Tootfinder

I am using MS Word’s web version for work and either the grammar checker has become a lot worse or just a lot more aggressive.
It keeps suggesting things that are not just wrong, but incomprehensible.
…
Fuck, they put an LLM in it, didn’t they?

Assessing an evolutionary search engine for small language models, prompts, and evaluation metrics
Cl\'audio L\'ucio do Val Lopes, Lucca Machado
https://arxiv.org/abs/2506.21512

Assessing an evolutionary search engine for small language models, prompts, and evaluation metrics
The concurrent optimization of language models and instructional prompts presents a significant challenge for deploying efficient and effective AI systems, particularly when balancing performance against computational costs like token usage. This paper introduces and assesses a bi-objective evolutionary search engine designed to navigate this complex space, focusing specifically on Small Language Models (SLMs). We employ the NSGA-II algorithm and prompt grammar to simultaneously optimize for ta…

Orchestration of Music by Grammar Systems
Jozef Maki\v{s} (Faculty of Information Technology, Brno University of Technology), Alexander Meduna (Faculty of Information Technology, Brno University of Technology), Zbyn\v{e}k K\v{r}ivka (Faculty of Information Technology, Brno University of Technology)
https://arxiv.org/abs/2507.153…

Orchestration of Music by Grammar Systems
This application-oriented study concerns computational musicology, which makes use of grammar systems. We define multi-generative rule-synchronized scattered-context grammar systems (without erasing rules) and demonstrates how to simultaneously make the arrangement of a musical composition for performance by a whole orchestra, consisting of several instruments. Primarily, an orchestration like this is illustrated by examples in terms of classical music. In addition, the orchestration of jazz co…

Efficient design of rna sequences with desired properties, structure, and motifs using a grammar variational autoencoder
Narges Zarnaghinaghsh, Byung-Jun Yoon
https://arxiv.org/abs/2507.15912

Efficient design of rna sequences with desired properties, structure, and motifs using a grammar variational autoencoder
Designing structurally stable RNA sequences with specific motifs and other desirable properties is an important challenge in bioinformatics. The potential design space increases exponentially with the length of the RNA to be engineered, which makes this a difficult combinatorial optimization problem. In this paper, we propose an RNA grammar variational autoencoder (RGVAE) that can efficiently generate novel RNA sequences with specific target properties. The proposed RGVAE builds on the recently…

PSPACE-completeness of Grammar logics of bounded density
Olivier Gasquet
https://arxiv.org/abs/2507.14956 https://arxiv.org/pdf/2507.…

PSPACE-completeness of Grammar logics of bounded density
We introduce the family of multi-modal logics of bounded density and with a tableau-like approach using finite \emph{windows} which were introduced in \cite{BalGasq25}, we prove that their satisfiability problem is PSPACE-complete. As a side effect, the monomodal logic of density is shown to be in para-PSPACE.

English is hard.
https://www.instagram.com/reel/DJXBn1kuetC/?igsh=NTJvbHNsaG45eWcy

Ashley Ottesen on Instagram: "Yay grammar rules #dadjoke #comedy #skit"
24K likes, 281 comments - ashleyottesen_ on May 7, 2025: "Yay grammar rules #dadjoke #comedy #skit".

LZSE: an LZ-style compressor supporting $O(\log n)$-time random access
Hiroki Shibata, Yuto Nakashima, Yutaro Yamaguchi, Shunsuke Inenaga
https://arxiv.org/abs/2506.20107

LZSE: an LZ-style compressor supporting $O(\log n)$-time random access
An LZ-like factorization of a string is a factorization in which each factor is either a single character or a copy of a substring that occurs earlier in the string. While grammar-based compression schemes support efficient random access with linear space in the size of the compressed representation, such methods are not known for general LZ-like factorizations. This has led to the development of restricted LZ-like schemes such as LZ-End [Kreft and Navarro, 2013] and height-bounded (LZHB) [Bann…

Read it in Two Steps: Translating Extremely Low-Resource Languages with Code-Augmented Grammar Books
Chen Zhang, Jiuheng Lin, Xiao Liu, Zekai Zhang, Yansong Feng
https://arxiv.org/abs/2506.01796

Read it in Two Steps: Translating Extremely Low-Resource Languages with Code-Augmented Grammar Books
While large language models (LLMs) have shown promise in translating extremely low-resource languages using resources like dictionaries, the effectiveness of grammar books remains debated. This paper investigates the role of grammar books in translating extremely low-resource languages by decomposing it into two key steps: grammar rule retrieval and application. To facilitate the study, we introduce ZhuangRules, a modularized dataset of grammar rules and their corresponding test sentences. Our …

WGRAMMAR: Leverage Prior Knowledge to Accelerate Structured Decoding
Ran Wang, Xiaoxuan Liu, Hao Ren, Gang Chen, Fanchao Qi, Maosong Sun
https://arxiv.org/abs/2507.16768

WGRAMMAR: Leverage Prior Knowledge to Accelerate Structured Decoding
Structured decoding enables large language models (LLMs) to generate outputs in formats required by downstream systems, such as HTML or JSON. However, existing methods suffer from efficiency bottlenecks due to grammar compilation, state tracking, and mask creation. We observe that many real-world tasks embed strong prior knowledge about output structure. Leveraging this, we propose a decomposition of constraints into static and dynamic components -- precompiling static structures offline and in…

Google's grammar checker does not speak Gay. I guess the AI never got laid.

AnnoGram: An Annotative Grammar of Graphics Extension
Md Dilshadur Rahman, Md Rahat-uz- Zaman, Andrew McNutt, Paul Rosen
https://arxiv.org/abs/2507.04236 h…

AnnoGram: An Annotative Grammar of Graphics Extension
Annotations are central to effective data communication, yet most visualization tools treat them as secondary constructs -- manually defined, difficult to reuse, and loosely coupled to the underlying visualization grammar. We propose a declarative extension to Wilkinson's Grammar of Graphics that reifies annotations as first-class design elements, enabling structured specification of annotation targets, types, and positioning strategies. To demonstrate the utility of our approach, we develop a …

Inferring Attributed Grammars from Parser Implementations
Andreas Pointner, Josef Pichler, Herbert Pr\"ahofer
https://arxiv.org/abs/2507.13117 https:/…

Inferring Attributed Grammars from Parser Implementations
Software systems that process structured inputs often lack complete and up-to-date specifications, which specify the input syntax and the semantics of input processing. While grammar mining techniques have focused on recovering syntactic structures, the semantics of input processing remains largely unexplored. In this work, we introduce a novel approach for inferring attributed grammars from parser implementations. Given an input grammar, our technique dynamically analyzes the implementation of…

{nplyr} has helper functions to work on nested dataframes: #rstats #datascience

You know, “this” used to be a perfectly innocent word. Nothing special, but a solid citizen of the grammar ecosystem. Who could have predicted it would turn into a major clickbait villain, meaning “We’re not going to tell you what this article is about until you click on it.”
FWIW I think I’m not alone in consciously avoiding clicking on such links.
#enshittification

This https://arxiv.org/abs/2001.09029 has been replaced.
link: https://scholar.google.com/scholar?q=a

Rewriting Structured Cospans
To support the study of compositional networks, we further develop the formalism of structured cospans. To enable rewriting, we introduce a category whose objects are structured cospans and characterize conditions under which this category is a topos or is adhesive. We then define a structured cospan grammar and language, using a 2-category framework. As an application, we demonstrate that for various sorts of graphs, hypergraphs, and Petri nets, any grammar induces the same language as its cor…

This https://arxiv.org/abs/2505.16978 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

HyGenar: An LLM-Driven Hybrid Genetic Algorithm for Few-Shot Grammar Generation
Grammar plays a critical role in natural language processing and text/code generation by enabling the definition of syntax, the creation of parsers, and guiding structured outputs. Although large language models (LLMs) demonstrate impressive capabilities across domains, their ability to infer and generate grammars has not yet been thoroughly explored. In this paper, we aim to study and improve the ability of LLMs for few-shot grammar generation, where grammars are inferred from sets of a small …

(De)composing Craft: An Elementary Grammar for Sharing Expertise in Craft Workflows
Ritik Batra, Lydia Kim, Ilan Mandel, Amritansh Kwatra, Jane L. E., Steven J. Jackson, Thijs Roumen
https://arxiv.org/abs/2506.10891

(De)composing Craft: An Elementary Grammar for Sharing Expertise in Craft Workflows
Craft practices rely on evolving archives of skill and knowledge, developed through generations of craftspeople experimenting with designs, materials, and techniques. Better documentation of these practices enables the sharing of knowledge and expertise between sites and generations. However, most documentation focuses solely on the linear steps leading to final artifacts, neglecting the tacit knowledge necessary to improvise, or adapt workflows to meet the unique demands of each craft project.…

Quantifying Azure RBAC Wildcard Overreach
Christophe Parisel
https://arxiv.org/abs/2506.10755 https://arxiv.org/pdf/2506.10755…

Quantifying Azure RBAC Wildcard Overreach
Azure RBAC leverages wildcard permissions to simplify policy authoring, but this abstraction often obscures the actual set of allowed operations and undermines least-privilege guarantees. We introduce Belshazaar, a two-stage framework that targets both the effective permission set problem and the evaluation of wildcards permissions spread. First, we formalize Azure action syntax via a context free grammar and implement a compiler that expands any wildcard into its explicit action set. Second, w…

Speak2Sign3D: A Multi-modal Pipeline for English Speech to American Sign Language Animation
Kazi Mahathir Rahman, Naveed Imtiaz Nafis, Md. Farhan Sadik, Mohammad Al Rafi, Mehedi Hasan Shahed
https://arxiv.org/abs/2507.06530

Speak2Sign3D: A Multi-modal Pipeline for English Speech to American Sign Language Animation
Helping deaf and hard-of-hearing people communicate more easily is the main goal of Automatic Sign Language Translation. Although most past research has focused on turning sign language into text, doing the reverse, turning spoken English into sign language animations, has been largely overlooked. That's because it involves multiple steps, such as understanding speech, translating it into sign-friendly grammar, and generating natural human motion. In this work, we introduce a complete pipeline …

Just finished watching series 1 and 2 of #Taskmaster.
Series 2 is definitely when they realized contestants completing the tasks not by the spirit of the instructions, but instead by the letter of the instructions IS the show.
Contestants finding loopholes, using alternate word definitions, challenging grammar, etc. makes the show more than simply who can complete the task the …

Advanced LPeg techniques: A dual case study approach
Zixuan Zhu
https://arxiv.org/abs/2507.01272 https://arxiv.org/pdf/2507.01272

Advanced LPeg techniques: A dual case study approach
This paper presents advanced optimization techniques for Lua Parsing Expression Grammars (LPeg) through two complementary case studies: a high-performance JSON parser and a sophisticated Glob-to-LPeg pattern converter. We demonstrate how strategic grammar construction can dramatically improve parsing performance without modifying the underlying LPeg library. For the JSON parser, we implement substitution capture and table construction optimization to reduce memory allocation overhead and improv…

This https://arxiv.org/abs/2502.12089 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

How Compositional Generalization and Creativity Improve as Diffusion Models are Trained
Natural data is often organized as a hierarchical composition of features. How many samples do generative models need in order to learn the composition rules, so as to produce a combinatorially large number of novel data? What signal in the data is exploited to learn those rules? We investigate these questions in the context of diffusion models both theoretically and empirically. Theoretically, we consider a simple probabilistic context-free grammar - a tree-like graphical model used to represe…

GenFair: Systematic Test Generation for Fairness Fault Detection in Large Language Models
Madhusudan Srinivasan, Jubril Abdel
https://arxiv.org/abs/2506.03024

GenFair: Systematic Test Generation for Fairness Fault Detection in Large Language Models
Large Language Models (LLMs) are increasingly deployed in critical domains, yet they often exhibit biases inherited from training data, leading to fairness concerns. This work focuses on the problem of effectively detecting fairness violations, especially intersectional biases that are often missed by existing template-based and grammar-based testing methods. Previous approaches, such as CheckList and ASTRAEA, provide structured or grammar-driven test generation but struggle with low test diver…

Concerning the Responsible Use of AI in the US Criminal Justice System
Cristopher Moore, Catherine Gill, Nadya Bliss, Kevin Butler, Stephanie Forrest, Daniel Lopresti, Mary Lou Maher, Helena Mentis, Shashi Shekhar, Amanda Stent, Matthew Turk
https://arxiv.org/abs/2506.00212

Concerning the Responsible Use of AI in the US Criminal Justice System
Artificial intelligence (AI) is increasingly being adopted in most industries, and for applications such as note taking and checking grammar, there is typically not a cause for concern. However, when constitutional rights are involved, as in the justice system, transparency is paramount. While AI can assist in areas such as risk assessment and forensic evidence generation, its "black box" nature raises significant questions about how decisions are made and whether they can be contested. This pa…

Engineering Fast and Space-Efficient Recompression from SLP-Compressed Text
Ankith Reddy Adudodla, Dominik Kempa
https://arxiv.org/abs/2506.12011 https://

Engineering Fast and Space-Efficient Recompression from SLP-Compressed Text
Compressed indexing enables powerful queries over massive and repetitive textual datasets using space proportional to the compressed input. While theoretical advances have led to highly efficient index structures, their practical construction remains a bottleneck (especially for complex components like recompression RLSLP), a grammar-based representation crucial for building powerful text indexes that support widely used suffix array queries. In this work, we present the first implementation …

It has taken me way too many years to figure out, but:
I have just realised that a core feature of a shell language is that it has very little grammar.
In other words, the language needs to be maximally permissive, so that you can layer whatever you need on top.
Take, for example, switches. They work because as far as sh/bash/etc. is concerned, starting a string with a hyphen is absolutely reasonable.
Numbers are integers, when you need them to be. Or they’re strings.…

SheetMind: An End-to-End LLM-Powered Multi-Agent Framework for Spreadsheet Automation
Ruiyan Zhu, Xi Cheng, Ke Liu, Brian Zhu, Daniel Jin, Neeraj Parihar, Zhoutian Xu, Oliver Gao
https://arxiv.org/abs/2506.12339

SheetMind: An End-to-End LLM-Powered Multi-Agent Framework for Spreadsheet Automation
We present SheetMind, a modular multi-agent framework powered by large language models (LLMs) for spreadsheet automation via natural language instructions. The system comprises three specialized agents: a Manager Agent that decomposes complex user instructions into subtasks; an Action Agent that translates these into structured commands using a Backus Naur Form (BNF) grammar; and a Reflection Agent that validates alignment between generated actions and the user's original intent. Integrated int…

Refining Czech GEC: Insights from a Multi-Experiment Approach
Petr Pechman, Milan Straka, Jana Strakov\'a, Jakub N\'aplava
https://arxiv.org/abs/2506.22402

Refining Czech GEC: Insights from a Multi-Experiment Approach
We present a grammar error correction (GEC) system that achieves state of the art for the Czech language. Our system is based on a neural network translation approach with the Transformer architecture, and its key feature is its real-time synthetic generation pipeline, which dynamically augments sentences with artificial errors by introducing both language-agnostic and Czech-specific errors. We conduct a comprehensive series of experiments, investigating the Czech GEC corpora as bases for synth…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new/
[2/5]:
Structuring Concept Space with the Musical Circle of Fifths by Utilizing Music Grammar Based Acti...

BMFM-DNA: A SNP-aware DNA foundation model to capture variant effects
Hongyang Li, Sanjoy Dey, Bum Chul Kwon, Michael Danziger, Michal Rosen-Tzvi, Jianying Hu, James Kozloski, Ching-Huei Tsou, Bharath Dandala, Pablo Meyer
https://arxiv.org/abs/2507.05265

BMFM-DNA: A SNP-aware DNA foundation model to capture variant effects
Large language models (LLMs) trained on text demonstrated remarkable results on natural language processing (NLP) tasks. These models have been adapted to decipher the language of DNA, where sequences of nucleotides act as "words" that encode genomic functions. However, the genome differs fundamentally from natural language, as it lacks clearly defined words or a consistent grammar. Although DNA language models (DNALMs) such as DNABERT, GENA-LM have achieved high level of performance on genome-…

AI's Euclid's Elements Moment: From Language Models to Computable Thought
Xinmin Fang, Lingfeng Tao, Zhengxiong Li
https://arxiv.org/abs/2506.23080

AI's Euclid's Elements Moment: From Language Models to Computable Thought
This paper presents a comprehensive five-stage evolutionary framework for understanding the development of artificial intelligence, arguing that its trajectory mirrors the historical progression of human cognitive technologies. We posit that AI is advancing through distinct epochs, each defined by a revolutionary shift in its capacity for representation and reasoning, analogous to the inventions of cuneiform, the alphabet, grammar and logic, mathematical calculus, and formal logical systems. Th…