Tootfinder

The Hidden Threat in Plain Text: Attacking RAG Data Loaders
Alberto Castagnaro, Umberto Salviati, Mauro Conti, Luca Pajola, Simeone Pizzi
https://arxiv.org/abs/2507.05093

The Hidden Threat in Plain Text: Attacking RAG Data Loaders
Large Language Models (LLMs) have transformed human-machine interaction since ChatGPT's 2022 debut, with Retrieval-Augmented Generation (RAG) emerging as a key framework that enhances LLM outputs by integrating external knowledge. However, RAG's reliance on ingesting external documents introduces new vulnerabilities. This paper exposes a critical security gap at the data loading stage, where malicious actors can stealthily corrupt RAG pipelines by exploiting document ingestion. We propose a t…

Building Open-Retrieval Conversational Question Answering Systems by Generating Synthetic Data and Decontextualizing User Questions
Christos Vlachos, Nikolaos Stylianou, Alexandra Fiotaki, Spiros Methenitis, Elisavet Palogiannidi, Themos Stafylakis, Ion Androutsopoulos
https://arxiv.org/abs/2507.04884

Building Open-Retrieval Conversational Question Answering Systems by Generating Synthetic Data and Decontextualizing User Questions
We consider open-retrieval conversational question answering (OR-CONVQA), an extension of question answering where system responses need to be (i) aware of dialog history and (ii) grounded in documents (or document fragments) retrieved per question. Domain-specific OR-CONVQA training datasets are crucial for real-world applications, but hard to obtain. We propose a pipeline that capitalizes on the abundance of plain text documents in organizations (e.g., product documentation) to automatically …

#SeriouslyIfYoureStillUsingInternetExplorerYouShouldStop

In his keynote, Raphael Troncy is asking whether we should keep building knowledge graphs....taking into account 20 years of experience in building knowledge graphs
https://2025.eswc-conferences.org/keynotes-announcement-raphael-troncy/

This https://arxiv.org/abs/2504.09200 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csNI_…

A Datagram Extension to DNS over QUIC: Proven Resource Conservation in the Internet of Things
In this paper, we investigate the Domain Name System (DNS) over QUIC (DoQ) and propose a non-disruptive extension, which can greatly reduce DoQ's resource consumption. This extension can benefit all DNS clients - especially Internet of Things (IoT) devices. This is important because even resource-constrained IoT devices can generate dozens of DNS requests every hour. DNS is a crucial service that correlates IP addresses and domain names. It is traditionally sent as plain-text, favoring low-late…

An Afternoon in a Café ☕️
咖啡厅的下午 ☕️
📷 Pentax MX
🎞️Lucky SHD 400
buy me ☕️ ?/请我喝杯☕️？
#filmphotography

Yiding Cao Geld mit PayPal.Me senden
Folgen Sie dem Link PayPal.Me/dingsterdingster und geben Sie den Betrag ein. Es ist bequem und sicher. Sie haben noch kein PayPal-Konto? Kein Problem.

This https://arxiv.org/abs/2412.04338 has been replaced.
initial toot: https://mastoxiv.page/@ar…

Numerical Aspects of Large Deviations
An introduction to numerical large-deviation sampling is provided. First, direct biasing with a known distribution is explained. As simple example, the Bernoulli experiment is used throughout the text. Next, Markov chain Monte Carlo (MCMC) simulations are introduced. In particular, the Metropolis-Hastings algorithm is explained. As first implementation of MCMC, sampling of the plain Bernoulli model is shown. Next, an exponential bias is used for the same model, which allows one to obtain the ta…

This https://arxiv.org/abs/2506.00261 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

GPR: Empowering Generation with Graph-Pretrained Retriever
Graph retrieval-augmented generation (GRAG) places high demands on graph-specific retrievers. However, existing retrievers often rely on language models pretrained on plain text, limiting their effectiveness due to domain misalignment and structure ignorance. To address these challenges, we propose GPR, a graph-based retriever pretrained directly on knowledge graphs. GPR aligns natural language questions with relevant subgraphs through LLM-guided graph augmentation and employs a structure-aware…

fresh_webs: Freshwater stream webs
A set of 26 networks of trophic-level species interactions in streams in New Zealand, Maine and North Carolina. Networks include the identities of aquatic insect, algae and fish species and their trophic interactions. Excel and plain text adjacency matrices available; webs can be downloaded individually or as a group.
This network has 71 nodes and 148 edges.
Tags: Biological, Food web, Unweighted, Metadata

"The first medium for humor was plain text, as was the first age of the Internet. There are Usenet groups entirely dedicated to jokes, such as rec.humor.funny or alt.humor.best-of-usenet. It was through those pre-web media that some classics were published first, like the epic Bastard Operator From Hell (BOFH) series, or the DEC WARS! storyline, a parody of Star Wars adapted to the world of UNIX and VMS minicomputers."

An Afternoon in a Café ☕️
咖啡厅的下午 ☕️
📷 Pentax MX
🎞️Lucky SHD 400
buy me ☕️ ?/请我喝杯☕️？
#filmphotography

Yiding Cao Geld mit PayPal.Me senden
Folgen Sie dem Link PayPal.Me/dingsterdingster und geben Sie den Betrag ein. Es ist bequem und sicher. Sie haben noch kein PayPal-Konto? Kein Problem.

Starmer's Labour outdid the fucking Tories for supplying war criminals.
#IsraelIsATerroristState #BoycottIsrael #IsraeliWarCrimes

GPR: Empowering Generation with Graph-Pretrained Retriever
Xiaochen Wang, Zongyu Wu, Yuan Zhong, Xiang Zhang, Suhang Wang, Fenglong Ma
https://arxiv.org/abs/2506.00261

GPR: Empowering Generation with Graph-Pretrained Retriever
Graph retrieval-augmented generation (GRAG) places high demands on graph-specific retrievers. However, existing retrievers often rely on language models pretrained on plain text, limiting their effectiveness due to domain misalignment and structure ignorance. To address these challenges, we propose GPR, a graph-based retriever pretrained directly on knowledge graphs. GPR aligns natural language questions with relevant subgraphs through LLM-guided graph augmentation and employs a structure-aware…

KGMark: A Diffusion Watermark for Knowledge Graphs
Hongrui Peng, Haolang Lu, Yuanlong Yu, Weiye Fu, Kun Wang, Guoshun Nan
https://arxiv.org/abs/2505.23873 …

KGMark: A Diffusion Watermark for Knowledge Graphs
Knowledge graphs (KGs) are ubiquitous in numerous real-world applications, and watermarking facilitates protecting intellectual property and preventing potential harm from AI-generated content. Existing watermarking methods mainly focus on static plain text or image data, while they can hardly be applied to dynamic graphs due to spatial and temporal variations of structured data. This motivates us to propose KGMARK, the first graph watermarking framework that aims to generate robust, detectable…

Today i wrote a parser & import to convert some semi-structured plain text into 40 different newsletter issues for an upcoming newsletter relaunch. And also fixed the internal structure of some of the mail widgets we are using, and their HTML representation.

Luca Faloni Baseball Cap LINEN $ 220
Made in It;ay.
No logos on them
#Faloni
#noMAGA

fresh_webs: Freshwater stream webs
A set of 26 networks of trophic-level species interactions in streams in New Zealand, Maine and North Carolina. Networks include the identities of aquatic insect, algae and fish species and their trophic interactions. Excel and plain text adjacency matrices available; webs can be downloaded individually or as a group.
This network has 105 nodes and 343 edges.
Tags: Biological, Food web, Unweighted, Metadata

fresh_webs: Freshwater stream webs
A set of 26 networks of trophic-level species interactions in streams in New Zealand, Maine and North Carolina. Networks include the identities of aquatic insect, algae and fish species and their trophic interactions. Excel and plain text adjacency matrices available; webs can be downloaded individually or as a group.
This network has 71 nodes and 155 edges.
Tags: Biological, Food web, Unweighted, Metadata

In Mastodon, is it possible to search for posts that do *not* contain a specific hashtag? I don't mean full-text search, but plain old hashtag search only for absence of hashtag instead of presence. 🤔
#question #askMastodon #search #Mastodon #MastodonSearch