Skip to content

Category

small language model

3,629 papers

#small language model Open access Sep 2026

AGENTRUN: Failure-Driven QLoRA Specialization for Multi-Tool Agent Behavior in a 7B Language Model

Parameter-efficient fine-tuning is widely assumed to improve small open-weight models on the specific behaviors it targets. We present a controlled case study that complicates this assumption for multi-tool agent execution. Using Qwen2.5-7B-Instruct and a fixed 23-task, machine-checkable benchmark, we show that an init...

Alyssa L · 0 citations
#small language model Book Open access Sep 2026

The Buyer's Chair

What a buyer abroad already believes before a seller says anything A buyer three time zones away decides about a supplier before the supplier has said anything, on evidence the supplier did not know was being read. A small manufacturer trying to sell abroad believes the problem is reach, and puts its effort into approa...

Alya Iskandar · 0 citations
#small language model Open access Sep 2026

From zero-shot to fine-tuning: optimize large language models for error detection of ultrasound reports

It is demonstrated that task-specific fine-tuning enables open-source LLMs to rival proprietary LLMs and expert radiologists in Chinese ultrasound report error detection, offering a locally deployable and privacy-preserving, and regulation-compliant solution for enhancing reporting consistency and reducing diagnostic e...

Min Lai, Jin Zhang, Ya-Er Lv et al. · 0 citations
#small language model Open access Sep 2026

TDLT_YasudaK_PI_Ab_Initio_Transcendence

TDLT_YasudaK π Ab Initio Transcendence What is presented here constitutes only a small sample of several years of independent research. This work does not ask the reader to accept The Dark Light Theory (TDLT) through persuasion. TDLT is proposed as a continuous dependency architecture, in which later structures are int...

SILVIO KOZO YASUDA · 0 citations
#edge computing Open access Sep 2026

TOPO-2026 Validation Framework: A Dual-Approach Evaluation Suite for Certified Vision-Language Models

TOPO-2026 Validation Framework: Complete Summary Document Overview Title: TOPO-2026 Validation Framework: A Dual-Approach Evaluation Suite for Certified Vision-Language Models Author: Frank Morales Aguilera, BEng, MEng, SMIEEE Affiliation: Sovereign Machine Laboratory (SOMALA), Montreal, Canada Date: August 2026 Core P...

Frank Morales · 0 citations
#small language model Book Open access Sep 2026

The Buyer's Chair

What a buyer abroad already believes before a seller says anything A buyer three time zones away decides about a supplier before the supplier has said anything, on evidence the supplier did not know was being read. A small manufacturer trying to sell abroad believes the problem is reach, and puts its effort into approa...

Alya Iskandar · 0 citations
#small language model Open access Sep 2026

Aromatic Heterocycle Ligands for Perovskite Photovoltaics: Balancing Defect Passivation and Heterostructure Formation.

Inverted perovskite solar cells (PSCs) possess great potential for improving efficiency and operating stability, but parasitic charge recombination at the interfaces still limits their performance. As additives and surface treatment agents, ammonium ligands have been reported to form either two/three-dimensional (2D/3D...

Yu-Lan Huang, Mu-Chen Li, Qing-Bin Cai et al. · 0 citations
#small language model Open access Sep 2026

AGENTRUN: Failure-Driven QLoRA Specialization for Multi-Tool Agent Behavior in a 7B Language Model

Parameter-efficient fine-tuning is widely assumed to improve small open-weight models on the specific behaviors it targets. We present a controlled case study that complicates this assumption for multi-tool agent execution. Using Qwen2.5-7B-Instruct and a fixed 23-task, machine-checkable benchmark, we show that an init...

Alyssa L · 0 citations
#small language model Open access Sep 2026

Tokenization Disparity in Kazakh: Cross-Tokenizer Measurement and Low-Cost Vocabulary Adaptation for Large Language Models

Large language models are billed by the token, and tokens are not distributed evenly across languages. We measure how many tokens ten widely deployed tokenizers require to encode identical content in Kazakh and English, using 900 sentence-aligned pairs from OPUS-100 with bootstrap confidence intervals over 10,000 resam...

Alikhan Akim, Zhibek Sarsen · 0 citations

FIT-SLM-HC: A Task–Technology Fit Framework for Identifying Tasks Suited to Small Language Models in Healthcare (Preprint)

BACKGROUND Small Language Models (SLMs) running on local hardware can reduce the privacy, latency, and cost concerns associated with cloud-based Large Language Models (LLMs) in healthcare, but deciding when to use them is typically informal and unsystematic in current practice. The problem is compounded by model turnov...

Hants Williams · 0 citations
#large language models Open access Sep 2026

Tokenization Disparity in Kazakh: Cross-Tokenizer Measurement and Low-Cost Vocabulary Adaptation for Large Language Models

Large language models are billed by the token, and tokens are not distributed evenly across languages. We measure how many tokens ten widely deployed tokenizers require to encode identical content in Kazakh and English, using 900 sentence-aligned pairs from OPUS-100 with bootstrap confidence intervals over 10,000 resam...

Alikhan Akim, Zhibek Sarsen · 0 citations
#large language models Open access Sep 2026

Replications for RealAIGC

RealAIGC: Towards More Realistic Evaluation of AI-Generated Code Detection in Real-World Code Repository Artifact Update (Camera Ready) In response to the latest feedback, we have substantially enhanced our replication materials in terms of dataset coverage, usability, and methodological transparency. RealAIGC++ Datase...

Chen Wentao, Chen Yufei · 0 citations

From tech blogs

See all →

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.