Skip to content

Category

small language model

343 papers

#machine learning Preprint Aug 2026

Semantic Overlays: Mitigating Prompt Injection with Annotations Beyond Tokens and Steering Vectors

This work introduces a general steering technique called Semantic Overlays: small learned adapters applied at chosen prefill positions to a frozen model's residual stream that defends against the broad class of prompt injections that add instructions in untrusted context.

Joshua Penman · 0 citations
#small language model Preprint Aug 2026

Mixture of Channel Experts: Static Sparse Supports with Input-Adaptive Mixing for Pointwise Projections

This work introduces Mixture of Channel Experts (MoCE), a structured sparse channel-mixing layer, inspired by MoE, that replaces pointwise (1x1) channel-reduction projections and matches or exceeds dense baselines and prior channel-selection methods while reducing MACs by 16.7% and end-to-end latency.

Elian Iluk, Gil Ben-Artzi · 0 citations
#small language model Preprint Aug 2026

MARS: Multi-Specialist LLM Relay System for Competitive Programming

This work presents MARS (Multi-Agent Relay of Specialized LLMs), a prompt-only framework in which each agent is a topic specialist---dynamic programming, graphs, strings, geometry, and so on---grounded by retrieval-augmented generation over an algorithm-theory corpus.

Andrei Mikhailov, M. Burtsev, Alsu Sagirova · 0 citations
#small language model Preprint Aug 2026

Towards LLM-Enhanced Android Taint Analysis

Whether off-the-shelf Large Language Models (LLMs) can effectively reason about taint flows in Android apps is investigated, and preliminary findings suggest that LLM reasoning may effectively complement traditional static taint analysis.

Nicholas Miazzo, Marco Alecci, Jordan Samhi et al. · 0 citations
#small language model Preprint Aug 2026

'Ghaib in Translation'aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with'Missed-in-Urdu'Scores in LLM Hate Speech Detection

Results indicate that current LLMs provide uneven safety assurance across Urdu's script varieties, with smaller open-weight models showing substantially higher instability and missed-harm rates than frontier closed models.

F. Kara-Isitt, Sonal Khosla, S. Swift · 0 citations
#small language model Preprint Aug 2026

Constraint-Guided Enterprise Data Mapping with Large Language Models

Constrained-guided mapping is proposed, a neuro-symbolic method with three stages: schema-grounded admissibility constraints with metadata mc =, where tau_c denotes the constraint type and delta_c provides executable relation and normalization logic, and constraint-restricted candidate generation with cascade relaxation to guarantee a nonempty feasible set under noise.

Sebastian Monka, Pramod Anantharam, Thị Minh et al. · 0 citations
#small language model Review Open access Sep 2026

Automating cost-effectiveness models with agentic artificial intelligence: Case study and implications for value assessment.

Findings support a hybrid paradigm in which AI augments, but does not replace, health economists in value assessment and formulary decision support within managed care settings.

R. Mudumba, A. Modi, Kevin Mayo · 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.