small language model

A Framework for Pluralistic Value Assessment (MindOrder)

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...

GQLSA: Grouped-Query Latent Sparse Attention: A Hardware-Native Architecture for Efficient and Effective Sequence Modeling

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...

Not All 4-bit Quantizers Are Equal: Deployment-Time Mitigation of PII Leakage in Fine-Tuned Small Language Models (research artifact)

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...

Structured PREreview of "Training Large Language Models for Small-Molecule Design with Synthetic Task Scaling"

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...

Judging the Judges: A Controlled Audit of Bias and Instability in LLM-as-Judge Evaluation

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...

LLM and CQL computable phenotypes for myocarditis adverse event feature and outcome determinations using patient FHIR data: a feasibility study

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.

Fine-tuned and AWQ-quantized checkpoints for "Not All 4-bit Quantizers Are Equal"

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...

PREreview of "Training Large Language Models for Small-Molecule Design with Synthetic Task Scaling"

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,...

Judging the Judges: A Controlled Audit of Bias and Instability in LLM-as-Judge Evaluation

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...

Adapting a small language model for plant protection information in Türkiye

GraphThought: A Pilot Study on Graph-Structured Multi-Hop Reasoning with a Single Free-Tier LLM

Chain-of-thought (CoT) prompting elicits intermediate reasoning steps from large language models (LLMs), but treats reasoning as a strictly linear sequence. Many multi-hop questions instead decompose naturally into a small directed acyclic graph (DAG) of sub-tasks, some of which are mutually independent. We implement G...

Flow-Guided Chemical Language Modeling for Linker Design in Reticular Chemistry

Reticular chemistry has enabled the synthesis of tens of thousands of metal–organic frameworks (MOFs), yet the discovery of new materials still relies largely on intuition-driven linker design and iterative experimentation. As a result, researchers explore only a small fraction of the vast chemical space accessible to...