Tootfinder

PhantomLint: Principled Detection of Hidden LLM Prompts in Structured Documents
Toby Murray
https://arxiv.org/abs/2508.17884 https://arxiv.org/pdf/2508.178…

PhantomLint: Principled Detection of Hidden LLM Prompts in Structured Documents
Hidden LLM prompts have appeared in online documents with increasing frequency. Their goal is to trigger indirect prompt injection attacks while remaining undetected from human oversight, to manipulate LLM-powered automated document processing systems, against applications as diverse as résumé screeners through to academic peer review processes. Detecting hidden LLM prompts is therefore important for ensuring trust in AI-assisted human decision making. This paper presents the first principl…

Background Prompt for Few-Shot Out-of-Distribution Detection
Songyue Cai, Zongqian Wu, Yujie Mo, Liang Peng, Ping Hu, Xiaoshuang Shi, Xiaofeng Zhu
https://arxiv.org/abs/2509.21055

Background Prompt for Few-Shot Out-of-Distribution Detection
Existing foreground-background (FG-BG) decomposition methods for the few-shot out-of-distribution (FS-OOD) detection often suffer from low robustness due to over-reliance on the local class similarity and a fixed background patch extraction strategy. To address these challenges, we propose a new FG-BG decomposition framework, namely Mambo, for FS-OOD detection. Specifically, we propose to first learn a background prompt to obtain the local background similarity containing both the background an…

Sense of Self and Time in Borderline Personality. A Comparative Robustness Study with Generative AI
Marcin Moskalewicz, Anna Sterna, Marek Pokropski, Paula Flores
https://arxiv.org/abs/2508.19008

Sense of Self and Time in Borderline Personality. A Comparative Robustness Study with Generative AI
This study examines the capacity of large language models (LLMs) to support phenomenological qualitative analysis of first-person experience in Borderline Personality Disorder (BPD), understood as a disorder of temporality and selfhood. Building on a prior human-led thematic analysis of 24 inpatients' life-story interviews, we compared three LLMs (OpenAI GPT-4o, Google Gemini 2.5 Pro, Anthropic Claude Opus 4) prompted to mimic the interpretative style of the original investigators. The models w…

Happy Birthday, Linux!
🎁🎂🎈 🥳
I first installed Linux on my computer many months after that announcement, in December 1992. I have memories of swapping an almost endless pack of floppy disks during the lengthy install at a Chaos Communication Congress in Hamburg, Germany. The album “Connected” by Stereo MC's was playing several times until I was finally greeted with a shell prompt.

Enabling Multi-Agent Systems as Learning Designers: Applying Learning Sciences to AI Instructional Design
Jiayi Wang, Ruiwei Xiao, Xinying Hou, John Stamper
https://arxiv.org/abs/2508.16659

Enabling Multi-Agent Systems as Learning Designers: Applying Learning Sciences to AI Instructional Design
K-12 educators are increasingly using Large Language Models (LLMs) to create instructional materials. These systems excel at producing fluent, coherent content, but often lack support for high-quality teaching. The reason is twofold: first, commercial LLMs, such as ChatGPT and Gemini which are among the most widely accessible to teachers, do not come preloaded with the depth of pedagogical theory needed to design truly effective activities; second, although sophisticated prompt engineering can …

Prompting with Sign Parameters for Low-resource Sign Language Instruction Generation
Md Tariquzzaman, Md Farhan Ishmam, Saiyma Sittul Muna, Md Kamrul Hasan, Hasan Mahmud
https://arxiv.org/abs/2508.16076

Prompting with Sign Parameters for Low-resource Sign Language Instruction Generation
Sign Language (SL) enables two-way communication for the deaf and hard-of-hearing community, yet many sign languages remain under-resourced in the AI space. Sign Language Instruction Generation (SLIG) produces step-by-step textual instructions that enable non-SL users to imitate and learn SL gestures, promoting two-way interaction. We introduce BdSLIG, the first Bengali SLIG dataset, used to evaluate Vision Language Models (VLMs) (i) on under-resourced SLIG tasks, and (ii) on long-tail visual c…

It's mysterious to me that micropayments, assumed to be essential for the future of the web prior to the dotcom crash, just fizzled out when advertising arrived.
We now have the relative friction of micropayments (captchas, cookie warnings, cryptographic challenges, prompts to switch off ad-blockers, age verification) without also providing the means to support services.

A State-Update Prompting Strategy for Efficient and Robust Multi-turn Dialogue
Ziyi Liu
https://arxiv.org/abs/2509.17766 https://arxiv.org/pdf/2509.17766…

A State-Update Prompting Strategy for Efficient and Robust Multi-turn Dialogue
Large Language Models (LLMs) struggle with information forgetting and inefficiency in long-horizon, multi-turn dialogues. To address this, we propose a training-free prompt engineering method, the State-Update Multi-turn Dialogue Strategy. It utilizes "State Reconstruction" and "History Remind" mechanisms to effectively manage dialogue history. Our strategy shows strong performance across multiple multi-hop QA datasets. For instance, on the HotpotQA dataset, it improves the core information fil…

Google says the median Gemini app text prompt consumes 0.24Wh of energy, about the same as running a microwave for a second, and emits 0.03g of CO2 equivalent (Casey Crownhart/MIT Technology Review)
https://www.technologyreview.com/2025/08/21/1122288/google-gemin…

In a first, Google has released data on how much energy an AI prompt uses
It’s the most transparent estimate yet from one of the big AI companies, and a long-awaited peek behind the curtain for researchers.

Extension of Vertical Equilibrium Model for Two-Phase Displacement in Layer-Cake Reservoirs: Accounting for Water-CO2 Partial Miscibility and Fines Migration
Kofi Ohemeng Kyei Prempeh (School of Chemical Engineering, University of Adelaide, Australia), Pavel Bedrikovetsky (School of Chemical Engineering, University of Adelaide, Australia), Rouhi Farajzadeh (Shell Global Solutions International, The Hague, The Netherlands, Faculty of Civil Engineering and Geosciences, Delft University o…

Extension of Vertical Equilibrium Model for Two-Phase Displacement in Layer-Cake Reservoirs: Accounting for Water-CO2 Partial Miscibility and Fines Migration
Numerical simulations of geological CO2 storage in deep saline aquifers have demonstrated that vertical equilibrium (VE) models offer a robust and computationally efficient framework for reservoir optimization and upscaling. These studies emphasize the influence of fines migration and partial miscibility between water and CO2 on the evolving storage behaviour. Specifically, capillary-driven mobilization of clay and silica fines can impair injectivity, while water evaporation into the CO2 phase …