Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Negreanu, Carina"'
Autor:
Murugadoss, Bhuvanashree, Poelitz, Christian, Drosos, Ian, Le, Vu, McKenna, Nick, Negreanu, Carina Suzana, Parnin, Chris, Sarkar, Advait
LLMs-as-a-judge is a recently popularized method which replaces human judgements in task evaluation (Zheng et al. 2024) with automatic evaluation using LLMs. Due to widespread use of RLHF (Reinforcement Learning from Human Feedback), state-of-the-art
Externí odkaz:
http://arxiv.org/abs/2408.08781
Publikováno v:
Proceedings of the 3rd Annual Meeting of the Symposium on Human-Computer Interaction for Work (CHIWORK 2024)
Generative AI tools can help users with many tasks. One such task is data analysis, which is notoriously challenging for non-expert end-users due to its expertise requirements, and where AI holds much potential, such as finding relevant data sources,
Externí odkaz:
http://arxiv.org/abs/2407.02903
Improving Steering and Verification in AI-Assisted Data Analysis with Interactive Task Decomposition
Autor:
Kazemitabaar, Majeed, Williams, Jack, Drosos, Ian, Grossman, Tovi, Henley, Austin, Negreanu, Carina, Sarkar, Advait
Publikováno v:
Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology (UIST 2024)
LLM-powered tools like ChatGPT Data Analysis, have the potential to help users tackle the challenging task of data analysis programming, which requires expertise in data processing, programming, and statistics. However, our formative study (n=15) unc
Externí odkaz:
http://arxiv.org/abs/2407.02651
Autor:
Barke, Shraddha, Poelitz, Christian, Negreanu, Carina Suzana, Zorn, Benjamin, Cambronero, José, Gordon, Andrew D., Le, Vu, Nouri, Elnaz, Polikarpova, Nadia, Sarkar, Advait, Slininger, Brian, Toronto, Neil, Williams, Jack
Large language models (LLMs) are rapidly replacing help forums like StackOverflow, and are especially helpful for non-professional programmers and end users. These users are often interested in data-centric tasks, such as spreadsheet manipulation and
Externí odkaz:
http://arxiv.org/abs/2402.11734
Autor:
Sarkar, Advait, Drosos, Ian, Deline, Rob, Gordon, Andrew D., Negreanu, Carina, Rintel, Sean, Williams, Jack, Zorn, Benjamin
Publikováno v:
Proceedings of the 34th Annual Conference of the Psychology of Programming Interest Group (PPIG 2023)
Generative AI, such as image generation models and large language models, stands to provide tremendous value to end-user programmers in creative and knowledge workflows. Current research methods struggle to engage end-users in a realistic conversatio
Externí odkaz:
http://arxiv.org/abs/2312.16633
Imagine a developer who can only change their last line of code, how often would they have to start writing a function from scratch before it is correct? Auto-regressive models for code generation from natural language have a similar limitation: they
Externí odkaz:
http://arxiv.org/abs/2310.17680
Autor:
Singh, Mukul, Cambronero, José, Gulwani, Sumit, Le, Vu, Negreanu, Carina, Nouri, Elnaz, Raza, Mohammad, Verbruggen, Gust
Formatting is an important property in tables for visualization, presentation, and analysis. Spreadsheet software allows users to automatically format their tables by writing data-dependent conditional formatting (CF) rules. Writing such rules is oft
Externí odkaz:
http://arxiv.org/abs/2310.17306
Autor:
Payan, Justin, Mishra, Swaroop, Singh, Mukul, Negreanu, Carina, Poelitz, Christian, Baral, Chitta, Roy, Subhro, Chakravarthy, Rasika, Van Durme, Benjamin, Nouri, Elnaz
With the evolution of Large Language Models (LLMs) we can solve increasingly more complex NLP tasks across various domains, including spreadsheets. This work investigates whether LLMs can generate code (Excel OfficeScripts, a TypeScript API for execu
Externí odkaz:
http://arxiv.org/abs/2310.14495
Autor:
Gordon, Andrew D., Negreanu, Carina, Cambronero, José, Chakravarthy, Rasika, Drosos, Ian, Fang, Hao, Mitra, Bhaskar, Richardson, Hannah, Sarkar, Advait, Simmons, Stephanie, Williams, Jack, Zorn, Ben
Users are increasingly being warned to check AI-generated content for correctness. Still, as LLMs (and other generative models) generate more complex output, such as summaries, tables, or code, it becomes harder for the user to audit or evaluate the
Externí odkaz:
http://arxiv.org/abs/2310.01297
String data is common in real-world datasets: 67.6% of values in a sample of 1.8 million real Excel spreadsheets from the web were represented as text. Systems that successfully clean such string data can have a significant impact on real users. Whil
Externí odkaz:
http://arxiv.org/abs/2308.10922