Tootfinder

Large Language Models for Toxic Language Detection in Low-Resource Balkan Languages
Amel Muminovic, Amela Kadric Muminovic
https://arxiv.org/abs/2506.09992

Large Language Models for Toxic Language Detection in Low-Resource Balkan Languages
Online toxic language causes real harm, especially in regions with limited moderation tools. In this study, we evaluate how large language models handle toxic comments in Serbian, Croatian, and Bosnian, languages with limited labeled data. We built and manually labeled a dataset of 4,500 YouTube and TikTok comments drawn from videos across diverse categories, including music, politics, sports, modeling, influencer content, discussions of sexism, and general topics. Four models (GPT-3.5 Turbo, G…

First Evidence of Potential Language-Like Communication in Dolphins: Study #AnimalRights

First Evidence of Potential Language-Like Communication in Dolphins: Study
Scientists with the Woods Hole Oceanographic Institution and partners have identified possible language-like communication among dolphins.

Meta launches V-JEPA 2, an open-source AI "world model" to understand and predict 3D environments and object movements, to help robotics and self-driving cars (Ryan Browne/CNBC)
https://www.cnbc.com/2025/06/11/meta-launc

Meta launches AI 'world model' to advance robotics, self-driving cars
Meta on Wednesday announced it's rolling out a new AI "world model" that can better understand the 3D environment and movements of physical objects.

Near-future rocket launches could slow ozone recovery: #launches would start harming the ozone layer – new research: https://theconversation.com/a-10-fold-increase-in-rocket-launches-would-start-harming-the-ozone-layer-new-research-257480

Former ABC News correspondent and anchor Terry Moran launches a Substack channel following his ouster from the news network (Glenn Garner/Deadline)
https://deadline.com/2025/06/terry-moran-launches-substack-abc-news-dismissal-1236431503/…

Terry Moran Launches Substack Channel To Continue “Important Work” After ABC News Dismissal
Following Terry Moran's unceremonious ousting from ABC News, the Emmy-winning anchor and reporter has already moved onto his next platform.

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

Linguine: A Natural-Language Programming Language with Formal Semantics and a Clean Compiler Pipeline
Lifan Hu
https://arxiv.org/abs/2506.08396 https://

Linguine: A Natural-Language Programming Language with Formal Semantics and a Clean Compiler Pipeline
Linguine is a natural-language-inspired programming language that enables users to write programs in a fluent, controlled subset of English while preserving formal semantics. The language introduces anaphoric constructs, such as pronoun variables (e.g., "it", "them"), that are statically resolved through referent-tracking analysis combined with a Hindley-Milner-style type system. Each pronoun is guaranteed to be unambiguous and well-typed at compile time. The Linguine compiler pipeline includ…

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 Emergence of Abstract Thought in Large Language Models Beyond Any Language
Yuxin Chen, Yiran Zhao, Yang Zhang, An Zhang, Kenji Kawaguchi, Shafiq Joty, Junnan Li, Tat-Seng Chua, Michael Qizhe Shieh, Wenxuan Zhang
https://arxiv.org/abs/2506.09890

The Emergence of Abstract Thought in Large Language Models Beyond Any Language
As large language models (LLMs) continue to advance, their capacity to function effectively across a diverse range of languages has shown marked improvement. Preliminary studies observe that the hidden activations of LLMs often resemble English, even when responding to non-English prompts. This has led to the widespread assumption that LLMs may "think" in English. However, more recent results showing strong multilingual performance, even surpassing English performance on specific tasks in other…

This https://arxiv.org/abs/2506.05850 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Cross-lingual Collapse: How Language-Centric Foundation Models Shape Reasoning in Large Language Models
We identify \textbf{Cross-lingual Collapse}, a systematic drift in which the chain-of-thought (CoT) of a multilingual language model reverts to its dominant pre-training language even when the prompt is expressed in a different language. Recent large language models (LLMs) with reinforcement learning with verifiable reward (RLVR) have achieved strong logical reasoning performances by exposing their intermediate reasoning traces, giving rise to large reasoning models (LRMs). However, the mechani…