Tootfinder

AngryGF: KI-Chatbot für Männer soll beim Umgang mit wütender Freundin helfen
Die KI-Chat-App "AngryGF" will Männer helfen, wütende Freundinnen zu beruhigen. Ein Übungsszenario lautet: "Mutter zuerst aus dem Fluss gerettet".

AngryGF: KI-Chatbot für Männer soll beim Umgang mit wütender Freundin helfen
Die KI-Chat-App "AngryGF" will Männer helfen, wütende Freundinnen zu beruhigen. Ein Übungsszenario lautet: "Mutter zuerst aus dem Fluss gerettet".

Using #PHP arrays as pseudo-objects is almost never the right answer. They're less self-documenting, slower, worse on memory, and more bug prone.
https://peakd.com/php/@crell/php-use-a

Using #PHP arrays as pseudo-objects is almost never the right answer. They're less self-documenting, slower, worse on memory, and more bug prone.
https://peakd.com/php/@crell/php-use-a

When to Retrieve: Teaching LLMs to Utilize Information Retrieval Effectively
Tiziano Labruna, Jon Ander Campos, Gorka Azkune
https://arxiv.org/abs/2404.19705 https://arxiv.org/pdf/2404.19705
arXiv:2404.19705v1 Announce Type: new
Abstract: In this paper, we demonstrate how Large Language Models (LLMs) can effectively learn to use an off-the-shelf information retrieval (IR) system specifically when additional context is required to answer a given question. Given the performance of IR systems, the optimal strategy for question answering does not always entail external information retrieval; rather, it often involves leveraging the parametric memory of the LLM itself. Prior research has identified this phenomenon in the PopQA dataset, wherein the most popular questions are effectively addressed using the LLM's parametric memory, while less popular ones require IR system usage. Following this, we propose a tailored training approach for LLMs, leveraging existing open-domain question answering datasets. Here, LLMs are trained to generate a special token, , when they do not know the answer to a question. Our evaluation of the Adaptive Retrieval LLM (Adapt-LLM) on the PopQA dataset showcases improvements over the same LLM under three configurations: (i) retrieving information for all the questions, (ii) using always the parametric memory of the LLM, and (iii) using a popularity threshold to decide when to use a retriever. Through our analysis, we demonstrate that Adapt-LLM is able to generate the token when it determines that it does not know how to answer a question, indicating the need for IR, while it achieves notably high accuracy levels when it chooses to rely only on its parametric memory.

This https://arxiv.org/abs/2310.16605 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

WebDRO: A Web-based Group-level Clustering and Reweighting Method for Unsupervised Dense Retrieval
The anchor-document data derived from web graphs offers a wealth of paired information for training dense retrieval models in an unsupervised manner. However, the presence of inherent noise invariably compromises the robustness of training dense retrieval models, consequently hurting the performance. In this paper, we introduce WebDRO, an efficient approach for clustering the web graph data and optimizing group weights to enhance the robustness of the pretraining process of dense retrieval mode…

Information Theory and Direction Selectivity
Aman Chawla
https://arxiv.org/abs/2404.02915 https://arxiv.org/pdf/2404.02915

Information Theory and Direction Selectivity
In this brief paper, the authors study the tuning curves of starburst amacrine cells (SACs) and introduce a quantity called the irresolution or ambiguity of a SAC. They show that the rate of data generated by a starburst amacrine cell is inversely proportional to its irresolution. This is done by providing bounds on the rate required to encode the generated data. This technique can be applied to different cell types with different tuning curves. In this manner, information theoretic views can b…

Ah, a Lactationally-Transmitted Infection (or disease). LTI (or LTD)
https://www.statnews.com/2024/04/30/h5n1-bird-flu-virus-cows-and-risk-to-people/

What we’re starting to learn about H5N1 in cows, and the risk to people
Questions about H5N1 for which there are pretty clear answers when it comes to birds are suddenly unsettled science in cows.

Memory-Augmented Generative Adversarial Transformers
Stephan Raaijmakers, Roos Bakker, Anita Cremers, Roy de Kleijn, Tom Kouwenhoven, Tessa Verhoef
https://arxiv.org/abs/2402.19218

Memory-Augmented Generative Adversarial Transformers
Conversational AI systems that rely on Large Language Models, like Transformers, have difficulty interweaving external data (like facts) with the language they generate. Vanilla Transformer architectures are not designed for answering factual questions with high accuracy. This paper investigates a possible route for addressing this problem. We propose to extend the standard Transformer architecture with an additional memory bank holding extra information (such as facts drawn from a knowledge ba…