Tootfinder

Absichtlich oder unabsichtlich trollt hier der Postillon die Mansplainerelite des Fediversums. Herrlich.
https://mastodon.social/@derpostillon/114829779655628148

Der Postillon 📯 (@derpostillon@mastodon.social)
Angehängt: 1 Bild Fakt des Tages Die besten Fakten als Buch 👉 https://shopillon.de/shop/buecher-magazine/faktillon-faktzination-tierwelt-100-unglaubliche-fakten-ueber-tiere/

There's a really charming movie from the '80s called "Saving Grace" starring Tom Conti as a young, newly installed #Pope who sends the Vatican into an uproar by going off on walkabout without telling them where he is.
In the movie his regnal name was Leo XIV, so I can't help but wonder whether the real world Leo XIV remembers that movie and thought, "Ha, why not…

From Ambiguity to Accuracy: The Transformative Effect of Coreference Resolution on Retrieval-Augmented Generation systems
Youngjoon Jang, Seongtae Hong, Junyoung Son, Sungjin Park, Chanjun Park, Heuiseok Lim
https://arxiv.org/abs/2507.07847

From Ambiguity to Accuracy: The Transformative Effect of Coreference Resolution on Retrieval-Augmented Generation systems
Retrieval-Augmented Generation (RAG) has emerged as a crucial framework in natural language processing (NLP), improving factual consistency and reducing hallucinations by integrating external document retrieval with large language models (LLMs). However, the effectiveness of RAG is often hindered by coreferential complexity in retrieved documents, introducing ambiguity that disrupts in-context learning. In this study, we systematically investigate how entity coreference affects both document re…

This https://arxiv.org/abs/2503.22315 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCY_…

Large Language Models Are Democracy Coders with Attitudes
Current political developments worldwide illustrate that research on democratic backsliding is as important as ever. A recent exchange in Political Science & Politics (2/2024) has highlighted again a fundamental challenge in this literature: the measurement of democracy. With many democracy indicators consisting of subjective assessments rather than factual observations, trends in democracy over time could be due to human biases in the coding of these indicators rather than empirical facts. In …

Der Liveblog vom Samstag zum Nachlesen
Nach Vorwürfen aus Moskau hat die Ukraine betont, am vereinbarten Gefangenenaustausch festhalten zu wollen. Der ukrainische Außenminister fordert mehr Druck auf Russland.
🔗 https://www.tagesschau.de/newstic…

Ukraine-Liveblog: ++ Kiew: Gefangenenaustausch "in kommenden Tagen" ++
Nach Vorwürfen aus Moskau hat die Ukraine betont, am vereinbarten Gefangenenaustausch festhalten zu wollen. Der ukrainische Außenminister fordert mehr Druck auf Russland. Die Entwicklungen im Liveblog.

Reinforcement Fine-Tuning for Reasoning towards Multi-Step Multi-Source Search in Large Language Models
Wentao Shi, Yiqing Shen
https://arxiv.org/abs/2506.08352

Reinforcement Fine-Tuning for Reasoning towards Multi-Step Multi-Source Search in Large Language Models
Large language models (LLMs) can face factual limitations when responding to time-sensitive queries about recent events that arise after their knowledge thresholds in the training corpus. Existing search-augmented approaches fall into two categories, each with distinct limitations: multi-agent search frameworks incur substantial computational overhead by separating search planning and response synthesis across multiple LLMs, while single-LLM tool-calling methods restrict themselves to sequentia…

from my link log —
Alan Kay did not invent object-oriented programming.
https://www.hillelwayne.com/post/alan-kay/
saved 2025-05-11 https://

Durch die anhaltende #Trockenheit und den schneearmen Winter sind die #Grundwasserstände in Zell im #Fichtelgebirge stark gesunken.
Bereits jetzt muss

I'm glad tjat it seems we're finally approaching the bet-hedging phase of the hype cycle.
#ai

Knowledge-Aware Self-Correction in Language Models via Structured Memory Graphs
Swayamjit Saha
https://arxiv.org/abs/2507.04625 https://

Knowledge-Aware Self-Correction in Language Models via Structured Memory Graphs
Large Language Models (LLMs) are powerful yet prone to generating factual errors, commonly referred to as hallucinations. We present a lightweight, interpretable framework for knowledge-aware self-correction of LLM outputs using structured memory graphs based on RDF triples. Without retraining or fine-tuning, our method post-processes model outputs and corrects factual inconsistencies via external semantic memory. We demonstrate the approach using DistilGPT-2 and show promising results on simpl…