Brihi Joshi

I am a 5th year CS PhD Candidate at the University of Southern California, advised by professors Xiang Ren and Swabha Swayamdipta as a part of the NLP Group, INK Lab and Dill Lab. I also work closely with Tim Paek and Rik Koncel-Kedziorski at Apple on various topics on personalization.
My research focuses on human-centered AI alignment, with a particular emphasis on personalization. I study how AI systems can adapt to individual users through interaction, making them more effective partners in learning, exploration, and knowledge building. To this end, I love to work on human-grounded evaluation and new methods that enable personalization. My research is supported by the USC Annenberg, 2023 Amazon ML and 2024 Apple Scholars in AI/ML Fellowships.
Prior to this, I was an Analyst at Goldman Sachs where I worked with the Regulatory Engineering team. Even before that, I graduated with a Bachelors in Computer Science from IIIT Delhi where I did research with Laboratory for Computational Social Systems (LCS2), Snap Research and IBM Research India.
Apart from pursuing my academic interests, I am extremely passionate about serving the community. I used to co-lead the Delhi chapter of Women Who Code Delhi, which was an organisation that works towards diversity and inclusion of women in tech, for more than 5 years. Currently, I am one of the organizers of the NLP with Friends. I am a huge advocate of diversity in CS Research and general mentoring, and always looking for opportunities to support them. Head over to the outreach & mentorship tab for more details. I am also a musician by passion and absolutely love singing and composing music. I’ve tried my hands at multiple instruments (and I plan to master some, explore more).
news
Aug 2025 | 3 (!!!) papers got accepted to EMNLP 2025 🥹! Internship works done at Apple last summer, PB&J and PrimeX (paper/dataset coming soon!) got into Findings and Main respectively, and Amulet got into Main. Super duper excited for Suzhou, China 🌸 |
---|---|
Jun 2025 | We released our ACL Findings 2025 work, ELI-Why, a benchmark and evaluation protocol for zero-shot personalization of LLM responses for people with different backgrounds 🙌🏽 |
May 2025 | Some new preprints: PB&J, my internship work from last summer at Apple, and Amulet, a collaboration with Sahana on preference evaluation for multi-turn human-AI conversations |
May 2025 | ELI-Why got accepted to ACL 2025 Findings! Preprint out soon, super excited for Vienna (and viennese coffee ☕️)! |
May 2025 | I’m in Seattle again this summer, doing cool personalization and user-centred NLP at 🍎! |
Dec 2024 | OATH-Frames won an Outstanding Paper Award at EMNLP 2024!! 🎉 |
Sep 2024 | OATH-Frames led by Jaspreet (and also my first truly interdisciplinary work) got accepted to EMNLP 2024 Main! 👏🏼 |
May 2024 | Started as an ML Research Intern at Apple in Seattle! Super excited to work on interesting problems in Humans x LLMs 🙌🏽 |
Mar 2024 | Awarded the 2024 Apple Scholars in AI/ML PhD fellowship! 🥺 |
Jan 2024 | MaRio accepted at ICLR 2024! See you in Vienna!! 🙌🏽 |
Nov 2023 | Excited to share our new work led by Sahana, on improving the quality of rationales generated by small LMs! |
Oct 2023 | Passed my PhD Quals! Officialy a PhD Candidate now :D |
Oct 2023 | Gave a talk at the USC-Amazon Centre on Trusted AI about Human-Centred Operationalization of Model Explanations! |
Jul 2023 | Honoured to be awarded the Amazon ML PhD Fellowship for 2023-24! 🥺 |
May 2023 | Started as an Applied Scientist Intern at Amazon Alexa 🎉 Excited to explore the greater Boston area and work with the NLG Team! |