Tootfinder

A Comparative Approach to Assessing Linguistic Creativity of Large Language Models and Humans
Anca Dinu, Andra-Maria Florescu, Alina Resceanu
https://arxiv.org/abs/2507.12039

A Comparative Approach to Assessing Linguistic Creativity of Large Language Models and Humans
The following paper introduces a general linguistic creativity test for humans and Large Language Models (LLMs). The test consists of various tasks aimed at assessing their ability to generate new original words and phrases based on word formation processes (derivation and compounding) and on metaphorical language use. We administered the test to 24 humans and to an equal number of LLMs, and we automatically evaluated their answers using OCSAI tool for three criteria: Originality, Elaboration, …

Space-filling efficiency and optical properties of hemoglycin
Julie E M McGeoch, Malcolm W McGeoch
https://arxiv.org/abs/2507.10612 https://

Space-filling efficiency and optical properties of hemoglycin
The empty, extensive low-density lattice topology of hemoglycin is examined to understand how in space, and possibly as early as 800M years into cosmic time a rod-like polymer of glycine and iron came into dominance. A central question to be answered is whether the hemoglycin rod lattice with diamond 2H symmetry represents the most efficient covering of space by a regular arrangement of identical rods. Starting from the tetrahedral symmetry of every hemoglycin lattice vertex we find that the re…

I was reminded again why it takes more than a feeling to get #Connections right, even when the hurried, obvious answer is waiting there for you. I nearly bit the dust by falling for a barracuda of a red herring.
#Connections734
Puzzle № 734
🟩🟩🟩🟩
🟪🟪🟪🟪
🟦🟦🟦🟦
🟨🟨🟨🟨

Reykjavík Grapevine provides answers to questions you were too afraid to ask
https://grapevine.is/mag/2025/07/07/help-call-charlie-campsites-expensive-vegetables-beautiful-but-harmless-eruption-more/…

From Iceland — Help? Call Charlie! Campsites, Expensive Vegetables, Beautiful But Harmless Eruption & More
Unsolicited advice from an unreliable advisor Help is a four-letter verb meaning “to make it easier or possible for someone...

❝Think! Think! What do people love? The warmth of sunshine on their skin? Fresh fruit? The smell of the top of a baby’s head? Doritos? Laughter? Joy? The feeling of being seen? No, no! These answers are all wrong. It needs to be something that you can access after the Event!❞ https://

Hey you, hold onto your humanity. You’ll thank me later.
Columnist and alum Alexandra Petri offers a little advice for the graduates — or, at least, for one of them (you know who you are).

This https://arxiv.org/abs/2504.21059 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

A remark on the number of automorphisms of some algebraic structures
In these notes we look at the following question. Given a category $\mathcal C$ of algebraic structure (e.g. the category of groups, monoids, partial groups, ...) and a rational $r\in \mathbb Q$, does there exists an element $x\in \mathcal C$ such that the size of its automorphism group $\text{Aut}_{\mathcal C} (x)$ divided by the size of $x$ (whatever that would means) is equal to $r$\,? To our knowledge, this question was introduced by Tărnăuceanu in the category of groups. Here, we answer …

23andMe leadership grilled by lawmakers demanding answers about data security amid bankruptcy sale https://therecord.media/23andme-leadership-grilled-by-lawmakers-hearing

“Humans generally want to feel chosen and special, and some individuals will believe they are to an extraordinary degree.” —YDS Prof Yii-Jan Lin as quoted in Rolling Stone on A.I. and religious fervor. https://www.rollingstone.com/culture/cultu

People Are Finding Spiritual Fulfillment in AI. Religious Scholars Have Thoughts
People keep falling down rabbit holes of prophecy and spiritualism thanks to conversations with AI chatbots. Here's what religious scholars are saying.

Shifting from Ranking to Set Selection for Retrieval Augmented Generation
Dahyun Lee, Yongrae Jo, Haeju Park, Moontae Lee
https://arxiv.org/abs/2507.06838 …

Shifting from Ranking to Set Selection for Retrieval Augmented Generation
Retrieval in Retrieval-Augmented Generation(RAG) must ensure that retrieved passages are not only individually relevant but also collectively form a comprehensive set. Existing approaches primarily rerank top-k passages based on their individual relevance, often failing to meet the information needs of complex queries in multi-hop question answering. In this work, we propose a set-wise passage selection approach and introduce SETR, which explicitly identifies the information requirements of a q…

Generalizing Verifiable Instruction Following
Valentina Pyatkin, Saumya Malik, Victoria Graf, Hamish Ivison, Shengyi Huang, Pradeep Dasigi, Nathan Lambert, Hannaneh Hajishirzi
https://arxiv.org/abs/2507.02833

Generalizing Verifiable Instruction Following
A crucial factor for successful human and AI interaction is the ability of language models or chatbots to follow human instructions precisely. A common feature of instructions are output constraints like ``only answer with yes or no" or ``mention the word `abrakadabra' at least 3 times" that the user adds to craft a more useful answer. Even today's strongest models struggle with fulfilling such constraints. We find that most models strongly overfit on a small set of verifiable constraints from …