Tootfinder

Cioè, gli Uncle Acid & The Deadbeats tornano con un nuovo disco dopo sei anni di silenzio e cos'è? La colonna sonora di un immaginario film poliziottesco/giallo italiano degli anni Settanta con dialoghi originali di Edwige Fenech e Franco Nero :0520:
Mannaggia alle fisse
http…

Uncle Acid & The Deadbeats are back, announce first album in six years
Inspired by '70s Italian cinema, 'Nell' Ora Blu' will be out May 10

With departure of Bryce Huff, how will Jets replace sack leaders' production? https://www.espn.com/nfl/story/_/id/39710166/bryce-huff-departure-new-york-jets-sack-leader-free-agency

Will the Jets be able to replace Bryce Huff's sack production? - ESPN
Huff led New York with 10 sacks last year, but he will be in Philadelphia next season with the Jets left looking for answers.

In 2021, the Boston Globe editorial board asked: “♦️Who owns the president?♦️”
It’s a reasonable question. We didn’t know the answer then. We still don’t.
Three years later, we have more than a half-billion reasons to ask that question.
Were he to be re-elected, his legal #debts would be a #national

InfiCoder-Eval: Systematically Evaluating the Question-Answering Capabilities of Code Large Language Models
Linyi Li, Shijie Geng, Zhenwen Li, Yibo He, Hao Yu, Ziyue Hua, Guanghan Ning, Siwei Wang, Tao Xie, Hongxia Yang
https://arxiv.org/abs/2404.07940

InfiCoder-Eval: Systematically Evaluating the Question-Answering Capabilities of Code Large Language Models
Large Language Models for understanding and generating code (code LLMs) have witnessed tremendous progress in recent years. With the rapid development of code LLMs, many popular evaluation benchmarks, such as HumanEval, DS-1000, and MBPP, have emerged to measure the performance of code LLMs with a particular focus on code generation tasks. However, they are insufficient to cover the full range of expected capabilities of code LLMs, which span beyond code generation to answering diverse coding-r…

He was born and raised in my home town. 😢 I loved the MacNeil Lehrer Report, even as a kid. RIP
https://press.coop/@nytimes/112259174425989704

The New York Times :press: (@nytimes@press.coop)
Attached: 1 image Robert MacNeil, Earnest News Anchor for PBS, Dies at 93 With his longtime co-host Jim Lehrer, he delivered thoughtful reports that stood in stark contrast to the commercial networks’ ever more sensational newscasts. #press https://www.nytimes.com/2024/04/12/business/media/robert-macneil-dead.html?utm_source=press.coop

“Unlike Google which took years to make its search really shitty, OpenAI plans to have outright false search results and dangerous answers to health questions from day one.”
https://www.reuters.com/technology/openai-…

OpenAI plans to announce Google search competitor on Monday, sources say
OpenAI plans to announce its artificial intelligence-powered search product on Monday, according to two sources familiar with the matter, raising the stakes in its competition with search king Google.

Improving Retrieval for RAG based Question Answering Models on Financial Documents
Spurthi Setty, Katherine Jijo, Eden Chung, Natan Vidra
https://arxiv.org/abs/2404.07221

Improving Retrieval for RAG based Question Answering Models on Financial Documents
The effectiveness of Large Language Models (LLMs) in generating accurate responses relies heavily on the quality of input provided, particularly when employing Retrieval Augmented Generation (RAG) techniques. RAG enhances LLMs by sourcing the most relevant text chunk(s) to base queries upon. Despite the significant advancements in LLMs' response quality in recent years, users may still encounter inaccuracies or irrelevant answers; these issues often stem from suboptimal text chunk retrieval by …

This https://arxiv.org/abs/2403.05326 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

ChatASU: Evoking LLM's Reflexion to Truly Understand Aspect Sentiment in Dialogues
Aspect Sentiment Understanding (ASU) in interactive scenarios (e.g., Question-Answering and Dialogue) has attracted ever-more interest in recent years and achieved important progresses. However, existing studies on interactive ASU largely ignore the coreference issue for opinion targets (i.e., aspects), while this phenomenon is ubiquitous in interactive scenarios especially dialogues, limiting the ASU performance. Recently, large language models (LLMs) shows the powerful ability to integrate va…

Tech Progress 🤣
@…
https://hachyderm.io/@thomasfuchs/112419203289198873