Tootfinder

The Impact of Language Mixing on Bilingual LLM Reasoning
Yihao Li, Jiayi Xin, Miranda Muqing Miao, Qi Long, Lyle Ungar
https://arxiv.org/abs/2507.15849 htt…

The Impact of Language Mixing on Bilingual LLM Reasoning
Proficient multilingual speakers often intentionally switch languages in the middle of a conversation. Similarly, recent reasoning-focused bilingual large language models (LLMs) with strong capabilities in both languages exhibit language mixing--alternating languages within their chain of thought. Discouraging this behavior in DeepSeek-R1 was found to degrade accuracy, suggesting that language mixing may benefit reasoning. In this work, we study language switching in Chinese-English bilingual r…

Please remember to flag the correct language on your Mastodon posts! Otherwise, everyone else's language filtering doesn't work.
Signed, someone who doesn't want to keep seeing posts in languages he can't understand and therefore gets no value from.
#Mastodon #Language

Telegram expands access to its TON crypto wallet, integrated into the Telegram app, for its 87M users in the US (Amanda Silberling/TechCrunch)
https://techcrunch.com/2025/07/22/telegrams-crypto-wallet-launches-in-the-us/

Telegram's crypto wallet launches in the US | TechCrunch
Telegram is expanding access to its crypto wallet for its 87 million users in the US.

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

Third Way has a point; jargon is often off-putting, making it sound like the language evangelicals use, the 'insider' language that differentiates between 'us' and 'them'
The ‘woke’ words Democrats should cut from their vocabulary - POLITICO
https://www.politico.com/news/2025/08/22/democrats-woke-language-blacklist-00519421

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

How important is language for human-like intelligence?
Gary Lupyan, Hunter Gentry, Martin Zettersten
https://arxiv.org/abs/2509.15560 https://arxiv.org/pdf…

How important is language for human-like intelligence?
We use language to communicate our thoughts. But is language merely the expression of thoughts, which are themselves produced by other, nonlinguistic parts of our minds? Or does language play a more transformative role in human cognition, allowing us to have thoughts that we otherwise could (or would) not have? Recent developments in artificial intelligence (AI) and cognitive science have reinvigorated this old question. We argue that language may hold the key to the emergence of both more gene…

Vivo demos Vivo Vision, its first MR headset, which looks like an Apple Vision Pro clone but is ~40% lighter with micro-OLED displays, and could cost ~$1,400 (David Heaney/UploadVR)
https://www.uploadvr.com/vivo-vision-discovery-edition-launches-as-store-demo/

Vivo Vision Is 40% Lighter Than Apple Vision Pro & "Could" Be 1/3 The Price
China's Vivo Vision is 40% lighter than Apple Vision Pro, and "could" be one third the price. But for now, it's just an in-store demo, not a product.

A Study of Privacy-preserving Language Modeling Approaches
Pritilata Saha, Abhirup Sinha
https://arxiv.org/abs/2508.15421 https://arxiv.org/pdf/2508.15421

A Study of Privacy-preserving Language Modeling Approaches
Recent developments in language modeling have increased their use in various applications and domains. Language models, often trained on sensitive data, can memorize and disclose this information during privacy attacks, raising concerns about protecting individuals' privacy rights. Preserving privacy in language models has become a crucial area of research, as privacy is one of the fundamental human rights. Despite its significance, understanding of how much privacy risk these language models p…

Evaluating Multilingual and Code-Switched Alignment in LLMs via Synthetic Natural Language Inference
Samir Abdaljalil, Erchin Serpedin, Khalid Qaraqe, Hasan Kurban
https://arxiv.org/abs/2508.14735

Evaluating Multilingual and Code-Switched Alignment in LLMs via Synthetic Natural Language Inference
Large language models (LLMs) are increasingly applied in multilingual contexts, yet their capacity for consistent, logically grounded alignment across languages remains underexplored. We present a controlled evaluation framework for multilingual natural language inference (NLI) that generates synthetic, logic-based premise-hypothesis pairs and translates them into a typologically diverse set of languages. This design enables precise control over semantic relations and allows testing in both mon…