Skip to content

Category

small language model

442 papers

#small language model Open access Aug 2026

Retrieval Granularity as Evidence Design in Small-Model RAG Question Answering: A Diagnostic HotpotQA Study

Results align with a diagnostic perspective on chunking: using evidence at a task-appropriate level of granularity can improve grounding, auditability, and answer quality, but the observed patterns should be interpreted within the HotpotQA distractor setting, fixed generator, and tested context budgets.

Weimao Ke, Lixia Yang, Mengyang Xu · 0 citations
#small language model Review Open access Aug 2026

FroLineR: Front-Line Response with Retrieval-Augmented Prompt-Engineered Reply Generation for IT Help Desks

IT help desks at large organizations face a high volume of recurrent, well-documented user requests that nevertheless require human-written replies, creating a persistent staff workload that is repetitive in content but non-trivial in tone and procedural correctness. We present FroLineR, short for Front-Line Response, a system that drafts the initial staff reply to such tickets in the login and account-activation category and integrates into a human-in-the-loop ticketing workflow on a Romanian-language ticketing platform. The generator is an unmodified instruct model augmented with retrieval from a small set of hand-curated guide documents, using a Romanian system prompt refined over several rounds of staff review. To evaluate and refine the prompt without manual labeling, we cluster the first user message of every historical thread with both BERTopic and Semantic Signal Separation (S3), score configurations along coherence and lexical-diversity axes, and extract a 200-message evaluation set from the winning model. Prompt convergence was certified by several rounds of manual review by support staff. The production system is quantized to Q4_K_M GGUF, served through llama-cpp-python behind a small Flask API, and deployed with GPU offloading on the target server, reducing end-to-end per-answer latency from approximately 830 s on the server’s CPU to roughly 61 s once layers are offloaded to the GPU, with no observable degradation in answer quality.

Alexandru Dima, Marian Mihailescu, Darius Mihai et al. · 0 citations
#small language model Open access Aug 2026

Interprofessional Education Experience, Self-Rated Knowledge, and Perceived Interprofessional Collaboration Among Health Professions Faculty and Educators: A Cross-Sectional Mixed-Methods Study in Albania and Italy

Self-reported prior IPE experience showed a clearer and more consistent association with perceived collaboration than did the single-item measure of self-rated IPE knowledge, whose association was small and less consistent across domains.

Viktorija Xharra, Rosario Caruso, Florian Spada et al. · 0 citations
#artificial intelligence Review Open access Nov 2026

A comparative review of modern large language model paradigms: GPT-4, BERT, Gemini, and DeepSeek

Comparison of GPT-4, BERT (bidirectional encoder representations from transformers), Gemini, and DeepSeek large language models (LLM), focusing on architectures, training methodologies, and real-world applications reveals GPT-4 excels in natural language generation and complex reasoning, supporting up to 128K tokens with moderate latency and higher costs making it effective for conversational artificial intelligence (AI).

Kavish Sanghvi, Aparna S. Sharma, Surbhi Hooda · 0 citations
#small language model Open access Aug 2026

LifeSciBench: Evaluating Language Models on Realistic, Expert-Level Tasks in the Life Sciences

LifeSciBench is introduced, a benchmark of 750 expert-authored tasks designed to evaluate whether language models can handle realistic life science research work, with each constituent task paired with a human expert-written rubric.

Amelia Liu, Andrew Ho, Anne Marie Droste et al. · 2 citations

An Explicit Interaction-Prompted Diffusion Framework for High-Fidelity 3D Molecular Generation.

Current structure-based drug design generative models often struggle to faithfully recapitulate genuine ligand-protein binding interactions. Instead, under the coupling of implicit learning architectures and biased training data, they tend to learn spurious statistical correlations. To address this, we propose EIP-Diff (Explicit Interaction-Prompted Diffusion), an architecture featuring a novel explicit interaction-prompt embedding mechanism that is better suited for real-world target-specific drug design. This architecture replaces biased implicit learning with explicit, residue-level biological guidance, thereby promoting more fine-grained geometric fidelity and more precise interaction-aware conditioning. To fully realize the capabilities of EIP-Diff and provide a reliable basis for performance evaluation, we further constructed CrystalData set, which provides higher-fidelity and less-biased structural supervision than existing data sets. This explicit architecture markedly improves distribution consistency: even when trained on the crossdocked data set, EIP-Diff achieves the highest alignment with authentic pharmacological distributions among evaluated models. Training on CrystalData set further enhances this alignment and improves 3D geometric accuracy, while retaining strong controllability, high chemical space coverage, and near-perfect uniqueness. In addition, target-based validation on KAT6A and YTHDC1 confirmed that EIP-Diff accurately recapitulates native-like binding modes. Furthermore, in a real-world drug design task against IDO1, we successfully designed a novel lead compound with nanomolar potency (IC50 = 0.31 nM). These results demonstrate that the EIP-Diff architecture can explicitly leverage experimentally derived structural data and biologically meaningful interaction information for target-specific molecular generation, thereby enabling its effective application to real-world structure-based drug design.

Huabin Du, Mingyang Wang, M. Luo et al. · 0 citations
#small language model Open access Aug 2026

A Proof‐of‐Concept Study of Language‐Stratified Assessment for Minimal Hepatic Encephalopathy: Integrating the Animal Naming Test and Serum IL‐6

It is suggested that primary spoken language may be associated with ANT1 performance in MHE assessments and Integrating ANT1 with serum IL-6 showed numerically improved discrimination in Mandarin speakers, whereas exploratory demographic calibration of S-ANT1 showed a numerically higher AUROC in Taiwanese Hokkien speakers.

Hsin-Che Lin, Cheng-Jen Chen, Tsung-Han Wu et al. · 0 citations
#small language model Review Open access Aug 2026

Quality, consistency, and clinical safety of AI-generated versus clinician-written clinical notes: a multi-country paired simulation study

In this simulation, AI-generated notes scored higher on documentation quality, varied less, and carried fewer clinically significant errors than notes written on the same consultations by junior-to-middle-grade clinicians.

H. Bergman, V. Liu, B. Austin et al. · 0 citations
#small language model Review Aug 2026

Brain-computer interface training for motor recovery after stroke.

Overall, the certainty of evidence was low to very low, downgraded primarily for these risk of bias concerns, severe imprecision (due to small sample sizes), and potential publication bias.

Yu Qin, Mei-xuan Li, Yan-fei Li et al. · 0 citations
#natural language process... Book Open access Aug 2026

Caduceus: MoE Foundation Models for Unifying Biological and Natural Language

This paper introduces Caduceus, a family of MoE-enhanced foundation models built with a hierarchical pre-training paradigm to jointly integrate biological and natural language, and incorporates a multi-task instruction tuning phase, enabling robust protein parsing and natural language question answering.

Mingze Yin, Yiheng Zhu, Jialu Wu et al. · 0 citations
#small language model Preprint Aug 2026

Structured Driving-State Narratives for Small Language Model-Based GNSS Spoofing Detection

The presented framework can detect and classify GNSS spoofing attacks in real-time while requiring relatively low computational and memory resources, and is therefore suitable for deployment on resource-constrained vehicular computing platforms.

Abyad Enan, Sagar Dasgupta, Mizanur Rahman et al. · 0 citations

From tech blogs

See all →
Microsoft Research Blog Aug 31, 2026

GigaPath-Flash and GigaTIME-Flash: Toward population-scale discovery with efficient pathology foundation models

What if pathology foundation models could do more with less? GigaPath-Flash and GigaTIME-Flash cut computational demands while maintaining strong performance, opening the door to larger studies and broader exploration. The post GigaPath-Flash and GigaTIME-Flash: Toward population-scale discovery with efficient pathology foundation models appeared first on Microsoft Research.