Tootfinder

AIMSCheck: Leveraging LLMs for AI-Assisted Review of Modern Slavery Statements Across Jurisdictions
Adriana Eufrosina Bora, Akshatha Arodi, Duoyi Zhang, Jordan Bannister, Mirko Bronzi, Arsene Fansi Tchango, Md Abul Bashar, Richi Nayak, Kerrie Mengersen
https://arxiv.org/abs/2506.01671

AIMSCheck: Leveraging LLMs for AI-Assisted Review of Modern Slavery Statements Across Jurisdictions
Modern Slavery Acts mandate that corporations disclose their efforts to combat modern slavery, aiming to enhance transparency and strengthen practices for its eradication. However, verifying these statements remains challenging due to their complex, diversified language and the sheer number of statements that must be reviewed. The development of NLP tools to assist in this task is also difficult due to a scarcity of annotated data. Furthermore, as modern slavery transparency legislation has bee…

This https://arxiv.org/abs/2503.19449 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

VecTrans: Enhancing Compiler Auto-Vectorization through LLM-Assisted Code Transformations
Auto-vectorization is a fundamental optimization for modern compilers to exploit SIMD parallelism. However, state-of-the-art approaches still struggle to handle intricate code patterns, often requiring manual hints or domain-specific expertise. Large language models (LLMs), with their ability to capture intricate patterns, provide a promising solution, yet their effective application in compiler optimizations remains an open challenge due to issues such as hallucinations and a lack of domain-sp…

A Functional Data Model and Query Language is All You Need
Jens Dittrich
https://arxiv.org/abs/2507.20671 https://arxiv.org/pdf/2507.20671

A Functional Data Model and Query Language is All You Need
We propose the vision of a functional data model (FDM) and an associated functional query language (FQL). Our proposal has far-reaching consequences: we show a path to come up with a modern QL that solves (almost if not) all problems of SQL (NULL-values, impedance mismatch, SQL injection, missing querying capabilities for updates, etc.). FDM and FQL are much more expressive than the relational model and SQL. In addition, in contrast to SQL, FQL integrates smoothly into existing programming lang…

This https://arxiv.org/abs/2503.19449 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

VecTrans: Enhancing Compiler Auto-Vectorization through LLM-Assisted Code Transformations
Auto-vectorization is a fundamental optimization for modern compilers to exploit SIMD parallelism. However, state-of-the-art approaches still struggle to handle intricate code patterns, often requiring manual hints or domain-specific expertise. Large language models (LLMs), with their ability to capture intricate patterns, provide a promising solution, yet their effective application in compiler optimizations remains an open challenge due to issues such as hallucinations and a lack of domain-sp…

The longest increasing subsequence of Brownian separable permutons
Arka Adhikari, Jacopo Borga, Thomas Budzinski, William Da Silva, Delphin S\'enizergues
https://arxiv.org/abs/2506.19123

The longest increasing subsequence of Brownian separable permutons
We establish a scaling limit result for the length $\operatorname{LIS}(σ_n)$ of the longest increasing subsequence of a permutation $σ_n$ of size $n$ sampled from the Brownian separable permuton $\boldsymbolμ_p$ of parameter $p\in(0,1)$, which is the universal limit of pattern-avoiding permutations. Specifically, we prove that \[\frac{\operatorname{LIS}(σ_n)}{n^α}\;\underset{n\to\infty}{\overset{\mathrm{a.s.}}{\longrightarrow}}\; X,\] where $α=α(p)$ is the unique solution in the interval…

"We think of generating source code from a prompt as an AI-powered feature of modern IDEs, but the general problem has a rich history in research efforts and domain-specific programming systems." Join William Benton at this year's Berlin Buzzwords to hear him talk about the history of program synthesis, its relationship to the history of AI, and the lessons we can learn from it today.
Learn more:

Agent0: Leveraging LLM Agents to Discover Multi-value Features from Text for Enhanced Recommendations
Bla\v{z} \v{S}krlj, Beno\^it Guilleminot, Andra\v{z} Tori
https://arxiv.org/abs/2507.18993

Agent0: Leveraging LLM Agents to Discover Multi-value Features from Text for Enhanced Recommendations
Large language models (LLMs) and their associated agent-based frameworks have significantly advanced automated information extraction, a critical component of modern recommender systems. While these multitask frameworks are widely used in code generation, their application in data-centric research is still largely untapped. This paper presents Agent0, an LLM-driven, agent-based system designed to automate information extraction and feature construction from raw, unstructured text. Categorical f…

Let's Measure the Elephant in the Room: Facilitating Personalized Automated Analysis of Privacy Policies at Scale
Rui Zhao, Vladyslav Melnychuk, Jun Zhao, Jesse Wright, Nigel Shadbolt
https://arxiv.org/abs/2507.14214

Let's Measure the Elephant in the Room: Facilitating Personalized Automated Analysis of Privacy Policies at Scale
In modern times, people have numerous online accounts, but they rarely read the Terms of Service or Privacy Policy of those sites despite claiming otherwise. This paper introduces PoliAnalyzer, a neuro-symbolic system that assists users with personalized privacy policy analysis. PoliAnalyzer uses Natural Language Processing (NLP) to extract formal representations of data usage practices from policy texts. In favor of deterministic, logical inference is applied to compare user preferences with t…

Context-Aware CodeLLM Eviction for AI-assisted Coding
Kishanthan Thangarajah, Boyuan Chen, Shi Chang, Ahmed E. Hassan
https://arxiv.org/abs/2506.18796 http…

Context-Aware CodeLLM Eviction for AI-assisted Coding
AI-assisted coding tools powered by Code Large Language Models (CodeLLMs) are increasingly integrated into modern software development workflows. To address concerns around privacy, latency, and model customization, many enterprises opt to self-host these models. However, the diversity and growing number of CodeLLMs, coupled with limited accelerator memory, introduce practical challenges in model management and serving efficiency. This paper presents CACE, a novel context-aware model eviction s…

SimdBench: Benchmarking Large Language Models for SIMD-Intrinsic Code Generation
Yibo He, Shuoran Zhao, Jiaming Huang, Yingjie Fu, Hao Yu, Cunjian Huang, Tao Xie
https://arxiv.org/abs/2507.15224

SimdBench: Benchmarking Large Language Models for SIMD-Intrinsic Code Generation
SIMD (Single Instruction Multiple Data) instructions and their compiler intrinsics are widely supported by modern processors to accelerate performance-critical tasks. SIMD intrinsic programming, a trade-off between coding productivity and high performance, is widely used in the development of mainstream performance-critical libraries and daily computing tasks. Large Language Models (LLMs), which have demonstrated strong and comprehensive capabilities in code generation, show promise in assistin…