Tootfinder

OpenMedLM: Prompt engineering can out-perform fine-tuning in medical question-answering with open-source large language models
Jenish Maharjan, Anurag Garikipati, Navan Preet Singh, Leo Cyrus, Mayank Sharma, Madalina Ciobanu, Gina Barnes, Rahul Thapa, Qingqing Mao, Ritankar Das
https://arxiv.org/abs/2402.19371

OpenMedLM: Prompt engineering can out-perform fine-tuning in medical question-answering with open-source large language models
LLMs have become increasingly capable at accomplishing a range of specialized-tasks and can be utilized to expand equitable access to medical knowledge. Most medical LLMs have involved extensive fine-tuning, leveraging specialized medical data and significant, thus costly, amounts of computational power. Many of the top performing LLMs are proprietary and their access is limited to very few research groups. However, open-source (OS) models represent a key area of growth for medical LLMs due to …

Explainable Automatic Grading with Neural Additive Models
Aubrey Condor, Zachary Pardos
https://arxiv.org/abs/2405.00489 https://arxi…

Explainable Automatic Grading with Neural Additive Models
The use of automatic short answer grading (ASAG) models may help alleviate the time burden of grading while encouraging educators to frequently incorporate open-ended items in their curriculum. However, current state-of-the-art ASAG models are large neural networks (NN) often described as "black box", providing no explanation for which characteristics of an input are important for the produced output. This inexplicable nature can be frustrating to teachers and students when trying to interpret,…

Aussage zu Atomwaffen: Tusk fordert von Duda Details
Polens Regierungschef Donald Tusk hat von Präsident Andrzej Duda weitere Details zu dessen Erklärung gefordert, Polen sei offen für die Stationierung von Atomwaffen. "Diese Idee ist sehr massiv und sehr ernst, würde ich sagen. Ich müsste alle Umstände kennen, die den Präsidenten dazu veranlasst haben, diese Erklärung abzugeben", sagte Tusk. Er wolle sich daher mit Duda tref…
📑

Ukraine-Liveblog: ++ Fernsehturm in Charkiw nach Angriff eingestürzt ++
Nach einem Angriff auf die ukrainische Stadt Charkiw ist dort ein Fernsehturm teilweise eingestürzt. Russland hat eigenen Angaben zufolge ein Dorf in der Ostukraine eingenommen. Die Entwicklungen vom Montag zum Nachlesen.

Allowing dignity in death to someone who has lived overseas for some time, but maintained close ties to family in WA is the right choice.
Everyone deserves dignity and respect at end of life.
Article here: https://www.abc.net.au/news/2024-04-24/is…

Can you still access voluntary assisted dying laws if you've been living elsewhere for a decade or more?
Can you still be a Western Australian resident and access the state's voluntary euthanasia process if you've spent most of the past 15 years living in Bali? The answer might surprise you.

Kaum ist bluesky offen für alle kippen die Sitten da Richtung twitter.
"Hey, guter Post, aber du hast da einen Fehler in deiner Aussage, damit machst du dich angreifbar."
"Oh danke Herr Oberlehrer. Bessere Idee. Ich hetze meine Follower auf dich und blocke dich..."

Abendessen heute: ein Gericht mit historischen russischen Wurzeln – »Passazhirsky-Salat« aus gebratenen Zwiebeln & Karotten, sauren Gurken und gebratener Leber. Alles in schmale Streifen geschnitten und mit etwas Mayonnaise angerichtet. »Nach Aussage vieler älterer Zeitgenossen wurde dieser Salat früher gern in Speisewagen von Fernverkehrszügen und auf Bahnhöfen serviert. Er war leicht vorzubereiten und aufzubewahren, schmackhaft und gesund.«
Gefällt mir sehr gut.

Explainable Automatic Grading with Neural Additive Models
Aubrey Condor, Zachary Pardos
https://arxiv.org/abs/2405.00489 https://arxi…

Explainable Automatic Grading with Neural Additive Models
The use of automatic short answer grading (ASAG) models may help alleviate the time burden of grading while encouraging educators to frequently incorporate open-ended items in their curriculum. However, current state-of-the-art ASAG models are large neural networks (NN) often described as "black box", providing no explanation for which characteristics of an input are important for the produced output. This inexplicable nature can be frustrating to teachers and students when trying to interpret,…

This https://arxiv.org/abs/2309.09973 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Coloring and density theorems for configurations of a given volume
This is a treatise on finite point configurations spanning a fixed volume to be found in a single color-class of an arbitrary finite (measurable) coloring of the Euclidean space $\mathbb{R}^n$, or in a single large measurable subset $A\subseteq\mathbb{R}^n$. More specifically, we study vertex-sets of simplices, rectangular boxes, and parallelotopes, attempting to make progress on several open problems posed in the 1970s and the 1980s. As one of the highlights, we give the negative answer to a q…

The Generative AI Paradox on Evaluation: What It Can Solve, It May Not Evaluate
Juhyun Oh, Eunsu Kim, Inha Cha, Alice Oh
https://arxiv.org/abs/2402.06204 h…

The Generative AI Paradox on Evaluation: What It Can Solve, It May Not Evaluate
This paper explores the assumption that Large Language Models (LLMs) skilled in generation tasks are equally adept as evaluators. We assess the performance of three LLMs and one open-source LM in Question-Answering (QA) and evaluation tasks using the TriviaQA (Joshi et al., 2017) dataset. Results indicate a significant disparity, with LLMs exhibiting lower performance in evaluation tasks compared to generation tasks. Intriguingly, we discover instances of unfaithful evaluation where models accu…