: Single-Pass Interpretable Visual Search for Multimodal LLMs

VisLens (Visual Focus via Logit Lens), a Visual Search method built on the logit lens, which decodes the semantics held in a hidden state by projecting it through the LLM head, and which matches or exceeds prior baselines while delivering a substantial latency advantage.