Tootfinder

Early Approaches to Adversarial Fine-Tuning for Prompt Injection Defense: A 2022 Study of GPT-3 and Contemporary Models
Gustavo Sandoval, Denys Fenchenko, Junyao Chen
https://arxiv.org/abs/2509.14271

Early Approaches to Adversarial Fine-Tuning for Prompt Injection Defense: A 2022 Study of GPT-3 and Contemporary Models
This paper documents early research conducted in 2022 on defending against prompt injection attacks in large language models, providing historical context for the evolution of this critical security domain. This research focuses on two adversarial attacks against Large Language Models (LLMs): prompt injection and goal hijacking. We examine how to construct these attacks, test them on various LLMs, and compare their effectiveness. We propose and evaluate a novel defense technique called Adversar…

An EFT study of the $pp \to \bar{t} t Z(ll) h(bb)$ process at the FCC-$\boldsymbol{hh}$
Shankha Banerjee, Rick S. Gupta, Shilpi Jain, Michelangelo Mangano, Elena Venturini
https://arxiv.org/abs/2509.10449

An EFT study of the $pp \to \bar{t} t Z(ll) h(bb)$ process at the FCC-$\boldsymbol{hh}$
We carry out an Effective Field Theory (EFT) study of the $pp \to \bar{t} t Zh$ process in the $4b + 3 \ell + \ge 2j + \slashed{E}_T$ final state. This process can uniquely probe the $\bar{t} t Zh$ couplings arising from higher dimensional EFT operators and can also provide bounds on $\bar{t} t Z$ coupling deviations. We highlight the importance of the proposed proton-proton Future Circular Collider (FCC-$hh$) to study this process and then perform a complete collider analysis by examining the …

https://www.theatlantic.com/economy/archive/2025/08/billionaire-tax-study/683987/?gift=7dKtnNrILXcLLty1b9gh3izs2-QbznZFuAgjH23TfLc

How the Richest People in America Avoid Paying Taxes
A clever new paper puts concrete numbers to the taxes paid by members of the Forbes 400.

Challenges and Applications of Large Language Models: A Comparison of GPT and DeepSeek family of models
Shubham Sharma, Sneha Tuli, Narendra Badam
https://arxiv.org/abs/2508.21377

Challenges and Applications of Large Language Models: A Comparison of GPT and DeepSeek family of models
Large Language Models (LLMs) are transforming AI across industries, but their development and deployment remain complex. This survey reviews 16 key challenges in building and using LLMs and examines how these challenges are addressed by two state-of-the-art models with unique approaches: OpenAI's closed source GPT-4o (May 2024 update) and DeepSeek-V3-0324 (March 2025), a large open source Mixture-of-Experts model. Through this comparison, we showcase the trade-offs between closed source models …

Punctuation and Predicates in Language Models
Sonakshi Chauhan, Maheep Chaudhary, Koby Choy, Samuel Nellessen, Nandi Schoots
https://arxiv.org/abs/2508.14067 https://

Punctuation and Predicates in Language Models
In this paper we explore where information is collected and how it is propagated throughout layers in large language models (LLMs). We begin by examining the surprising computational importance of punctuation tokens which previous work has identified as attention sinks and memory aids. Using intervention-based techniques, we evaluate the necessity and sufficiency (for preserving model performance) of punctuation tokens across layers in GPT-2, DeepSeek, and Gemma. Our results show stark model-sp…