The paper introduces FlockMTL, an extension for database management systems that deeply integrates large language models and retrieval‑augmented generation into DuckDB. It provides model‑driven scalar and aggregate functions, cost‑based optimizations like batching and caching, and new SQL DDL abstractions (PROMPT and MODEL) to treat LLMs as first‑class schema objects. These features aim to simplify the development of knowledge‑intensive analytical applications by reducing the effort required to orchestrate heterogeneous data systems and manage LLM context.
By Anas Dorbani, Sunny Yasser, Jimmy Lin, Amine Mhedhbi
arXiv:2609.05760v1 Announce Type: cross
Abstract: We present RAGMark, a modular benchmarking framework for advanced Retrieval-Augmented Generation (RAG) systems targeting small-scale multi-GPU enviro...
By Zlatan Feric, Amir Taherin, Bin Ren, Yanzhi Wang, Jennifer Dy, David Kaeli
arXiv:2609.08307v1 Announce Type: cross
Abstract: Large language models (LLMs) are increasingly used as backends for intelligent web services, but serving them across the edge continuum requires bala...
By Maysam Khatib, Moysis Symeonides, Demetris Trihinas, George Pallis, Marios D. Dikaiakos
text2ql is an open‑source Python framework that enables natural language querying of databases without being limited to SQL, without requiring large language model inference at query time, and with a runtime confidence score for each generated query. It uses a language‑agnostic Intermediate Representation (QueryIR) and a pluggable renderer that supports both SQL and GraphQL through a single seven‑stage detection pipeline. In deterministic mode, it achieves 100% execution accuracy with a median latency of 3.2 ms, while the LLM‑backed mode reaches 62‑70% exact match and 84‑91% execution accuracy on benchmark samples.
text2ql is an open‑source Python framework that enables natural language querying of databases without relying on large language models at query time. It uses a language‑agnostic intermediate representation (QueryIR) and a pluggable renderer to support both SQL and GraphQL targets through a single seven‑stage detection pipeline. In deterministic mode, it achieves 100% execution accuracy with a median latency of 3.2 ms, while the LLM‑backed mode delivers 62‑70% exact match and 84‑91% execution accuracy on benchmark samples.
By Ritesh Kumar
Parameter-efficient fine-tuning (PEFT) and low-bit quantization are now standard tools for adapting language models under tight compute budgets, yet their interaction is most often studied on billion-parameter models where the design space is expensive to explore. We ask a complementary question: on a specific, fully reproducible 60M-parameter encoder-decoder model (T5-small) and a single-table text-to-SQL benchmark (WikiSQL), how much task accuracy does each efficiency knob actually cost?
arXiv:2602. 10387v2 Announce Type: replace-cross Abstract: Traditional query optimization relies on cost-based optimizers that estimate execution cost (e.
By Mehmet Hamza Erol, Xiangpeng Hao, Federico Bianchi, Ciro Greco, Jacopo Tagliabue, James Zou
arXiv:2608. 15602v1 Announce Type: cross Abstract: While binary quantization theoretically promises extreme compression and acceleration for Large Language Models (LLMs), existing research often overlooks the necessity of specialized hardware kernels, thus failing to unleash the full acceleration potential due to persistent reliance on expensive floating-point arithmetic or runtime dequantization overheads.
By Qingyao Yang, Runming Yang, He Xiao, Wendong Xu, Junyu Chen, Haobo Liu, Chenchen Ding, Ruihan Hu, Yik-Chung Wu, Ngai Wong
PerfReasoning is a new benchmark that tests large language models (LLMs) on their ability to reason about hardware performance and generate analytical performance‑model code. The benchmark presents workloads, architectures, and mapping specifications, asking models to compare mappings and predict off‑chip traffic and buffer requirements. While the best closed‑source models achieve over 90% accuracy on reasoning‑based Q&A and the top open‑weight model scores 82.4%, constructing full performance models remains difficult, with most models scoring below 15% and significant variability across runs. Task‑specific reinforcement learning can improve a 4B model’s mapping‑reasoning accuracy by 15.7 points, but feedback‑free self‑revision prompting is not reliably effective.
By Dan Zhao, Karthikeyan Sankaralingam, Christos Kozyrakis, Qijing Huang
We’re releasing gpt-oss-120b and gpt-oss-20b—two state-of-the-art open-weight language models that deliver strong real-world performance at low cost. Available under the flexible Apache 2.
arXiv:2608. 13076v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved remarkable success in natural language understanding and generation, but their deployment is constrained by high computational demands.
By Divya Jyoti Bajpai, Kishan Kumar Upadhyay, Manjesh Kumar Hanawal
arXiv:2607. 23815v1 Announce Type: cross Abstract: Large language models are increasingly used as semantic operators for filtering, extracting, ranking, joining, and transforming unstructured data.
By Hojae Son, Md Ashraful Islam, Huy Gia Cao, Hui Guan, Marco Serafini