Tootfinder

China releases an AI model trained on "Xi Jinping Thought" and other official literature, initially in research testing, a source says before a wider launch (Financial Times)
https://t.co/ulIhw2jiGm

"My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models
Xinpeng Wang, Bolei Ma, Chengzhi Hu, Leon Weber-Genzel, Paul R\"ottger, Frauke Kreuter, Dirk Hovy, Barbara Plank
https://arxiv.org/abs/2402.14499

"My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models
The open-ended nature of language generation makes the evaluation of autoregressive large language models (LLMs) challenging. One common evaluation approach uses multiple-choice questions (MCQ) to limit the response space. The model is then evaluated by ranking the candidate answers by the log probability of the first token prediction. However, first-tokens may not consistently reflect the final response output, due to model's diverse response styles such as starting with "Sure" or refusing to …

HOLY SHIT! Fellas - run far, FAR away from this woman….😳
“Is It Reasonable To Expect My Future Husband To Propose To Me With A Ring Worth $800,000 To $1,000,000?”
https://digg.com/good-q…

Is It Reasonable To Expect My Future Husband To Propose To Me With A Ring Worth $800,000 To $1,000,000, And Other Advice Column Questions | Digg
This week, a young adult who wants a seven-figure engagement ring, a grandfather who gave his father’s skull to a grandchild and a husband angry that his wife stays out of his arguments with his sons.

MM-PhyRLHF: Reinforcement Learning Framework for Multimodal Physics Question-Answering
Avinash Anand, Janak Kapuriya, Chhavi Kirtani, Apoorv Singh, Jay Saraf, Naman Lal, Jatin Kumar, Adarsh Raj Shivam, Astha Verma, Rajiv Ratn Shah, Roger Zimmermann
https://arxiv.org/abs/2404.12926

MM-PhyRLHF: Reinforcement Learning Framework for Multimodal Physics Question-Answering
Recent advancements in LLMs have shown their significant potential in tasks like text summarization and generation. Yet, they often encounter difficulty while solving complex physics problems that require arithmetic calculation and a good understanding of concepts. Moreover, many physics problems include images that contain important details required to understand the problem's context. We propose an LMM-based chatbot to answer multimodal physics MCQs. For domain adaptation, we utilize the MM-P…

Selenskyj bittet um Hilfe gegen russische Gleitbomben
Der ukrainische Präsident Wolodymyr Selenskyj hat westliche Staaten um Hilfe gegen Angriffe mit Gleitbomben gebeten. Sie seien das wichtigste Instrument der russischen Luftangriffe. "Die Ukraine benötigt Systeme und Taktiken, die es uns ermöglichen, unsere Stellungen, unsere Städte und unsere Gemeinden vor diesen Bomben zu schützen", sagte er in …
🐦

Volodymyr Zelenskyy / Володимир Зеленський (@ZelenskyyUa) on X
I appreciate Sweden’s long-term support for Ukraine, which will strengthen everyone—not just Ukraine but Europe’s entire perimeter from the Baltics to the Black Sea and every region where Russian madmen may attempt to revise land or sea borders. Today, I also continued our

Succede ancora: un ospedale francese fermo a causa di un attacco informatico. Questa volta senza richiesta di riscatto
https://poliverso.org/display/0477a01e-6d752757-5e40f00df4323825
Succede ancora: un ospedale francese fermo a causa di un attacco …

This https://arxiv.org/abs/2403.16687 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCY_…

Investigation of the effectiveness of applying ChatGPT in Dialogic Teaching Using Electroencephalography
In recent years, the rapid development of artificial intelligence technology, especially the emergence of large language models (LLMs) such as ChatGPT, has presented significant prospects for application in the field of education. LLMs possess the capability to interpret knowledge, answer questions, and consider context, thus providing support for dialogic teaching to students. Therefore, an examination of the capacity of LLMs to effectively fulfill instructional roles, thereby facilitating stu…

A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students' Formative Assessment Responses in Science
Clayton Cohn, Nicole Hutchins, Tuan Le, Gautam Biswas
https://arxiv.org/abs/2403.14565

A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students' Formative Assessment Responses in Science
This paper explores the use of large language models (LLMs) to score and explain short-answer assessments in K-12 science. While existing methods can score more structured math and computer science assessments, they often do not provide explanations for the scores. Our study focuses on employing GPT-4 for automated assessment in middle school Earth Science, combining few-shot and active learning with chain-of-thought reasoning. Using a human-in-the-loop approach, we successfully score and provi…

Attacco informatico alla British Library: il ransomware Rhysida colpisce ancora
https://poliverso.org/display/0477a01e-b14c2a6e-082c73e1c32f422d
Attacco informatico alla British Library: il ransomware Rhysida colpisce ancora Il recente attacco infor…

Slicing and Dicing the Bits: CPU Design the Old Fashioned Way
https://poliverso.org/display/0477a01e-01bbb710-3012261f6e5b90a3
Slicing and Dicing the Bits: CPU Design the Old Fashioned Way Writing for Hackaday can be somewhat hazardous. Sure, we don…