arXiv subjects

Frederick Reiss

Publications and source records attributed to Frederick Reiss.

3 recordsLinked to original sources

arXiv2025

A Library of LLM Intrinsics for Retrieval-Augmented Generation

In the developer community for large language models (LLMs), there is not yet a clean pattern analogous to a software library, to support very large scale collaboration. Even for the commonplace use case of Retrieval-Augmented Generation (RAG), it is not currently possible to write a RAG application against a well-defined set of APIs that are agreed upon by different LLM providers. Inspired by the idea of compiler intrinsics, we propose some elements of such a concept through introducing a library of LLM Intrinsics for RAG. An LLM intrinsic is defined as a capability that can be invoked through a well-defined API that is reasonably stable and independent of how the LLM intrinsic itself is implemented. The intrinsics in our library are released as LoRA adapters on HuggingFace, and through a software interface with clear structured input/output characteristics on top of vLLM as an inference platform, accompanied in both places with documentation and code. This article describes the intended usage, training details, and evaluations for each intrinsic, as well as compositions of multiple intrinsics.

cs.AI↗

arXiv2021

CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks

Over the last several decades, software has been woven into the fabric of every aspect of our society. As software development surges and code infrastructure of enterprise applications ages, it is now more critical than ever to increase software development productivity and modernize legacy applications. Advances in deep learning and machine learning algorithms have enabled numerous breakthroughs, motivating researchers to leverage AI techniques to improve software development efficiency. Thus, the fast-emerging research area of AI for Code has garnered new interest and gathered momentum. In this paper, we present a large-scale dataset CodeNet, consisting of over 14 million code samples and about 500 million lines of code in 55 different programming languages, which is aimed at teaching AI to code. In addition to its large scale, CodeNet has a rich set of high-quality annotations to benchmark and help accelerate research in AI techniques for a variety of critical coding tasks, including code similarity and classification, code translation between a large variety of programming languages, and code performance (runtime and memory) improvement techniques. Additionally, CodeNet provides sample input and output test sets for 98.5% of the code samples, which can be used as an oracle for determining code correctness and potentially guide reinforcement learning for code quality improvements. As a usability feature, we provide several pre-processing tools in CodeNet to transform source code into representations that can be readily used as inputs into machine learning models. Results of code classification and code similarity experiments using the CodeNet dataset are provided as a reference. We hope that the scale, diversity and rich, high-quality annotations of CodeNet will offer unprecedented research opportunities at the intersection of AI and Software Engineering.

cs.SE↗

arXiv2006

Impliance: A Next Generation Information Management Appliance

ably successful in building a large market and adapting to the changes of the last three decades, its impact on the broader market of information management is surprisingly limited. If we were to design an information management system from scratch, based upon today's requirements and hardware capabilities, would it look anything like today's database systems?" In this paper, we introduce Impliance, a next-generation information management system consisting of hardware and software components integrated to form an easy-to-administer appliance that can store, retrieve, and analyze all types of structured, semi-structured, and unstructured information. We first summarize the trends that will shape information management for the foreseeable future. Those trends imply three major requirements for Impliance: (1) to be able to store, manage, and uniformly query all data, not just structured records; (2) to be able to scale out as the volume of this data grows; and (3) to be simple and robust in operation. We then describe four key ideas that are uniquely combined in Impliance to address these requirements, namely the ideas of: (a) integrating software and off-the-shelf hardware into a generic information appliance; (b) automatically discovering, organizing, and managing all data - unstructured as well as structured - in a uniform way; (c) achieving scale-out by exploiting simple, massive parallel processing, and (d) virtualizing compute and storage resources to unify, simplify, and streamline the management of Impliance. Impliance is an ambitious, long-term effort to define simpler, more robust, and more scalable information systems for tomorrow's enterprises.

cs.DB↗