Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation

International AI Safety Report 2026

Bielik-Q2-Sharp: A Comparative Study of Extreme 2-bit Quantization Methods for a Polish 11B Language Model

From Scale to Speed: Adaptive Test-Time Scaling for Image Editing

Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?

The Prompt Report: A Systematic Survey of Prompt Engineering Techniques

Reporting LLM Prompting in Automated Software Engineering: A Guideline Based on Current Practices and Expectations

A Survey of Automatic Prompt Engineering: An Optimization Perspective

Which Prompting Technique Should I Use? An Empirical Investigation of Prompting Techniques for Software Engineering Tasks

AI Alignment Strategies from a Risk Perspective: Independent Safety Mechanisms or Shared Failures?