Zobrazeno 1 - 10
of 15 055
pro vyhledávání: '"A. Wallach"'
Large language model (LLM) evaluations often assume there is a single correct response -- a gold label -- for each item in the evaluation corpus. However, some tasks can be ambiguous -- i.e., they provide insufficient information to identify a unique
Externí odkaz:
http://arxiv.org/abs/2411.13760
Autor:
Dow, P. Alex, Vaughan, Jennifer Wortman, Barocas, Solon, Atalla, Chad, Chouldechova, Alexandra, Wallach, Hanna
There are few principles or guidelines to ensure evaluations of generative AI (GenAI) models and systems are effective. To help address this gap, we propose a set of general dimensions that capture critical choices involved in GenAI evaluation design
Externí odkaz:
http://arxiv.org/abs/2411.12709
Autor:
Wallach, Hanna, Desai, Meera, Pangakis, Nicholas, Cooper, A. Feder, Wang, Angelina, Barocas, Solon, Chouldechova, Alexandra, Atalla, Chad, Blodgett, Su Lin, Corvi, Emily, Dow, P. Alex, Garcia-Gathright, Jean, Olteanu, Alexandra, Reed, Stefanie, Sheng, Emily, Vann, Dan, Vaughan, Jennifer Wortman, Vogel, Matthew, Washington, Hannah, Jacobs, Abigail Z.
Across academia, industry, and government, there is an increasing awareness that the measurement tasks involved in evaluating generative AI (GenAI) systems are especially difficult. We argue that these measurement tasks are highly reminiscent of meas
Externí odkaz:
http://arxiv.org/abs/2411.10939
Autor:
Wallach, Nolan R.
This paper, in particular, gives a complete proof of the direct integral version of the Whittaker Plancherel Theorem. The main emphasis is on certain Hilbert and Fr\'echet vector bundles over a space that has a submersion onto the tempered dual. This
Externí odkaz:
http://arxiv.org/abs/2410.23226
Autonomous and intelligent systems (AIS) facilitate a wide range of beneficial applications across a variety of different domains. However, technical characteristics such as unpredictability and lack of transparency, as well as potential unintended c
Externí odkaz:
http://arxiv.org/abs/2404.13719
Autor:
Scott, Joan Wallach
Publikováno v:
Daedalus, 2024 Jul 01. 153(3), 149-165.
Externí odkaz:
https://www.jstor.org/stable/48784947
Autor:
Magooda, Ahmed, Helyar, Alec, Jackson, Kyle, Sullivan, David, Atalla, Chad, Sheng, Emily, Vann, Dan, Edgar, Richard, Palangi, Hamid, Lutz, Roman, Kong, Hongliang, Yun, Vincent, Kamal, Eslam, Zarfati, Federico, Wallach, Hanna, Bird, Sarah, Chen, Mei
We present a framework for the automated measurement of responsible AI (RAI) metrics for large language models (LLMs) and associated products and services. Our framework for automatically measuring harms from LLMs builds on existing technical and soc
Externí odkaz:
http://arxiv.org/abs/2310.17750
Fairness-related assumptions about what constitute appropriate NLG system behaviors range from invariance, where systems are expected to behave identically for social groups, to adaptation, where behaviors should instead vary across them. To illumina
Externí odkaz:
http://arxiv.org/abs/2310.15398
Shared automated mobility-on-demand promises efficient, sustainable, and flexible transportation. Nevertheless, security concerns, resilience, and their mutual influence - especially at night - will likely be the most critical barriers to public adop
Externí odkaz:
http://arxiv.org/abs/2308.02616
Autor:
Landau, Arie, Eduardus, Behar, Doron, Wallach, Eliana Ruth, Pašteka, Lukáš F., Faraji, Shirin, Borschevsky, Anastasia, Shagam, Yuval
Publikováno v:
J. Chem. Phys. 159, 114307 (2023)
Parity non-conservation (PNC) due to the weak interaction is predicted to give rise to enantiomer dependent vibrational constants in chiral molecules, but the phenomenon has so far eluded experimental observation. The enhanced sensitivity of molecule
Externí odkaz:
http://arxiv.org/abs/2306.09788