AI Wiki — Knowledge Base

Zero-Shot Multi-Disease Labeling of Chest, Abdomen, and Pelvis CT Reports Using Open-Weight Large Language Models: The Effect of Labeling Conventions

arXiv:2506.03259v3 Announce Type: replace Abstract: Purpose: To compare five lightweight open-weight large language models (LLMs) with a rule-based algorithm (RBA) and fine-tuned RadBERT for zero-shot

model-releasesarxiv-cs-cl

7 Aug 2026

Search: “open-weights”

The Devil in the Details: Emergent Misalignment, Format and Coherence in Open-Weights LLMs

Secure On-Premise Deployment of Open-Weights Large Language Models in Radiology: An Isolation-First Architecture with Prospective Pilot Evaluation

Behavioral Reprogramming of Open-Weights Models: Cognitive Plasticity and Alignment Bounds

Replicating the Geometry of Emotion Representations in a Base Open-Weights Model

Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks

Linguistic Triggers of Gender and Racial Bias in Open-Weight LLMs Applied to Recruitment

Crypto Accounting Bench: Evaluating Frontier and Open-Weight Models on Crypto-Asset Accounting Tasks

Can Open-Weight Models Compete on Financial Text Comprehension?

A governance horizon for ethical-use constraints in open-weight AI models

Jailbreaking Open-Weight LLMs via Random Embedding Perturbations

The Fragility of Trigger-Tag Mechanisms for Misuse Detection in Open-Weight LLMs

Comparison of techniques for fine-tuning open-weight models for entity extraction from radiology reports

Position: Current Model Cards Are Insufficient for Downstream Governance of Open-Weight Foundation Models

Fool's Gold: Defensive Deception Against Safety-Removal Attacks on Open-Weight Models

Zero-Shot Multi-Disease Labeling of Chest, Abdomen, and Pelvis CT Reports Using Open-Weight Large Language Models: The Effect of Labeling Conventions

Selecting Open-Weight Language Models for Zero-Shot Intent Classification: A Systematic Evaluation of 41 Models

HEBATRON: A Hebrew-Specialized Open-Weight Mixture-of-Experts Language Model

AgentFloor: How Far Up the tool use Ladder Can Small Open-Weight Models Go?

Beyond User-Side Defenses: Image Protection in Open-Weight Diffusion Models

Removing Information Content Does Not Certify Tamper Resistance in Open-Weight Models

You Cannot Pick a Provider From the Price List: Market-Aware Routing for Open-Weight LLM Inference

Misaligned Clinical Risk Classification and Cost Asymmetry in Open-Weight Large Language Models

AquiLLM: Evaluating Faithfulness in Open-Weight RAG-LLM Systems for Scientific Research

Nameless Tokenization: A Lossless Tokenizer-Level Defense Against Control-Token Forgery in Open-Weight LLMs

Uncensored Open-weight Models: Redistribution as the Persistence Layer

Role-Specialized Mixture-of-Agents with Open-Weight LLMs for Clinical Prediction

Open-Weight Masked Introspection: Measuring What Language Models Can Report About Their Own Computation

Kozuchi Agent: A Language-Agnostic Open-Weight Agent for Software Repair

Distribution-Specific Curvature Control with Finite-Sample Guarantees for Open-Weight Safety

Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data preparation tasks

Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware Analysis

Revisiting Vul-RAG: Reproducibility and Replicability of RAG-based Vulnerability Detection with Open-Weight Models

Unpredictable Safety: Domain-Dependent Compliance and the Transparency Gap in Open-Weight LLMs

Verbal Confidence Saturation in 3-9B Open-Weight Instruction-Tuned LLMs: A Pre-Registered Psychometric Validity Screen

Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Models

Network-based Spatial Context Retrieval for Open-weight LLMs: A Faithfulness Benchmark for Grounded Geographic Reasoning

Evaluating Open-Weight LLMs for Turkish Domain Documents Under Retrieval and Hardware Constraints

Adapting Open-Weight MLLMs to Generate Point Prompts for Electron Microscopy Segmentation

GeoNatureAgent Benchmark: Benchmarking LLM Agents for Environmental Geospatial Analysis Across Frontier and Open-Weight Foundation Models

LLM-Only PDDL Domain Repair with Open-Weight Models

Behavior and Representation in Open-Weight Large Language Models for Combinatorial Optimization: From Feature Extraction to Algorithm Selection

Graph Feedback Controls Consensus and Clique Formation in Open-Weight Language-Model Populations

Large Databases Need Small, Open-Weight Language Models

Hallucination Detection via Activations of Open-Weight Proxy Analyzers

Quad-State Safety Evaluation of Open-Weight Large Language Models on Non-Canonical Inputs

Identical Runs, Different Results: Benchmarking AI Coding Agents on Open-Weight Models

Benchmarking the Explanatory Quality of Open-Weight Vision-Language Models in Face Recognition

Evaluating Open-Weight E-Commerce Agents with Environment-Grounded Verification