Related papers: Parsing TTree Formula in Python

Automating the formalization of mathematical statements for theorem proving remains a major challenge for Large Language Models (LLMs). LLMs struggle to identify and utilize the prerequisite mathematical knowledge and its corresponding…

TextFormats is a software system for efficient and user-friendly creation of text format specifications, accessible from multiple programming languages (C/C++, Python, Nim) and the Unix command line. To work with a format, a specification…

Technology-assisted review (TAR) is an important industrial application of information retrieval (IR) and machine learning (ML). While a small TAR research community exists, the complexity of TAR software and workflows is a major barrier to…

We encode arrays as functions which, in turn, are encoded as sets of ordered pairs. The set cardinality of each of these functions coincides with the length of the array it is representing. Then we define a fragment of set theory that is…

Initially developed for natural language processing (NLP), Transformers are now widely used for source code processing, due to the format similarity between source code and text. In contrast to natural language, source code is strictly…

Nested relations, built up from atomic types via product and set types, form a rich data model. Over the last decades the nested relational calculus, NRC, has emerged as a standard language for defining transformations on nested…

The addition of syntax-aware decoding in Neural Machine Translation (NMT) systems requires an effective tree-structured neural network, a syntax-aware attention model and a language generation model that is sensitive to sentence structure.…

Recent works such as VisProg and ViperGPT have smartly composed foundation models for visual reasoning-using large language models (LLMs) to produce programs that can be executed by pre-trained vision-language models. However, they operate…

Extended Berkeley Packet Filter (BPF) is a language and run-time system that allows non-superusers to extend the Linux and Windows operating systems by downloading user code into the kernel. To ensure that user code is safe to run in kernel…

In this paper, we study how to improve the zero-shot reasoning ability of large language models~(LLMs) over structured data in a unified way. Inspired by the study on tool augmentation for LLMs, we develop an \emph{Iterative…

Software developers often repeat code changes, known as "code change patterns" (CPATs), within and across projects. Automating these CPATs accelerates development, but current Transformation by Example (TBE) techniques are limited by the…

The ROOT TTree data format encodes hundreds of petabytes of High Energy and Nuclear Physics events. Its columnar layout drives rapid analyses, as only those parts ("branches") that are really used in a given analysis need to be read from…

Natural language is one of the most intuitive ways to express human intent. However, translating instructions and commands towards robotic motion generation and deployment in the real world is far from being an easy task. The challenge of…

Large language models (LLMs) exhibit in-context learning abilities which enable the same model to perform several tasks without any task-specific training. In contrast, traditional adaptation approaches, such as fine-tuning, modify the…

While Large Language Models (LLMs) have demonstrated significant potential in natural language processing , complex general-purpose reasoning requiring multi-step logic, planning, and verification remains a critical bottleneck. Although…

Formal verification of a software system relies on formalising the requirements to which it should adhere, which can be challenging. While formalising requirements from natural-language, we have dependencies that lead to duplication of…

Throughput and latency critical applications could often benefit of performing computations close to the client. To enable this, distributed computing paradigms such as edge computing have recently emerged. However, with the advent of…

We study machine learning formulations of inductive program synthesis; that is, given input-output examples, synthesize source code that maps inputs to corresponding outputs. Our key contribution is TerpreT, a domain-specific language for…

We propose a new, training-free method, Graph Reasoning via Retrieval Augmented Framework (GRRAF), that harnesses retrieval-augmented generation (RAG) alongside the code-generation capabilities of large language models (LLMs) to address a…

Automatic Program Repair (APR) is a core technology in software development and maintenance, with aims to enable automated defect repair with minimal human intervention. In recent years, the substantial advancements in Large Language Models…