Tootfinder

A private citizen will be punished for contempt of Parliament by the Canadian House of Commons by being "called to the bar" and admonished by the Speaker.
The guilty party is some CEO of some company that got a favourable contract for the ArriveCan app.
#CanPoli #CdnPoli

“Professors like me … should be part of the embodied change we seek: turning off our computers and phones, taking all our annual leave, refusing to answer emails out of hours and only scheduling meetings within work hours everyone—including colleagues with caring responsibilities—can make.” #HigherEducation

"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 …

Raiffeisen vorn dabei - So finanzieren westliche Banken Putins Kriegskassa #News #Nachrichten

This https://arxiv.org/abs/2401.10838 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csHC_…

Rambler: Supporting Writing With Speech via LLM-Assisted Gist Manipulation
Dictation enables efficient text input on mobile devices. However, writing with speech can produce disfluent, wordy, and incoherent text and thus requires heavy post-processing. This paper presents Rambler, an LLM-powered graphical user interface that supports gist-level manipulation of dictated text with two main sets of functions: gist extraction and macro revision. Gist extraction generates keywords and summaries as anchors to support the review and interaction with spoken text. LLM-assisted…