Tootfinder

Intermediate Languages Matter: Formal Languages and LLMs affect Neurosymbolic Reasoning
Alexander Beiser, David Penz, Nysret Musliu
https://arxiv.org/abs/2509.04083 https://

Intermediate Languages Matter: Formal Languages and LLMs affect Neurosymbolic Reasoning
Large language models (LLMs) achieve astonishing results on a wide range of tasks. However, their formal reasoning ability still lags behind. A promising approach is Neurosymbolic LLM reasoning. It works by using LLMs as translators from natural to formal languages and symbolic solvers for deriving correct results. Still, the contributing factors to the success of Neurosymbolic LLM reasoning remain unclear. This paper demonstrates that one previously overlooked factor is the choice of the forma…

What if I ask in \textit{alia lingua}? Measuring Functional Similarity Across Languages
Debangan Mishra, Arihant Rastogi, Agyeya Negi, Shashwat Goel, Ponnurangam Kumaraguru
https://arxiv.org/abs/2509.04032

What if I ask in \textit{alia lingua}? Measuring Functional Similarity Across Languages
How similar are model outputs across languages? In this work, we study this question using a recently proposed model similarity metric $κ_p$ applied to 20 languages and 47 subjects in GlobalMMLU. Our analysis reveals that a model's responses become increasingly consistent across languages as its size and capability grow. Interestingly, models exhibit greater cross-lingual consistency within themselves than agreement with other models prompted in the same language. These results highlight not o…

unicodelang: Languages spoken by country (2015)
A bipartite network of languages and the countries in which they are spoken, as estimated by Unicode. Edges are weighted by the proportion of the given country's population that is literate in a particular language.
This network has 868 nodes and 1255 edges.
Tags: Informational, Relatedness, Weighted

"The overall life expectancy of a programming language has dwindled in the past 56 years. A COBOL developer in the 1960s most probably retired in the 2000s, still writing COBOL. As a former professional VBScript, then C#, then Objective-C, later Swift, and finally Go developer, I can only see this trend accelerating. We should expect our favorite programming language to be replaced and removed from the market in a relatively shorter time every decade."

Janus-faces of temporal constraint languages: a dichotomy of expressivity
Johanna Brunar, Michael Pinsker, Moritz Sch\"obi
https://arxiv.org/abs/2509.04347 https://

Janus-faces of temporal constraint languages: a dichotomy of expressivity
The Bodirsky-Kára classification of temporal constraint languages stands as one of the earliest and most seminal complexity classifications within infinite-domain Constraint Satisfaction Problems (CSPs), yet it remains one of the most mysterious in terms of algorithms and algebraic invariants for the tractable cases. We show that those temporal languages which do not pp-construct EVERYTHING (and thus by the classification are solvable in polynomial time) have, in fact, very limited expressive …

Internal languages of locally cartesian closed $(\infty,1)$-categories
El Mehdi Cherradi
https://arxiv.org/abs/2509.03371 https://arxiv.org/pdf/2509.03371

Internal languages of locally cartesian closed $(\infty,1)$-categories
We establish a DK-equivalence between the relative category of $π$-tribes and the relative category of locally cartesian closed quasicategories. From this follows one of the internal languages conjecture: Martin-Löf type theory with dependent sums, intensional identity types, and dependent products satisfying functional extensionality is the internal language of locally cartesian closed $(\infty,1)$-categories.

Dredging up recollections of my experience as R6RS editor for my PLSS talk tomorrow.
https://2025.ecoop.org/details/plss-2025-papers/8/Do-Programming-Languages-Fulfill-Requirements-Should-They-

MSPs back new powers supporting Gaelic and Scots https://www.bbc.com/news/articles/clyzll5m2j1o?utm_source=dlvr.it&utm_content=muz4now/magazine/Signs of Hope&utm_medium=masto…

MSPs back new powers supporting Gaelic and Scots
The Scottish Languages Bill would see both recognised as official languages.

Voxlect: A Speech Foundation Model Benchmark for Modeling Dialects and Regional Languages Around the Globe
Tiantian Feng, Kevin Huang, Anfeng Xu, Xuan Shi, Thanathai Lertpetchpun, Jihwan Lee, Yoonjeong Lee, Dani Byrd, Shrikanth Narayanan
https://arxiv.org/abs/2508.01691

Voxlect: A Speech Foundation Model Benchmark for Modeling Dialects and Regional Languages Around the Globe
We present Voxlect, a novel benchmark for modeling dialects and regional languages worldwide using speech foundation models. Specifically, we report comprehensive benchmark evaluations on dialects and regional language varieties in English, Arabic, Mandarin and Cantonese, Tibetan, Indic languages, Thai, Spanish, French, German, Brazilian Portuguese, and Italian. Our study used over 2 million training utterances from 30 publicly available speech corpora that are provided with dialectal informati…

unicodelang: Languages spoken by country (2015)
A bipartite network of languages and the countries in which they are spoken, as estimated by Unicode. Edges are weighted by the proportion of the given country's population that is literate in a particular language.
This network has 868 nodes and 1255 edges.
Tags: Informational, Relatedness, Weighted

MultiWikiQA: A Reading Comprehension Benchmark in 300 Languages
Dan Saattrup Smart
https://arxiv.org/abs/2509.04111 https://arxiv.org/pdf/2509.04111

MultiWikiQA: A Reading Comprehension Benchmark in 300+ Languages
We introduce a new reading comprehension dataset, dubbed MultiWikiQA, which covers 306 languages. The context data comes from Wikipedia articles, with questions generated by an LLM and the answers appearing verbatim in the Wikipedia articles. We conduct a crowdsourced human evaluation of the fluency of the generated questions across 30 of the languages, providing evidence that the questions are of good quality. We evaluate 6 different language models, both decoder and encoder models of varying …

A look at India's push to compete in the global AI race, as the country's vast linguistic diversity poses a core challenge to building foundational AI models (Shadma Shaikh/MIT Technology Review)
https://www.technologyreview.com/2025/07/0

Inside India’s scramble for AI independence
Structural challenges and the nation’s many languages have made it tough to develop foundational AI models. But the government is keen not to be left behind.

IMO the reason why people yearn for tools that generate code is that programming is broken—everything now is giant layer cakes of huge, complex and intransparent frameworks designed by and for large teams in giant tech companies.
The same tech companies that flooded programming with overly complex tools, endless toolchains, new programming languages du jour every few years, required backwards-compatibility breaking updates and mandatory design overhauls are now selling you “AI” to generate code for the mess they made.

A substitution lemma for multiple context-free languages
Andrew Duncan, Murray Elder, Lisa Frenkel, Mengfan Lyu
https://arxiv.org/abs/2509.02117 https://ar…

A substitution lemma for multiple context-free languages
We present a new criterion for proving that a language is not multiple context-free, which we call a Substitution Lemma. We apply it to show a sample selection of languages are not multiple context-free, including the word problem of $F_2\times F_2$. Our result is in contrast to Kanazawa et al. [2014, Theory Comput. Syst.] who proved that it was not possible to generalise the standard pumping lemma for context-free languages to multiple context-free languages, and Kanazawa [2019, Inform. and …

Google specifically looking for expertise in machine learning and PROGRAMMING LANGUAGES. Papers at conferences like PLDI/ICFP, experience w/ LC, types, CL… ML slowly coming to its senses. (-:
https://www.google.com/about/careers/appli

Have Object-Oriented Languages Missed a Trick with Class Function and its Subclasses?
Lloyd Allison
https://arxiv.org/abs/2507.00488 https://

Have Object-Oriented Languages Missed a Trick with Class Function and its Subclasses?
Compared to functions in mathematics, functions in programming languages seem to be under classified. Functional programming languages based on the lambda calculus famously treat functions as first-class values. Object-oriented languages have adopted ``lambdas'', notably for call-back routines in event-based programming. Typically a programming language has functions, a function has a type, and some functions act on other functions and/or return functions but there is generally a lack of (i) ``…

@… Yes, I am with you. I like writing Haskell for Serious Business, because I find I can work with the grain better than other languages, but for experimentation? No thanks. (I must learn a Lisp properly at some point. Got any recommendations?)

Great news. Canada is doing offering government services (commercial driver’s license tests) in Ojibwe/Anishinaabemowin.
It’s a crime and a tragedy that indigenous languages are in danger of dying and everything that can be done to fight that is for the better, especially by governments using them.

Indigenous man's 'jaw nearly hit the counter' when told he could write driver's test in Ojibwe | CBC News
The former chief of the Chippewas of Kettle and Stony Point First Nation got an early birthday surprise when he was finally able to do his written driver’s test in Ojibwe.   

Putting Perspective into OWL [sic]: Complexity-Neutral Standpoint Reasoning for Ontology Languages via Monodic S5 over Counting Two-Variable First-Order Logic (Extended Version with Appendix)
Luc\'ia G\'omez \'Alvarez, Sebastian Rudolph
https://arxiv.org/abs/2508.00653

Putting Perspective into OWL [sic]: Complexity-Neutral Standpoint Reasoning for Ontology Languages via Monodic S5 over Counting Two-Variable First-Order Logic (Extended Version with Appendix)
Standpoint extensions of knowledge representation formalisms have been recently introduced as a means to incorporate multi-perspective modelling and reasoning through modal operators that attribute pieces of knowledge to specific entities or agents. In these extensions, the integration between conceptual modelling and perspective annotations can vary in strength, with monodic standpoint extensions offering a well-balanced approach. They allow for advanced modelling features, such as the express…

Exploring NLP Benchmarks in an Extremely Low-Resource Setting
Ulin Nuha, Adam Jatowt
https://arxiv.org/abs/2509.03962 https://arxiv.org/pdf/2509.03962

Exploring NLP Benchmarks in an Extremely Low-Resource Setting
The effectiveness of Large Language Models (LLMs) diminishes for extremely low-resource languages, such as indigenous languages, primarily due to the lack of labeled data. Despite growing interest, the availability of high-quality natural language processing (NLP) datasets for these languages remains limited, making it difficult to develop robust language technologies. This paper addresses such gap by focusing on Ladin, an endangered Romance language, specifically targeting the Val Badia varian…

Should we teach vibe coding? Here's why not.
Should AI coding be taught in undergrad CS education?
1/2
I teach undergraduate computer science labs, including for intro and more-advanced core courses. I don't publish (non-negligible) scholarly work in the area, but I've got years of craft expertise in course design, and I do follow the academic literature to some degree. In other words, In not the world's leading expert, but I have spent a lot of time thinking about course design, and consider myself competent at it, with plenty of direct experience in what knowledge & skills I can expect from students as they move through the curriculum.
I'm also strongly against most uses of what's called "AI" these days (specifically, generative deep neutral networks as supplied by our current cadre of techbro). There are a surprising number of completely orthogonal reasons to oppose the use of these systems, and a very limited number of reasonable exceptions (overcoming accessibility barriers is an example). On the grounds of environmental and digital-commons-pollution costs alone, using specifically the largest/newest models is unethical in most cases.
But as any good teacher should, I constantly question these evaluations, because I worry about the impact on my students should I eschew teaching relevant tech for bad reasons (and even for his reasons). I also want to make my reasoning clear to students, who should absolutely question me on this. That inspired me to ask a simple question: ignoring for one moment the ethical objections (which we shouldn't, of course; they're very stark), at what level in the CS major could I expect to teach a course about programming with AI assistance, and expect students to succeed at a more technically demanding final project than a course at the same level where students were banned from using AI? In other words, at what level would I expect students to actually benefit from AI coding "assistance?"
To be clear, I'm assuming that students aren't using AI in other aspects of coursework: the topic of using AI to "help you study" is a separate one (TL;DR it's gross value is not negative, but it's mostly not worth the harm to your metacognitive abilities, which AI-induced changes to the digital commons are making more important than ever).
So what's my answer to this question?
If I'm being incredibly optimistic, senior year. Slightly less optimistic, second year of a masters program. Realistic? Maybe never.
The interesting bit for you-the-reader is: why is this my answer? (Especially given that students would probably self-report significant gains at lower levels.) To start with, [this paper where experienced developers thought that AI assistance sped up their work on real tasks when in fact it slowed it down] (https://arxiv.org/abs/2507.09089) is informative. There are a lot of differences in task between experienced devs solving real bugs and students working on a class project, but it's important to understand that we shouldn't have a baseline expectation that AI coding "assistants" will speed things up in the best of circumstances, and we shouldn't trust self-reports of productivity (or the AI hype machine in general).
Now we might imagine that coding assistants will be better at helping with a student project than at helping with fixing bugs in open-source software, since it's a much easier task. For many programming assignments that have a fixed answer, we know that many AI assistants can just spit out a solution based on prompting them with the problem description (there's another elephant in the room here to do with learning outcomes regardless of project success, but we'll ignore this over too, my focus here is on project complexity reach, not learning outcomes). My question is about more open-ended projects, not assignments with an expected answer. Here's a second study (by one of my colleagues) about novices using AI assistance for programming tasks. It showcases how difficult it is to use AI tools well, and some of these stumbling blocks that novices in particular face.
But what about intermediate students? Might there be some level where the AI is helpful because the task is still relatively simple and the students are good enough to handle it? The problem with this is that as task complexity increases, so does the likelihood of the AI generating (or copying) code that uses more complex constructs which a student doesn't understand. Let's say I have second year students writing interactive websites with JavaScript. Without a lot of care that those students don't know how to deploy, the AI is likely to suggest code that depends on several different frameworks, from React to JQuery, without actually setting up or including those frameworks, and of course three students would be way out of their depth trying to do that. This is a general problem: each programming class carefully limits the specific code frameworks and constructs it expects students to know based on the material it covers. There is no feasible way to limit an AI assistant to a fixed set of constructs or frameworks, using current designs. There are alternate designs where this would be possible (like AI search through adaptation from a controlled library of snippets) but those would be entirely different tools.
So what happens on a sizeable class project where the AI has dropped in buggy code, especially if it uses code constructs the students don't understand? Best case, they understand that they don't understand and re-prompt, or ask for help from an instructor or TA quickly who helps them get rid of the stuff they don't understand and re-prompt or manually add stuff they do. Average case: they waste several hours and/or sweep the bugs partly under the rug, resulting in a project with significant defects. Students in their second and even third years of a CS major still have a lot to learn about debugging, and usually have significant gaps in their knowledge of even their most comfortable programming language. I do think regardless of AI we as teachers need to get better at teaching debugging skills, but the knowledge gaps are inevitable because there's just too much to know. In Python, for example, the LLM is going to spit out yields, async functions, try/finally, maybe even something like a while/else, or with recent training data, the walrus operator. I can't expect even a fraction of 3rd year students who have worked with Python since their first year to know about all these things, and based on how students approach projects where they have studied all the relevant constructs but have forgotten some, I'm not optimistic seeing these things will magically become learning opportunities. Student projects are better off working with a limited subset of full programming languages that the students have actually learned, and using AI coding assistants as currently designed makes this impossible. Beyond that, even when the "assistant" just introduces bugs using syntax the students understand, even through their 4th year many students struggle to understand the operation of moderately complex code they've written themselves, let alone written by someone else. Having access to an AI that will confidently offer incorrect explanations for bugs will make this worse.
To be sure a small minority of students will be able to overcome these problems, but that minority is the group that has a good grasp of the fundamentals and has broadened their knowledge through self-study, which earlier AI-reliant classes would make less likely to happen. In any case, I care about the average student, since we already have plenty of stuff about our institutions that makes life easier for a favored few while being worse for the average student (note that our construction of that favored few as the "good" students is a large part of this problem).
To summarize: because AI assistants introduce excess code complexity and difficult-to-debug bugs, they'll slow down rather than speed up project progress for the average student on moderately complex projects. On a fixed deadline, they'll result in worse projects, or necessitate less ambitious project scoping to ensure adequate completion, and I expect this remains broadly true through 4-6 years of study in most programs (don't take this as an endorsement of AI "assistants" for masters students; we've ignored a lot of other problems along the way).
There's a related problem: solving open-ended project assignments well ultimately depends on deeply understanding the problem, and AI "assistants" allow students to put a lot of code in their file without spending much time thinking about the problem or building an understanding of it. This is awful for learning outcomes, but also bad for project success. Getting students to see the value of thinking deeply about a problem is a thorny pedagogical puzzle at the best of times, and allowing the use of AI "assistants" makes the problem much much worse. This is another area I hope to see (or even drive) pedagogical improvement in, for what it's worth.
1/2

Bridging Language Gaps in Open-Source Documentation with Large-Language-Model Translation
Elijah Kayode Adejumo, Brittany Johnson, Mariam Guizani
https://arxiv.org/abs/2508.02497

Bridging Language Gaps in Open-Source Documentation with Large-Language-Model Translation
While open source communities attract diverse contributors globally, few repositories provide essential documentation in languages other than English. Large language models (LLMs) have demonstrated remarkable capabilities in software engineering tasks and translations across domains. However, little is known about LLM capabilities in translating open-source technical documentation, which mixes natural language, code, URLs, and markdown formatting. To understand the need and potential for LLMs i…

Store Languages of Turing Machines and Counter Machines
Noah Friesen, Oscar H. Ibarra, Jozef Jir\'asek, Ian McQuillan
https://arxiv.org/abs/2509.02828 https://

Store Languages of Turing Machines and Counter Machines
The store language of an automaton is the set of store configurations (state and store contents, but not the input) that can appear as an intermediate step in an accepting computation. A one-way nondeterministic finite-visit Turing machine (fvNTM) is a Turing machine with a one-way read-only input tape, and a single worktape, where there is some number $k$ such that in every accepting computation, each worktape cell is visited at most $k$ times. We show that the store language of every fvNTM is…

Characterization of Speech Similarity Between Australian Aboriginal and High-Resource Languages: A Case Study on Dharawal
Ting Dang, Trini Manoj Jeyaseelan, Eliathamby Ambikairajah, Vidhyasaharan Sethu
https://arxiv.org/abs/2509.01419

Characterization of Speech Similarity Between Australian Aboriginal and High-Resource Languages: A Case Study on Dharawal
Australian Aboriginal languages are of significant cultural and linguistic value but remain severely underrepresented in modern speech AI systems. While state-of-the-art speech foundation models and automatic speech recognition excel in high-resource settings, they often struggle to generalize to low-resource languages, especially those lacking clean, annotated speech data. In this work, we collect and clean a speech dataset for Dharawal, a low-resource Australian Aboriginal language, by carefu…

From Sentences to Sequences: Rethinking Languages in Biological System
Ke Liu, Shuanke Shen, Hao Chen
https://arxiv.org/abs/2507.00953 https://

From Sentences to Sequences: Rethinking Languages in Biological System
The paradigm of large language models in natural language processing (NLP) has also shown promise in modeling biological languages, including proteins, RNA, and DNA. Both the auto-regressive generation paradigm and evaluation metrics have been transferred from NLP to biological sequence modeling. However, the intrinsic structural correlations in natural and biological languages differ fundamentally. Therefore, we revisit the notion of language in biological systems to better understand how NLP …

You may know I’m a big fan of #OpenTelemetry. I recently finished developing a master class for the YOW! conference at the end of the year. During development, I noticed massive differences in configuration and results across programming languages. Even worse, differences exist across frameworks inside the same programming language.
In this post, I want to compare the different zero-cod…

Replaced article(s) found for cs.PL. https://arxiv.org/list/cs.PL/new
[1/1]:
- MCTS-SQL: Light-Weight LLMs can Master the Text-to-SQL through Monte Carlo Tree Search
Shuozhi Yuan, Limin Chen, Miaomiao Yuan, Jin Zhao

Python is also the most desired programming language in the Stack Overflow developer survey, while Rust remains the most admired: https://survey.stackoverflow.co/2025/technology#2-programming-scripting-and-markup-languages

Shape and word parts combine linearly in the Bouba–Kiki effect https://link.springer.com/article/10.3758/s13414-025-03151-1

Shape and word parts combine linearly in the Bouba–Kiki effect - Attention, Perception, & Psychophysics
Languages have evolved in part due to cross-modal associations between shape and sound. A famous example is the Bouba–Kiki effect, wherein humans associate words like bouba/kiki to round/angular shapes. How does the Bouba–Kiki effect work for natural words and shapes that contain a mixture of features? If the effect is holistic, the effect for a composite stimulus would not be explainable using the parts. If the effect is compositional, it will be. Here we provide evidence for the latter po…

As I'm learning Dutch, I'm reminded that the idea that there are people who believe that the bible is to be taken literally. The idea that a several hundred year old translation of a collection of texts in multiple languages, that were themselves translated multiple times between languages, before the whole thing was translated to Latin, then being translated to English, could somehow perfectly reflect the original text... Yeah, it's only possible to believe that if you have no idea how languages work and have never learned another language.
Like, just from linguistic drift alone if the bible were written in King James English you're losing *so* much context. But Hebrew, Aramaic, and Greek translated to Latin, then to English, then to English again?
There are so many things that erg can't be translated, even as a beginner. Dutch and English are two of the closest languages that exist, they're both Germanic languages and they're the closest to each other (other than Friesian). You can't really be much closer, and yet, there are so many things you can't mutually represent. Hebrew and Latin, Aramaic and Latin, Latin and English, Greek and English, these aren't even the same families at all... They're extremely distant. There's absolutely no way to represent concepts from one to another without another book's worth of explanation.
And that ignores all the cultural context, which is mostly lost and a library and decade of education to get the stuff that we *do* know.
Only monolingual Americans could come up with an idea so incredibly asinine.

word_adjacency: Word Adjacency Networks
Directed Networks of word adjacency in texts of several languages including English, French, Spanish and Japanese.
This network has 7381 nodes and 46281 edges.
Tags: Informational, Language, Unweighted
https://networks.skewed.de/net/word_ad

L3Cube-IndicHeadline-ID: A Dataset for Headline Identification and Semantic Evaluation in Low-Resource Indian Languages
Nishant Tanksale, Tanmay Kokate, Darshan Gohad, Sarvadnyaa Barate, Raviraj Joshi
https://arxiv.org/abs/2509.02503

L3Cube-IndicHeadline-ID: A Dataset for Headline Identification and Semantic Evaluation in Low-Resource Indian Languages
Semantic evaluation in low-resource languages remains a major challenge in NLP. While sentence transformers have shown strong performance in high-resource settings, their effectiveness in Indic languages is underexplored due to a lack of high-quality benchmarks. To bridge this gap, we introduce L3Cube-IndicHeadline-ID, a curated headline identification dataset spanning ten low-resource Indic languages: Marathi, Hindi, Tamil, Gujarati, Odia, Kannada, Malayalam, Punjabi, Telugu, Bengali and Engli…

Supervisory Control of Discrete Event Systems for Small Language Under Cyber Attacks
Xiaojun Wang, Shaolong Shu, Feng Lin
https://arxiv.org/abs/2508.02083 https://

Supervisory Control of Discrete Event Systems for Small Language Under Cyber Attacks
Cyber attacks are unavoidable in networked discrete event systems where the plant and the supervisor communicate with each other via networks. Because of the nondeterminism in observation and control caused by cyber attacks, the language generated by the supervised system becomes nondeterministic. The small language is defined as the lower bound on all possible languages that can be generated by the supervised system, which is needed for a supervised system to perform some required tasks under …

Bookmarked: Talking About Muslims in Middle French: The Potential of Word-to-Vector Models for Studying Semantic Relationships in Medieval Languages – DH Lab #Digital_Humanities

from my link log —
Writing that can change how you think about programming languages.
https://bernsteinbear.com/blog/pl-writing/
saved 2025-05-13

Adapting Language Models to Indonesian Local Languages: An Empirical Study of Language Transferability on Zero-Shot Settings
Rifki Afina Putri
https://arxiv.org/abs/2507.01645

Adapting Language Models to Indonesian Local Languages: An Empirical Study of Language Transferability on Zero-Shot Settings
In this paper, we investigate the transferability of pre-trained language models to low-resource Indonesian local languages through the task of sentiment analysis. We evaluate both zero-shot performance and adapter-based transfer on ten local languages using models of different types: a monolingual Indonesian BERT, multilingual models such as mBERT and XLM-R, and a modular adapter-based approach called MAD-X. To better understand model behavior, we group the target languages into three categori…

https://linuxiac.com/new-movie-python-the-documentary-traces-the-languages-story/

Strategic Communication and Language Bias in Multi-Agent LLM Coordination
Alessio Buscemi, Daniele Proverbio, Alessandro Di Stefano, The Anh Han, German Castignani, Pietro Li\`o
https://arxiv.org/abs/2508.00032

Strategic Communication and Language Bias in Multi-Agent LLM Coordination
Large Language Model (LLM)-based agents are increasingly deployed in multi-agent scenarios where coordination is crucial but not always assured. Previous studies indicate that the language used to frame strategic scenarios can influence cooperative behavior. This paper explores whether allowing agents to communicate amplifies these language-driven effects. Leveraging the FAIRGAME framework, we simulate one-shot and repeated games across different languages and models, both with and without comm…

A look at the ~$377 TranscribeGlass smart glasses that use AI to subtitle conversations in nearly real time, built for the deaf or hard-of-hearing (Boone Ashworth/Wired)
https://www.wired.com/story/these-translating-ai-glasses-put-subtitles-on-…

These Transcribing Eyeglasses Put Subtitles on the World
TranscribeGlass can subtitle conversations in nearly real time and will soon be able to translate languages and tell you when the person you’re talking to you is feeling socially awkward.

Interesting… 🤔 "ICU4X - Solving i18n for client-side and resource-constrained environments" https://icu4x.unicode.org/
> Why ICU4X?
> Small and fast
> ICU4X floats like a butterfly and stings like a bee
😅🦋🐝

Replaced article(s) found for cs.PL. https://arxiv.org/list/cs.PL/new
[1/1]:
- Escape with Your Self: Sound and Expressive Bidirectional Typing with Avoidance for Reachability ...
Songlin Jia, Guannan Wei, Siyuan He, Yuyan Bao, Tiark Rompf

Combining Type Inference and Automated Unit Test Generation for Python
Lukas Krodinger, Stephan Lukasczyk, Gordon Fraser
https://arxiv.org/abs/2507.01477 h…

Combining Type Inference and Automated Unit Test Generation for Python
Automated unit test generation is an established research field that has so far focused on statically-typed programming languages. The lack of type information in dynamically-typed programming languages, such as Python, inhibits test generators, which heavily rely on information about parameter and return types of functions to select suitable arguments when constructing test cases. Since automated test generators inherently rely on frequent execution of candidate tests, we make use of these fre…

Replaced article(s) found for cs.FL. https://arxiv.org/list/cs.FL/new
[1/1]:
- Universality Frontier for Asynchronous Cellular Automata
Ivan Baburin, Matthew Cook, Florian Gr\"otschla, Andreas Plesner, Roger Wattenhofer

Meta-Pretraining for Zero-Shot Cross-Lingual Named Entity Recognition in Low-Resource Philippine Languages
David Demitri Africa, Suchir Salhan, Yuval Weiss, Paula Buttery, Richard Diehl Martinez
https://arxiv.org/abs/2509.02160

Meta-Pretraining for Zero-Shot Cross-Lingual Named Entity Recognition in Low-Resource Philippine Languages
Named-entity recognition (NER) in low-resource languages is usually tackled by finetuning very large multilingual LMs, an option that is often infeasible in memory- or latency-constrained settings. We ask whether small decoder LMs can be pretrained so that they adapt quickly and transfer zero-shot to languages unseen during pretraining. To this end we replace part of the autoregressive objective with first-order model-agnostic meta-learning (MAML). Tagalog and Cebuano are typologically similar …

Crosslisted article(s) found for cs.PL. https://arxiv.org/list/cs.PL/new
[1/1]:
- Lattice Annotated Temporal (LAT) Logic for Non-Markovian Reasoning
Mukherji, Patil, Aditya, Shakarian, Parkar, Pokala, Dorman, Simari

Decision algorithms for fragments of real analysis. III: A theory of differentiable functions with (semi-)open intervals
G. Buriola, D. Cantone, G. Cincotti, E. G. Omodeo, G. T. Spart\`a
https://arxiv.org/abs/2507.02742

Decision algorithms for fragments of real analysis. III: A theory of differentiable functions with (semi-)open intervals
This paper enriches preexisting satisfiability tests for unquantified languages, which in turn augment a fragment of Tarski's elementary algebra with unary real functions possessing a continuous first derivative. Two sorts of individual variables are available, one ranging over real numbers and the other one ranging over the functions of interest. Numerical terms are built from real variables through constructs designating the four basic arithmetic operations and through the function-applicat…

Google says NotebookLM's Video Overviews now support 80 languages, and Audio Overviews now provide more detailed non-English summaries (Lauren Forristal/TechCrunch)
https://techcrunch.com/2025/08/25/notebooklms-video-overview-feature-now-su…

NotebookLM’s Video Overview feature now supports 80 languages | TechCrunch
NotebookLM’s Video Overviews now supports 80 languages, including French and Spanish.

Are We SOLID Yet? An Empirical Study on Prompting LLMs to Detect Design Principle Violations
Fatih Pehlivan, Ar\c{c}in \"Ulk\"u Erg\"uzen, Sahand Moslemi Yengejeh, Mayasah Lami, Anil Koyuncu
https://arxiv.org/abs/2509.03093

Are We SOLID Yet? An Empirical Study on Prompting LLMs to Detect Design Principle Violations
Traditional static analysis methods struggle to detect semantic design flaws, such as violations of the SOLID principles, which require a strong understanding of object-oriented design patterns and principles. Existing solutions typically focus on individual SOLID principles or specific programming languages, leaving a gap in the ability to detect violations across all five principles in multi-language codebases. This paper presents a new approach: a methodology that leverages tailored prompt e…

Replaced article(s) found for cs.PL. https://arxiv.org/list/cs.PL/new
[1/1]:
- Modal Abstractions for Virtualizing Memory Addresses
Ismail Kuru, Colin S. Gordon
h…

Replaced article(s) found for cs.FL. https://arxiv.org/list/cs.FL/new
[1/1]:
- A Finite-State Symbolic Automaton Model for the Collatz Map and Its Convergence Properties
Leonard Ben Aurel Brauer

from my link log —
Sapir-Whorf does not apply to programming languages.
https://buttondown.com/hillelwayne/archive/sapir-whorf-does-not-apply-to-programming/
saved 2025-08-21

Sapir-Whorf does not apply to Programming Languages
Linguistics is about human languages, not programming ones

An LLM-enabled semantic-centric framework to consume privacy policies
Rui Zhao, Vladyslav Melnychuk, Jun Zhao, Jesse Wright, Nigel Shadbolt
https://arxiv.org/abs/2509.01716 http…

An LLM-enabled semantic-centric framework to consume privacy policies
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, due to the practical difficulty in comprehending them. The mist of data privacy practices forms a major barrier for user-centred Web approaches, and for data sharing and reusing in an agentic world. Existing research proposed methods for using formal languages and reasoning for verifying the compliance of a specified policy, as a potentia…

Natural language processing for African languages
David Ifeoluwa Adelani
https://arxiv.org/abs/2507.00297 https://arxiv.org/pdf/2507.…

Natural language processing for African languages
Recent advances in word embeddings and language models use large-scale, unlabelled data and self-supervised learning to boost NLP performance. Multilingual models, often trained on web-sourced data like Wikipedia, face challenges: few low-resource languages are included, their data is often noisy, and lack of labeled datasets makes it hard to evaluate performance outside high-resource languages like English. In this dissertation, we focus on languages spoken in Sub-Saharan Africa where all the …

Replaced article(s) found for cs.FL. https://arxiv.org/list/cs.FL/new
[1/1]:
- Risk-Aware Autonomous Driving with Linear Temporal Logic Specifications
Shuhao Qi, Zengjie Zhang, Zhiyong Sun, Sofie Haesaert

Crosslisted article(s) found for cs.FL. https://arxiv.org/list/cs.FL/new
[1/1]:
- Identifiability and minimality bounds of quantum and post-quantum models of classical stochastic ...
Paul M. Riechers, Thomas J. Elliott

[2025-08-04 Mon (UTC), 6 new articles found for cs.PL Programming Languages]
toXiv_bot_toot

What Challenges Do Developers Face When Using Verification-Aware Programming Languages?
Francisco Oliveira, Alexandra Mendes, Carolina Carreira
https://arxiv.org/abs/2506.23696

What Challenges Do Developers Face When Using Verification-Aware Programming Languages?
Software reliability is critical in ensuring that the digital systems we depend on function correctly. In software development, increasing software reliability often involves testing. However, for complex and critical systems, developers can use Design by Contract (DbC) methods to define precise specifications that software components must satisfy. Verification-Aware (VA) programming languages support DbC and formal verification at compile-time or run-time, offering stronger correctness guarant…

Virtual Group Knowledge and Group Belief in Topological Evidence Models (Extended Version)
Alexandru Baltag, Malvin Gattinger, Djanira Gomes
https://arxiv.org/abs/2509.00184 htt…

Virtual Group Knowledge and Group Belief in Topological Evidence Models (Extended Version)
We study notions of (virtual) group knowledge and group belief within multi-agent evidence models, obtained by extending the topological semantics of evidence-based belief and fallible knowledge from individuals to groups. We completely axiomatize and show the decidability of the logic of ("hard" and "soft") group evidence, and do the same for an especially interesting fragment of it: the logic of group knowledge and group belief. We also extend these languages with dynamic evidence-sharing ope…

Replaced article(s) found for cs.FL. https://arxiv.org/list/cs.FL/new
[1/1]:
- Autoformalization in the Wild: Assessing LLMs on Real-World Mathematical Definitions
Lan Zhang, Marco Valentino, Andre Freitas

[2025-08-05 Tue (UTC), 2 new articles found for cs.PL Programming Languages]
toXiv_bot_toot

Crosslisted article(s) found for cs.FL. https://arxiv.org/list/cs.FL/new
[1/1]:
- Simplicity Lies in the Eye of the Beholder: A Strategic Perspective on Controllers in Reactive Sy...
Mickael Randour

Eka-Eval : A Comprehensive Evaluation Framework for Large Language Models in Indian Languages
Samridhi Raj Sinha, Rajvee Sheth, Abhishek Upperwal, Mayank Singh
https://arxiv.org/abs/2507.01853

Eka-Eval : A Comprehensive Evaluation Framework for Large Language Models in Indian Languages
The rapid advancement of Large Language Models (LLMs) has intensified the need for evaluation frameworks that go beyond English centric benchmarks and address the requirements of linguistically diverse regions such as India. We present EKA-EVAL, a unified and production-ready evaluation framework that integrates over 35 benchmarks, including 10 Indic-specific datasets, spanning categories like reasoning, mathematics, tool use, long-context understanding, and reading comprehension. Compared to e…

[2025-09-04 Thu (UTC), 1 new article found for cs.PL Programming Languages]
toXiv_bot_toot

Tencent open sources translation models Hunyuan-MT-7B and Hunyuan-MT-Chimera-7B, which support 33 languages, claiming they beat established models in benchmarks (Jonathan Kemper/The Decoder)
https://the-decoder.com/tencent-open-sources-two-high-performing…

Tencent open sources two high-performing translation models
Chinese tech giant Tencent has open sourced two specialized translation models, claiming they outperform established tools like Google Translate in international benchmarks.

[2025-09-05 Fri (UTC), 1 new article found for cs.PL Programming Languages]
toXiv_bot_toot

NIRANTAR: Continual Learning with New Languages and Domains on Real-world Speech Data
Tahir Javed, Kaushal Bhogale, Mitesh M. Khapra
https://arxiv.org/abs/2507.00534

NIRANTAR: Continual Learning with New Languages and Domains on Real-world Speech Data
We introduce Nirantar, a comprehensive framework for evaluating continual learning (CL) in multilingual and multi-domain ASR. Designed to reflect real-world CL challenges, Nirantar leverages data collected incrementally across 22 languages and 208 districts in India through natural episodes. This enables evaluation across Language-Incremental (LIL), Domain-Incremental (DIL), and the novel Language-Incremental Domain-Incremental Learning (LIDIL) scenarios. Unlike prior work that relies on simula…

When Lifetimes Liberate: A Type System for Arenas with Higher-Order Reachability Tracking
Siyuan He, Songlin Jia, Yuyan Bao, Tiark Rompf
https://arxiv.org/abs/2509.04253 https:/…

When Lifetimes Liberate: A Type System for Arenas with Higher-Order Reachability Tracking
Static resource management in higher-order functional languages remains elusive due to tensions between control, expressiveness, and flexibility. Region-based systems [Grossman et al. 2002; Tofte et al. 2001] offer control over lifetimes and expressive in-region sharing, but restrict resources to lexical scopes. Rust, an instance of ownership types [Clarke et al. 2013], offers non-lexical lifetimes and robust safety guarantees, yet its global invariants make common sharing patterns hard to expr…

A RoBERTa-Based Functional Syntax Annotation Model for Chinese Texts
Han Xiaohui, Zhang Yunlong, Guo Yuxi
https://arxiv.org/abs/2509.04046 https://arxiv.or…

A RoBERTa-Based Functional Syntax Annotation Model for Chinese Texts
Systemic Functional Grammar and its branch, Cardiff Grammar, have been widely applied to discourse analysis, semantic function research, and other tasks across various languages and texts. However, an automatic annotation system based on this theory for Chinese texts has not yet been developed, which significantly constrains the application and promotion of relevant theories. To fill this gap, this research introduces a functional syntax annotation model for Chinese based on RoBERTa (Robustly O…

Replaced article(s) found for cs.FL. https://arxiv.org/list/cs.FL/new
[1/1]:
- Dynamic Membership for Regular Tree Languages
Antoine Amarilli, Corentin Barloy, Louis Jachiet, Charles Paperman

Scalable Thread-Safety Analysis of Java Classes with CodeQL
Bj{\o}rnar Haugstad J{\aa}tten, Simon Boye J{\o}rgensen, Rasmus Petersen, Ra\'ul Pardo
https://arxiv.org/abs/2509.02022

Scalable Thread-Safety Analysis of Java Classes with CodeQL
In object-oriented languages software developers rely on thread-safe classes to implement concurrent applications. However, determining whether a class is thread-safe is a challenging task. This paper presents a highly scalable method to analyze thread-safety in Java classes. We provide a definition of thread-safety for Java classes founded on the correctness principle of the Java memory model, data race freedom. We devise a set of properties for Java classes that are proven to ensure thread-sa…

Towards a unified framework for programming paradigms: A systematic review of classification formalisms and methodological foundations
Mikel Vandeloise
https://arxiv.org/abs/2508.00534

Towards a unified framework for programming paradigms: A systematic review of classification formalisms and methodological foundations
The rise of multi-paradigm languages challenges traditional classification methods, leading to practical software engineering issues like interoperability defects. This systematic literature review (SLR) maps the formal foundations of programming paradigms. Our objective is twofold: (1) to assess the state of the art of classification formalisms and their limitations, and (2) to identify the conceptual primitives and mathematical frameworks for a more powerful, reconstructive approach. Based …

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[3/3]:
- Science Across Languages: Assessing LLM Multilingual Translation of Scientific Papers
Hannah Calzi Kleidermacher, James Zou

[2025-07-04 Fri (UTC), 1 new article found for cs.FL Formal Languages and Automata Theory]
toXiv_bot_toot

Efficient compilation and execution of synchronous programs via type-state programming
Avinash Malik
https://arxiv.org/abs/2508.01199 https://arxiv.org/pdf…

Efficient compilation and execution of synchronous programs via type-state programming
Synchronous programs are used extensively in implementation of safety critical embedded software. Imperative synchronous programming languages model multiple Finite State Machines (FSMs) executing in lockstep at logical clock ticks. The synchronous view of time along with the FSM based design enables easier formal verification. The synchronous composition of multiple FSMs, during compilation, results in the well known state space explosion problem. Hence, efficiently compiling imperative synchr…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[2/3]:
- Traveling Across Languages: Benchmarking Cross-Lingual Consistency in Multimodal LLMs
Hao Wang, Pinzhi Huang, Jihan Yang, Saining Xie, Daisuke Kawahara

[2025-08-05 Tue (UTC), 1 new article found for cs.FL Formal Languages and Automata Theory]
toXiv_bot_toot

MELAC: Massive Evaluation of Large Language Models with Alignment of Culture in Persian Language
Farhan Farsi, Farnaz Aghababaloo, Shahriar Shariati Motlagh, Parsa Ghofrani, MohammadAli SadraeiJavaheri, Shayan Bali, Amirhossein Shabani, Farbod Bijary, Ghazal Zamaninejad, AmirMohammad Salehoof, Saeedeh Momtazi
https://arxiv.org/abs/2508.006…

MELAC: Massive Evaluation of Large Language Models with Alignment of Culture in Persian Language
As large language models (LLMs) become increasingly embedded in our daily lives, evaluating their quality and reliability across diverse contexts has become essential. While comprehensive benchmarks exist for assessing LLM performance in English, there remains a significant gap in evaluation resources for other languages. Moreover, because most LLMs are trained primarily on data rooted in European and American cultures, they often lack familiarity with non-Western cultural contexts. To address …

Semantically Reflected Programs
Eduard Kamburjan, Vidar Norstein Klungre, Yuanwei Qu, Rudolf Schlatte, Egor V. Kostylev, Martin Giese, Einar Broch Johnsen
https://arxiv.org/abs/2509.03318

Semantically Reflected Programs
This paper addresses the dichotomy between the formalization of structural and the formalization of behavioral knowledge by means of semantically lifted programs, which explore an intuitive connection between programs and knowledge graphs. While knowledge graphs and ontologies are eminently useful to represent formal knowledge about a system's individuals and universals, programming languages are designed to describe the system's evolution. To address this dichotomy, we introduce a semantic lif…

[2025-09-04 Thu (UTC), 1 new article found for cs.FL Formal Languages and Automata Theory]
toXiv_bot_toot

[2025-09-05 Fri (UTC), 1 new article found for cs.FL Formal Languages and Automata Theory]
toXiv_bot_toot

[2025-08-04 Mon (UTC), no new articles found for cs.FL Formal Languages and Automata Theory]
toXiv_bot_toot

Replaced article(s) found for cs.PL. https://arxiv.org/list/cs.PL/new
[1/1]:
- Abstract Interpretation of Temporal Safety Effects of Higher Order Programs
Mihai Nicola, Chaitanya Agarwal, Eric Koskinen, Thomas Wies

Crosslisted article(s) found for cs.PL. https://arxiv.org/list/cs.PL/new
[1/1]:
- REFINESTAT: Efficient Exploration for Probabilistic Program Synthesis
Madhav Kanda, Shubham Ugare, Sasa Misailovic

Investigating Hallucination in Conversations for Low Resource Languages
Amit Das, Md. Najib Hasan, Souvika Sarkar, Zheng Zhang, Fatemeh Jamshidi, Tathagata Bhattacharya, Nilanjana Raychawdhury, Dongji Feng, Vinija Jain, Aman Chadha
https://arxiv.org/abs/2507.22720

Investigating Hallucination in Conversations for Low Resource Languages
Large Language Models (LLMs) have demonstrated remarkable proficiency in generating text that closely resemble human writing. However, they often generate factually incorrect statements, a problem typically referred to as 'hallucination'. Addressing hallucination is crucial for enhancing the reliability and effectiveness of LLMs. While much research has focused on hallucinations in English, our study extends this investigation to conversational data in three languages: Hindi, Farsi, and Mandari…

EfficientXLang: Towards Improving Token Efficiency Through Cross-Lingual Reasoning
Sanchit Ahuja, Praneetha Vaddamanu, Barun Patra
https://arxiv.org/abs/2507.00246

EfficientXLang: Towards Improving Token Efficiency Through Cross-Lingual Reasoning
Despite recent advances in Language Reasoning Models (LRMs), most research focuses solely on English, even though many models are pretrained on multilingual data. In this work, we investigate: Is English the most token-efficient language for reasoning? We evaluate three open-source RLMs: DeepSeek R1, Qwen 2.5 and Qwen 3, across four math datasets and seven typologically diverse languages. We find that reasoning in non-English languages not only reduces token usage, but also preserves accuracy. …

Languages Still Left Behind: Toward a Better Multilingual Machine Translation Benchmark
Chihiro Taguchi, Seng Mai, Keita Kurabe, Yusuke Sakai, Georgina Agyei, Soudabeh Eslami, David Chiang
https://arxiv.org/abs/2508.20511

Languages Still Left Behind: Toward a Better Multilingual Machine Translation Benchmark
Multilingual machine translation (MT) benchmarks play a central role in evaluating the capabilities of modern MT systems. Among them, the FLORES+ benchmark is widely used, offering English-to-many translation data for over 200 languages, curated with strict quality control protocols. However, we study data in four languages (Asante Twi, Japanese, Jinghpaw, and South Azerbaijani) and uncover critical shortcomings in the benchmark's suitability for truly multilingual evaluation. Human assessments…

Replaced article(s) found for cs.FL. https://arxiv.org/list/cs.FL/new
[1/1]:
- List of Results on the \v{C}ern\'y Conjecture and Reset Thresholds for Synchronizing Automata
Mikhail V. Volkov

Unveiling the Influence of Amplifying Language-Specific Neurons
Inaya Rahmanisa, Lyzander Marciano Andrylie, Krisna Mahardika Ihsani, Alfan Farizki Wicaksono, Haryo Akbarianto Wibowo, Alham Fikri Aji
https://arxiv.org/abs/2507.22581

Unveiling the Influence of Amplifying Language-Specific Neurons
Language-specific neurons in LLMs that strongly correlate with individual languages have been shown to influence model behavior by deactivating them. However, their role in amplification remains underexplored. This work investigates the effect of amplifying language-specific neurons through interventions across 18 languages, including low-resource ones, using three models primarily trained in different languages. We compare amplification factors by their effectiveness in steering to the target …

Crosslisted article(s) found for cs.FL. https://arxiv.org/list/cs.FL/new
[1/1]:
- Mean-payoff and Energy Discrete Bidding Games
Guy Avni, Suman Sadhukhan
https://…

[2025-09-03 Wed (UTC), 6 new articles found for cs.PL Programming Languages]
toXiv_bot_toot

[2025-07-03 Thu (UTC), 2 new articles found for cs.PL Programming Languages]
toXiv_bot_toot

Text2Cypher Across Languages: Evaluating Foundational Models Beyond English
Makbule Gulcin Ozsoy, William Tai
https://arxiv.org/abs/2506.21445 https://

Text2Cypher Across Languages: Evaluating Foundational Models Beyond English
Recent advances in large language models have enabled natural language interfaces that translate user questions into database queries, such as Text2SQL, Text2SPARQL, and Text2Cypher. While these interfaces enhance database accessibility, most research today focuses solely on English, with limited evaluation in other languages. This paper investigates the performance of foundational LLMs on the Text2Cypher task across multiple languages. We create and release a multilingual test set by translati…

Type-Based Incorrectness Reasoning
Zhe Zhou, Benjamin Delaware, Suresh Jagannathan
https://arxiv.org/abs/2509.01511 https://arxiv.org/pdf/2509.01511…

Type-Based Incorrectness Reasoning
A coverage type generalizes refinement types found in many functional languages with support for must-style underapproximate reasoning. Property-based testing frameworks are one particularly useful domain where such capabilities are useful as they allow us to verify the completeness, as well as safety, of test generators. There is a surprising connection between the kind of underapproximate reasoning coverage types offer and the style of reasoning enabled by recently proposed Incorrectness Logi…

Flavors of Moonshine: Tiny Specialized ASR Models for Edge Devices
Evan King, Adam Sabra, Manjunath Kudlur, James Wang, Pete Warden
https://arxiv.org/abs/2509.02523 https://

Flavors of Moonshine: Tiny Specialized ASR Models for Edge Devices
We present the Flavors of Moonshine, a suite of tiny automatic speech recognition (ASR) models specialized for a range of underrepresented languages. Prevailing wisdom suggests that multilingual ASR models outperform monolingual counterparts by exploiting cross-lingual phonetic similarities. We challenge this assumption, showing that for sufficiently small models (27M parameters), training monolingual systems on a carefully balanced mix of high-quality human-labeled, pseudo-labeled, and synthet…

DIY-MKG: An LLM-Based Polyglot Language Learning System
Kenan Tang, Yanhong Li, Yao Qin
https://arxiv.org/abs/2507.01872 https://arxi…

DIY-MKG: An LLM-Based Polyglot Language Learning System
Existing language learning tools, even those powered by Large Language Models (LLMs), often lack support for polyglot learners to build linguistic connections across vocabularies in multiple languages, provide limited customization for individual learning paces or needs, and suffer from detrimental cognitive offloading. To address these limitations, we design Do-It-Yourself Multilingual Knowledge Graph (DIY-MKG), an open-source system that supports polyglot language learning. DIY-MKG allows the…

Adaptability of ASR Models on Low-Resource Language: A Comparative Study of Whisper and Wav2Vec-BERT on Bangla
Md Sazzadul Islam Ridoy, Sumi Akter, Md. Aminur Rahman
https://arxiv.org/abs/2507.01931

Adaptability of ASR Models on Low-Resource Language: A Comparative Study of Whisper and Wav2Vec-BERT on Bangla
In recent years, neural models trained on large multilingual text and speech datasets have shown great potential for supporting low-resource languages. This study investigates the performances of two state-of-the-art Automatic Speech Recognition (ASR) models, OpenAI's Whisper (Small & Large-V2) and Facebook's Wav2Vec-BERT on Bangla, a low-resource language. We have conducted experiments using two publicly available datasets: Mozilla Common Voice-17 and OpenSLR to evaluate model performances. Th…

PalmX 2025: The First Shared Task on Benchmarking LLMs on Arabic and Islamic Culture
Fakhraddin Alwajih, Abdellah El Mekki, Hamdy Mubarak, Majd Hawasly, Abubakr Mohamed, Muhammad Abdul-Mageed
https://arxiv.org/abs/2509.02550

PalmX 2025: The First Shared Task on Benchmarking LLMs on Arabic and Islamic Culture
Large Language Models (LLMs) inherently reflect the vast data distributions they encounter during their pre-training phase. As this data is predominantly sourced from the web, there is a high chance it will be skewed towards high-resourced languages and cultures, such as those of the West. Consequently, LLMs often exhibit a diminished understanding of certain communities, a gap that is particularly evident in their knowledge of Arabic and Islamic cultures. This issue becomes even more pronounce…

MuRating: A High Quality Data Selecting Approach to Multilingual Large Language Model Pretraining
Zhixun Chen, Ping Guo, Wenhan Han, Yifan Zhang, Binbin Liu, Haobin Lin, Fengze Liu, Yan Zhao, Bingni Zhang, Taifeng Wang, Yin Zheng, Meng Fang
https://arxiv.org/abs/2507.01785

MuRating: A High Quality Data Selecting Approach to Multilingual Large Language Model Pretraining
Data quality is a critical driver of large language model performance, yet existing model-based selection methods focus almost exclusively on English. We introduce MuRating, a scalable framework that transfers high-quality English data-quality signals into a single rater for 17 target languages. MuRating aggregates multiple English "raters" via pairwise comparisons to learn unified document-quality scores,then projects these judgments through translation to train a multilingual evaluator on mon…

It's All About In-Context Learning! Teaching Extremely Low-Resource Languages to LLMs
Yue Li, Zhixue Zhao, Carolina Scarton
https://arxiv.org/abs/2508.19089 https://

It's All About In-Context Learning! Teaching Extremely Low-Resource Languages to LLMs
Extremely low-resource languages, especially those written in rare scripts, as shown in Figure 1, remain largely unsupported by large language models (LLMs). This is due in part to compounding factors such as the lack of training data. This paper delivers the first comprehensive analysis of whether LLMs can acquire such languages purely via in-context learning (ICL), with or without auxiliary alignment signals, and how these methods compare to parameter-efficient fine-tuning (PEFT). We systemat…

chDzDT: Word-level morphology-aware language model for Algerian social media text
Abdelkrime Aries
https://arxiv.org/abs/2509.01772 https://arxiv.org/pdf/2…

chDzDT: Word-level morphology-aware language model for Algerian social media text
Pre-trained language models (PLMs) have substantially advanced natural language processing by providing context-sensitive text representations. However, the Algerian dialect remains under-represented, with few dedicated models available. Processing this dialect is challenging due to its complex morphology, frequent code-switching, multiple scripts, and strong lexical influences from other languages. These characteristics complicate tokenization and reduce the effectiveness of conventional word-…