Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Baldini, Ioana"'
The widespread use of large language models has brought up essential questions about the potential biases these models might learn. This led to the development of several metrics aimed at evaluating and mitigating these biases. In this paper, we firs
Externí odkaz:
http://arxiv.org/abs/2406.05918
Autor:
Achintalwar, Swapnaja, Garcia, Adriana Alvarado, Anaby-Tavor, Ateret, Baldini, Ioana, Berger, Sara E., Bhattacharjee, Bishwaranjan, Bouneffouf, Djallel, Chaudhury, Subhajit, Chen, Pin-Yu, Chiazor, Lamogha, Daly, Elizabeth M., DB, Kirushikesh, de Paula, Rogério Abreu, Dognin, Pierre, Farchi, Eitan, Ghosh, Soumya, Hind, Michael, Horesh, Raya, Kour, George, Lee, Ja Young, Madaan, Nishtha, Mehta, Sameep, Miehling, Erik, Murugesan, Keerthiram, Nagireddy, Manish, Padhi, Inkit, Piorkowski, David, Rawat, Ambrish, Raz, Orna, Sattigeri, Prasanna, Strobelt, Hendrik, Swaminathan, Sarathkrishna, Tillmann, Christoph, Trivedi, Aashka, Varshney, Kush R., Wei, Dennis, Witherspooon, Shalisha, Zalmanovici, Marcel
Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations. Due to several limiting factors surrounding LLMs (training cost, API access, data availability, etc.), it may not always be
Externí odkaz:
http://arxiv.org/abs/2403.06009
Autor:
Achintalwar, Swapnaja, Baldini, Ioana, Bouneffouf, Djallel, Byamugisha, Joan, Chang, Maria, Dognin, Pierre, Farchi, Eitan, Makondo, Ndivhuwo, Mojsilovic, Aleksandra, Nagireddy, Manish, Ramamurthy, Karthikeyan Natesan, Padhi, Inkit, Raz, Orna, Rios, Jesus, Sattigeri, Prasanna, Singh, Moninder, Thwala, Siphiwe, Uceda-Sosa, Rosario A., Varshney, Kush R.
The alignment of large language models is usually done by model providers to add or control behaviors that are common or universally understood across use cases and contexts. In contrast, in this article, we present an approach and architecture that
Externí odkaz:
http://arxiv.org/abs/2403.09704
The increasing size of large language models (LLMs) has introduced challenges in their training and inference. Removing model components is perceived as a solution to tackle the large model sizes, however, existing pruning methods solely focus on per
Externí odkaz:
http://arxiv.org/abs/2312.15398
Current datasets for unwanted social bias auditing are limited to studying protected demographic features such as race and gender. In this work, we introduce a comprehensive benchmark that is meant to capture the amplification of social bias, via sti
Externí odkaz:
http://arxiv.org/abs/2312.07492
Autor:
Sheppard, Brooklyn, Richter, Anna, Cohen, Allison, Smith, Elizabeth Allyn, Kneese, Tamara, Pelletier, Carolyne, Baldini, Ioana, Dong, Yue
Using novel approaches to dataset development, the Biasly dataset captures the nuance and subtlety of misogyny in ways that are unique within the literature. Built in collaboration with multi-disciplinary experts and annotators themselves, the datase
Externí odkaz:
http://arxiv.org/abs/2311.09443
Bias auditing of language models (LMs) has received considerable attention as LMs are becoming widespread. As such, several benchmarks for bias auditing have been proposed. At the same time, the rapid evolution of LMs can make these benchmarks irrele
Externí odkaz:
http://arxiv.org/abs/2305.12620
Autor:
Adam, Hammaad, Yang, Ming Ying, Cato, Kenrick, Baldini, Ioana, Senteio, Charles, Celi, Leo Anthony, Zeng, Jiaming, Singh, Moninder, Ghassemi, Marzyeh
Publikováno v:
Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society (AIES 2022)
Clinical notes are becoming an increasingly important data source for machine learning (ML) applications in healthcare. Prior research has shown that deploying ML models can perpetuate existing biases against racial minorities, as bias can be implici
Externí odkaz:
http://arxiv.org/abs/2205.03931
This paper evaluates synthetically generated healthcare data for biases and investigates the effect of fairness mitigation techniques on utility-fairness. Privacy laws limit access to health data such as Electronic Medical Records (EMRs) to preserve
Externí odkaz:
http://arxiv.org/abs/2203.04462
The use of machine learning (ML)-based language models (LMs) to monitor content online is on the rise. For toxic text identification, task-specific fine-tuning of these models are performed using datasets labeled by annotators who provide ground-trut
Externí odkaz:
http://arxiv.org/abs/2112.03529