LLM

Imagine a reporting product that connects to both PostgreSQL and SQL Server. A user asks for orders over 100 yuan, sorted by ID in descending order, with the first 10 rows returned. The system needs to produce two SQL statements. Turning this request into two code snippets is easy for an LLM. Making the feature maintainable, and making failures explainable, takes more work. The first decision is simple: which parts belong to the model, and which conversion rules belong in deterministic code where they can be written down and tested. ...

VenueAAAI 2026 TitleAn LLM-based Quantitative Framework for Evaluating High-Stealthy Backdoor Risks in OSS Supply Chains AuthorsZihe Yan, Kai Luo, et al. (SJTU / Tsinghua / Tencent Xuanwu Lab) PaperarXiv:2511.13341 DOI10.1609/aaai.v40i2.37116 Codegithub.com/XuanwuLab/HSBRiskEvaluator ForReaders working on supply chain security, Linux distribution dependency governance, or red-team target selection SummaryThe paper breaks a high-stealth backdoor campaign into four stages from an attacker's perspective, then scores repositories with APT dependency data, GitHub community activity, and LLM-assisted semantic analysis. It evaluates 66 high-priority Debian packages with public GitHub repositories and uses xz as a case study. ...