Zobrazeno 1 - 10
of 46
pro vyhledávání: '"AMERSHI, SALEEMA"'
Autor:
Fourney, Adam, Bansal, Gagan, Mozannar, Hussein, Tan, Cheng, Salinas, Eduardo, Erkang, Zhu, Niedtner, Friederike, Proebsting, Grace, Bassman, Griffin, Gerrits, Jack, Alber, Jacob, Chang, Peter, Loynd, Ricky, West, Robert, Dibia, Victor, Awadallah, Ahmed, Kamar, Ece, Hosn, Rafah, Amershi, Saleema
Modern AI agents, driven by advances in large foundation models, promise to enhance our productivity and transform our lives by augmenting our knowledge and capabilities. To achieve this vision, AI agents must effectively plan, perform multi-step rea
Externí odkaz:
http://arxiv.org/abs/2411.04468
Autor:
Dibia, Victor, Chen, Jingya, Bansal, Gagan, Syed, Suff, Fourney, Adam, Zhu, Erkang, Wang, Chi, Amershi, Saleema
Multi-agent systems, where multiple agents (generative AI models + tools) collaborate, are emerging as an effective pattern for solving long-running, complex tasks in numerous domains. However, specifying their parameters (such as models, tools, and
Externí odkaz:
http://arxiv.org/abs/2408.15247
Large language models (LLMs) can be used to generate text data for training and evaluating other models. However, creating high-quality datasets with LLMs can be challenging. In this work, we explore human-AI partnerships to facilitate high diversity
Externí odkaz:
http://arxiv.org/abs/2306.04140
Autor:
Buçinca, Zana, Pham, Chau Minh, Jakesch, Maurice, Ribeiro, Marco Tulio, Olteanu, Alexandra, Amershi, Saleema
While demands for change and accountability for harmful AI consequences mount, foreseeing the downstream effects of deploying AI systems remains a challenging task. We developed AHA! (Anticipating Harms of AI), a generative framework to assist AI pra
Externí odkaz:
http://arxiv.org/abs/2306.03280
Large language models are becoming increasingly pervasive and ubiquitous in society via deployment in sociotechnical systems. Yet these language models, be it for classification or generation, have been shown to be biased and behave irresponsibly, ca
Externí odkaz:
http://arxiv.org/abs/2304.09991
Autor:
Dibia, Victor, Fourney, Adam, Bansal, Gagan, Poursabzi-Sangdeh, Forough, Liu, Han, Amershi, Saleema
Large language models have demonstrated great potential to assist programmers in generating code. For such human-AI pair programming scenarios, we empirically demonstrate that while generated code is most often evaluated in terms of their functional
Externí odkaz:
http://arxiv.org/abs/2210.16494
Publikováno v:
2022 ACM Conference on Fairness, Accountability, and Transparency (FAccT '22), June 21-24, 2022, Seoul, Republic of Korea
Private companies, public sector organizations, and academic groups have outlined ethical values they consider important for responsible artificial intelligence technologies. While their recommendations converge on a set of central values, little is
Externí odkaz:
http://arxiv.org/abs/2205.07722
Autor:
Smith, Jessie J., Amershi, Saleema, Barocas, Solon, Wallach, Hanna, Vaughan, Jennifer Wortman
Transparency around limitations can improve the scientific rigor of research, help ensure appropriate interpretation of research findings, and make research claims more credible. Despite these benefits, the machine learning (ML) research community la
Externí odkaz:
http://arxiv.org/abs/2205.08363
Autor:
Simard, Patrice Y., Amershi, Saleema, Chickering, David M., Pelton, Alicia Edelman, Ghorashi, Soroush, Meek, Christopher, Ramos, Gonzalo, Suh, Jina, Verwey, Johan, Wang, Mo, Wernsing, John
The current processes for building machine learning systems require practitioners with deep knowledge of machine learning. This significantly limits the number of machine learning systems that can be created and has led to a mismatch between the dema
Externí odkaz:
http://arxiv.org/abs/1707.06742
Autor:
Amershi, Saleema Amin
Traditional approaches to developing user models, especially for computer-based learning environments, are notoriously difficult and time-consuming because they rely heavily on expert-elicited knowledge about the target application and domain. Furthe
Externí odkaz:
http://hdl.handle.net/2429/31622