Sign In

Ioana Baldini

Senior Research Scientist, Tech Lead for Generative Language Models Auditing and Red-Teaming - IBM Research AI

Professional Background

Ioana Baldini is an accomplished generalist researcher with extensive experience in applied natural language processing (NLP) and cloud infrastructure. Her professional journey has seen her excel in various prestigious roles, notably at IBM, where she held multiple positions over the years. With a focus on evaluating, analyzing, and improving generative language models, Ioana has made significant contributions to her field, utilizing her skills to uncover model failure and enhance product development. Her multi-disciplinary collaboration with research teams, combined with her ability to leverage real-world data, underscores her value in driving innovative advancements in technology and research.

Ioana’s tenure as a Senior Research Scientist at IBM is a testament to her expertise and commitment to excellence in her work. In this capacity, she engaged deeply with cutting-edge projects, ensuring that her findings were not only theoretically robust but also practically applicable in real-world scenarios. Her role as a Research Staff Member at IBM Research AI further solidified her reputation as a leader in the research community, where she was responsible for spearheading initiatives that pushed the boundaries of what is possible in NLP and machine learning.

Throughout her academic and professional career, Ioana has consistently shown a passion for research. Her experiences as a Graduate Research Intern at both IBM TJ Watson and Intel have equipped her with a versatile skill set that spans multiple domains of engineering and computer science.

Education and Achievements

Ioana's impressive educational background is a strong foundation for her achievements in the technology field. She earned her PhD in Electrical and Computer Engineering from the University of Toronto, where she further developed her expertise in advanced technologies and conducted pioneering research that contributes to her current work in natural language processing. Her thesis work focused on innovative methodologies for data evaluation, solidifying her interest in understanding how models function and where they may fail.

Prior to her doctoral studies, Ioana obtained her MASc in Computer Engineering from the University of Toronto, emphasizing her commitment to intellectual growth and technological advancement. She also holds a BSc in Computer Science and Engineering from the University POLITEHNICA of Bucharest, which laid the groundwork for her technical prowess and analytical abilities.

Throughout her academic career, Ioana has not only gained extensive knowledge in her field but also honed her practical skills through various research projects and collaborations. Her educational accomplishments highlight her determination to push the boundaries of knowledge and application in her area of expertise.

Notable Achievements

Dr. Ioana Baldini has made remarkable strides in her career, showcasing a blend of academic rigor and practical application. Her research endeavors have encompassed a range of topics, including but not limited to natural language processing, machine learning, and generative models, marking her as a thought leader in these areas. She has contributed to numerous publications, bringing insights into the complexities of machine learning paradigms and their implications in real-world applications.

A notable aspect of Ioana's career is her role in evaluating and analyzing model failures in generative language models. Her focused efforts in this area aim to refine and improve existing systems, helping to advance the technology and ensuring higher reliability in its applications. This analytical approach not only enhances the performance of generative models but also underscores Ioana's dedication to technological impact and innovation.

Additionally, her collaborations within multi-disciplinary teams have been instrumental in fostering a rich research environment that encourages the exchange of ideas and the development of groundbreaking solutions. Ioana's capacity to interface between different technical domains has made her a valuable asset in driving impactful research projects, making technology more accessible and effective for end-users.

In summary, Ioana Baldini is not just a researcher; she is a pioneer in her field with a wealth of knowledge and experience. Her background in computer engineering combined with her profound expertise in natural language processing positions her as an ideal candidate for leading innovative research initiatives in AI and machine learning. Whether working with complex models or engaging with diverse teams, Ioana continues to demonstrate the essence of a dedicated researcher, tirelessly seeking to enhance the field of technology through her work.

Highlights

Aug 8 · linkedin

There are many individual and group characteristics beyond the protected attributes usually considered in algorithmic fairness that are stigmatized and may lead to unwanted discrimination or other harms. If you'd like to test your LLM against a broader set of stigmas, you could use the SocialStigmaQA dataset that we recently open-sourced on Hugging Face https://lnkd.in/d7qyizce. The datasets builds on social sciences research on social stigmas (https://lnkd.in/dfsMRqw4) and includes 93 US-centric stigmas, such as facial scars and voluntarily childless.    The first version, which was peer-reviewed at AAAI 2024 https://lnkd.in/d-HGbi8k, is in English and based on American culture. The JA version, which we've also open-sourced on Hugging Face, is in Japanese and slightly adapted to the Japanese culture https://lnkd.in/dtEdgE6z.     Many thanks to the collaborators who made this work possible: Manish Nagireddy, Moninder Singh, Lamogha C., Ryo Iwaki , Mikio Takeuchi, Hiroshi Kanayama, and Gakuto KURATA, and to Kush Varshney for his support and encouragement.     Please let us know if you find it useful or have feedback on how to improve the datasets.

Related Questions

How did Ioana Baldini become interested in evaluating generative language models?
In what ways did Ioana Baldini contribute to product development during her time at IBM?
What insights has Ioana Baldini gained from her experience in multi-disciplinary research teams?
How did Ioana Baldini's education shape her approach to research in natural language processing?
What are the most significant projects Ioana Baldini has worked on during her career?
Ioana Baldini
Add to my network

Location

New York, New York, United States