Official Alimama tech channel, showcasing all of Alimama's technical innovations.
This article introduces ConfuseBench, a benchmark that classifies LLM uncertainty into document‑missing, ability‑limited, and ambiguous types, and presents methods—including retrieval, chain‑of‑thought, and clarification—to detect and actively resolve uncertainty, improving answer quality across diverse tasks.
ROLL is an open‑source reinforcement‑learning framework designed for large language model post‑training that combines multi‑task RL, agentic support, flexible algorithm configuration, elastic resource scheduling, and rich observability, delivering significant accuracy gains across benchmarks while remaining easy to use for researchers, product developers, and infrastructure engineers.
This article presents a large‑scale advertising risk‑control solution that combines deep‑research paradigms, domain‑graph constraints, and large language models to enable explainable, responsible, and high‑precision fraud detection, detailing system architecture, challenges, demo workflow, and future directions.
The article presents the Universal Recommendation Model (URM), a large‑language‑model‑based recall framework that integrates world knowledge and e‑commerce expertise through knowledge injection and prompt‑driven alignment, achieving significant offline recall gains and a 3.1% increase in ad consumption while meeting high‑QPS, low‑latency production constraints.
The campus AI Agent competition showcased how large‑language‑model‑powered agents can reason, deceive, and collaborate in a social deduction game, revealing model performance trends, participant insights, and future directions for multi‑agent AI research.
Distribution‑aware Graph Prompt Tuning (DAGPrompT) tackles the pre‑training/downstream mismatch on heterophilic graphs by jointly applying low‑rank GLoRA adaptation and hop‑specific prompts that recast tasks as link‑prediction, yielding up to 4.79% accuracy gains and an average 2.43% improvement in few‑shot node classification.
The paper introduces an explainable LLM framework (ELLM‑rele) that uses chain‑of‑thought reasoning and a multi‑dimensional knowledge distillation pipeline to compress large‑model relevance judgments into lightweight student models, achieving superior offline relevance scores and online click‑through and conversion improvements in Taobao’s search advertising.
The Ali Mama External Investment & Brand Algorithm Series compiles recent KDD, NAACL, and SIGIR research on ad allocation, pacing, traffic estimation, and creative optimization, offering a comprehensive overview of cutting‑edge techniques that enhance advertising efficiency and brand performance across digital platforms.
PosterMaker leverages a ControlNet‑based TextRenderNet with character‑level visual features and a reward‑driven foreground‑extension detector to generate high‑quality product posters that accurately render Chinese text (over 90% sentence accuracy) while preserving product fidelity, and is already deployed in Alibaba’s AI creative tool.
The article details how Apache Paimon, integrated as an external table format in Alibaba’s Dolphin OLAP engine, achieves millisecond‑level query latency and up to 10k QPS through ORC push‑down, manifest conversion, caching, concurrency, and encoding optimizations, outperforming StarRocks and Hologres.
