Tamanna Hossain-Kay

Hi, I’m a PhD Candidate researching LLM safety, evaluation & reasoning robustness. My work at the Computer Science department of UC, Irvine advised by Sameer Singh is generously funded by the Hasso-Plattner Institute.

360+ citations. Published papers on AI safety, evaluation, and benchmarking, in top-tier NLP conferences (3 first author) and workshops, including a best paper award.
Ongoing research on using symbolic representations to guide LLM decoding, improving reasoning and enhancing interpretability and robustness.
Industry data science experience delivering production lead-scoring models and contact-center and sales monitoring systems.
Extensive community organizing experience spanning reading groups, mixers, advocacy and charity events, and student organizations.

I’d love to connect about:

  ➤ Industry opportunities
  ➤ Research collaborations
  ➤ Community building in Santa Cruz

Papers •

Characterizing Mamba's Selective Memory using Auto-Encoders
AACL 2025. Oral Presentation.
Tamanna Hossain, Robert L. Logan IV, Ganesh Jagadeesan, Sameer Singh, Joel Tetreault, Alejandro Jaimes

MisgenderMender: A Community-Informed Approach to Misgendering Interventions
NAACL 2024.
Tamanna Hossain, Sunipa Dev, Sameer Singh.
PDF Video BibTeX

MISGENDERED: Limits of Large Language Models in Understanding Pronouns
ACL 2023.
Tamanna Hossain, Sunipa Dev, Sameer Singh.
PDF Video BibTeX

Evaluating the generalisability of neural rumour verification models
Information Processing & Management 2023.
Elena Kochkina, Tamanna Hossain, Robert L. Logan IV, Miguel Arana-Catania, Rob Procter, Arkaitz Zubiaga, Sameer Singh, Yulan He, Maria Liakata.
PDF BibTeX

COVIDLies: Detecting COVID-19 Misinformation on Social Media
EMNLP NLP Covid19 Workshop 2020. Best Paper Award
Tamanna Hossain, Robert L. Logan IV, Arjuna Ugarte, Yoshitomo Matsubara, Sean Young, Sameer Singh.
PDF Video BibTeX

Blog Posts •

2026/01/27 SATLM: Satisfiability-Aided Language Models Using Declarative Prompting

2025/02/08 Yet Another DeepSeek Overview

2023/08/05 Paper Summary: Whose Opinions Do Language Models Reflect?

2022/01/08 Paper Summary: Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies

2021/11/28 Weird Stuff in High Dimensions

2021/11/09 Box Embeddings: Paper Overviews

2021/06/28 Orthogonal Procrustes

2019/12/25 Five Year Anniversary Trip to Maui

2018/11/01 A Brief Introduction to fMRI Analysis

2018/05/18 Viz : The Rohingya Exodus

2018/05/16 Viz : Drawing [e]