Search
130 resources
-
Josh Dzieza|Jun 20th, 2023|webpageJosh DziezaJun 20th, 2023
How many humans does it take to make tech seem human? Millions.
-
Raunak Chowdhuri, Neil Deshmukh, David D...|Jun 18th, 2023|webpageRaunak Chowdhuri, Neil Deshmukh, David D...Jun 18th, 2023
A new tool that blends your everyday work apps into one. It's the all-in-one workspace for you and your team
-
Ziyang Luo, Can Xu, Pu Zhao|Jun 14th, 2023|preprintZiyang Luo, Can Xu, Pu ZhaoJun 14th, 2023
Code Large Language Models (Code LLMs), such as StarCoder, have demonstrated exceptional performance in code-related tasks. However, most existing models are solely pre-trained on extensive raw code data without instruction fine-tuning. In this paper, we introduce WizardCoder, which empowers Code LLMs with complex instruction fine-tuning, by adapting the Evol-Instruct method to the domain of code. Through comprehensive experiments on four prominent code generation benchmarks, namely...
-
Jun 10th, 2023|blogPostJun 10th, 2023
-
Can Xu, Qingfeng Sun, Kai Zheng|Jun 10th, 2023|preprintCan Xu, Qingfeng Sun, Kai ZhengJun 10th, 2023
Training large language models (LLMs) with open-domain instruction following data brings colossal success. However, manually creating such instruction data is very time-consuming and labor-intensive. Moreover, humans may struggle to produce high-complexity instructions. In this paper, we show an avenue for creating large amounts of instruction data with varying levels of complexity using LLM instead of humans. Starting with an initial set of instructions, we use our proposed Evol-Instruct to...
-
Can Xu, Qingfeng Sun, Kai Zheng|Jun 10th, 2023|preprintCan Xu, Qingfeng Sun, Kai ZhengJun 10th, 2023
Training large language models (LLMs) with open-domain instruction following data brings colossal success. However, manually creating such instruction data is very time-consuming and labor-intensive. Moreover, humans may struggle to produce high-complexity instructions. In this paper, we show an avenue for creating large amounts of instruction data with varying levels of complexity using LLM instead of humans. Starting with an initial set of instructions, we use our proposed Evol-Instruct to...
-
EdArXiv|Jun 5th, 2023|reportEdArXivJun 5th, 2023
Algorithms and machine learning models are being used more frequently in educational settings, but there are concerns that they may discriminate against certain groups. While there is some research on algorithmic fairness, there are two main issues with the current research. Firstly, it often focuses on gender and race and ignores other groups. Secondly, studies often find algorithmic bias in educational models but don't explore ways to reduce it. This study evaluates three drop-out...
-
EdArXiv|Jun 5th, 2023|reportEdArXivJun 5th, 2023
Algorithms and machine learning models are being used more frequently in educational settings, but there are concerns that they may discriminate against certain groups. While there is some research on algorithmic fairness, there are two main issues with the current research. Firstly, it often focuses on gender and race and ignores other groups. Secondly, studies often find algorithmic bias in educational models but don't explore ways to reduce it. This study evaluates three drop-out...
-
Annenberg Institute at Brown...|Jun 3rd, 2023|reportAnnenberg Institute at Brown...Jun 3rd, 2023
Providing consistent, individualized feedback to teachers is essential for improving instruction but can be prohibitively resource-intensive in most educational contexts. We develop M-Powering Teachers, an automated tool based on natural language processing to give teachers feedback on their uptake of student contributions, a high-leverage dialogic teaching practice that makes students feel heard. We conduct a randomized controlled trial in an online computer science course (n=1,136...
-
EdArXiv|Jun 2nd, 2023|reportEdArXivJun 2nd, 2023
Coaching, which involves classroom observation and expert feedback, is a widespread and fundamental part of teacher training. However, the majority of teachers do not have access to consistent, high quality coaching due to limited resources and access to expertise. We explore whether generative AI could become a cost-effective complement to expert feedback by serving as an automated teacher coach. In doing so, we propose three teacher coaching tasks for generative AI: (A) scoring transcript...
-
EdArXiv|Jun 2nd, 2023|reportEdArXivJun 2nd, 2023
Coaching, which involves classroom observation and expert feedback, is a widespread and fundamental part of teacher training. However, the majority of teachers do not have access to consistent, high quality coaching due to limited resources and access to expertise. We explore whether generative AI could become a cost-effective complement to expert feedback by serving as an automated teacher coach. In doing so, we propose three teacher coaching tasks for generative AI: (A) scoring transcript...
-
EdArXiv|Jun 2nd, 2023|reportEdArXivJun 2nd, 2023
Coaching, which involves classroom observation and expert feedback, is a widespread and fundamental part of teacher training. However, the majority of teachers do not have access to consistent, high quality coaching due to limited resources and access to expertise. We explore whether generative AI could become a cost-effective complement to expert feedback by serving as an automated teacher coach. In doing so, we propose three teacher coaching tasks for generative AI: (A) scoring transcript...
-
Rose Wang, Dorottya Demszky|Jun 2nd, 2023|preprintRose Wang, Dorottya DemszkyJun 2nd, 2023
Coaching, which involves classroom observation and expert feedback, is a widespread and fundamental part of teacher training. However, the majority of teachers do not have access to consistent, high quality coaching due to limited resources and access to expertise. We explore whether generative AI could become a cost-effective complement to expert feedback by serving as an automated teacher coach. In doing so, we propose three teacher coaching tasks for generative AI: (A) scoring transcript...
-
Zach Tilton, John M. LaVelle, Tian Ford,...|Jun 14th, 2023|journalArticleZach Tilton, John M. LaVelle, Tian Ford,...Jun 14th, 2023
Advancements in Artificial Intelligence (AI) signal a paradigmatic shift with the potential for transforming many various aspects of society, including evaluation education, with implications for subsequent evaluation practice. This article explores the potential implications of AI for evaluator and evaluation education. Specifically, the article discusses key issues in evaluation education including equitable language access to evaluation education, navigating program, social science, and...
-
May 31st, 2023|webpageMay 31st, 2023
Following the AI Roadmap suggestions for concrete activities aimed at aligning EU and U.S. risk-based approaches, a group of experts engaged to prepare an initial draft AI terminologies and taxonomies. A total number of 65 terms were identified with reference to key documents from the EU and the U.S.
-
Hannibal046|May 25th, 2023|computerProgramHannibal046May 25th, 2023
Awesome-LLM: a curated list of Large Language Model
-
Victoria Yaneva, Matthias Von Davier, Su...|May 25th, 2023|bookSectionVictoria Yaneva, Matthias Von Davier, Su...May 25th, 2023
-
Arjun Kharpal|May 24th, 2023|webpageArjun KharpalMay 24th, 2023
Artificial intelligence has been thrust into the center of conversations among policymakers grappling with what the tech should look like in the future.
-
Tim Dettmers, Artidoro Pagnoni, Ari Holt...|May 23rd, 2023|preprintTim Dettmers, Artidoro Pagnoni, Ari Holt...May 23rd, 2023
We present QLoRA, an efficient finetuning approach that reduces memory usage enough to finetune a 65B parameter model on a single 48GB GPU while preserving full 16-bit finetuning task performance. QLoRA backpropagates gradients through a frozen, 4-bit quantized pretrained language model into Low Rank Adapters~(LoRA). Our best model family, which we name Guanaco, outperforms all previous openly released models on the Vicuna benchmark, reaching 99.3% of the performance level of ChatGPT while...
-
Yang Liu, Dan Iter, Yichong Xu|May 23rd, 2023|preprintYang Liu, Dan Iter, Yichong XuMay 23rd, 2023
The quality of texts generated by natural language generation (NLG) systems is hard to measure automatically. Conventional reference-based metrics, such as BLEU and ROUGE, have been shown to have relatively low correlation with human judgments, especially for tasks that require creativity and diversity. Recent studies suggest using large language models (LLMs) as reference-free metrics for NLG evaluation, which have the benefit of being applicable to new tasks that lack human references....