About Me

I'm a graduate student in Computer Science at the University of California, Davis advised by Professor Muhao Chen. My research is focused on (1) Using data-driven approaches to increase Large Language Model performance and interpretability in various use cases; (2) Augmenting Large Language Model robustness, fairness and security; (3) Using Large Language Models for social good. Aside from my PhD I have been a summer Machine Learning intern at Comcast (twice), Pinterest and Nvidia.

News

2025  Sep LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions was accepted at Neurips'25.
2025  Jun Started a 3 month internship at Nvidia, working on Nvidia's Deep Research Agent to generate detailed reports from multiple tools connected to their internal bug databases.
2025  Jan Test-time backdoor mitigation for black-box large language models with defensive demonstrations was accepted at NAACL-Findings'25.
2025  Jan Assessing LLMs for Zero-shot Abstractive Summarization Through the Lens of Relevance Paraphrasing was accepted at NAACL-Findings'25.
2024  Sep Presented Incentivizing news consumption on social media platforms using large language models and realistic bot accounts at the Trust & Safety Research Conference at Stanford University.
2024  Aug Incentivizing news consumption on social media platforms using large language models and realistic bot accounts was accepted at PNAS Nexus.
2024  June Started 3 Month Internship as a Machine Learning Research Intern at Pinterest Research Labs.
2024  Mar Revisiting Zero-Shot Abstractive Summarization in the Era of Large Language Models from the Perspective of Position Bias was accepted at NAACL'24.
2023  June Started 3 Month Internship as a Machine Learning Intern at the Comcast Media Analytics Team.
2023  May A Utility-Preserving Obfuscation Approach for YouTube Recommendations was accepted at PETS'23.
2022  Dec Attended the second annual ProperData Symposium at UC Irvine.
2022  Nov Attended the UC Noyce Initiative Symposium '22 at UC Santa Barbara.
2022  Oct Presented at the UC Davis Noyce Workshop.
2022  June Started 3 Month Internship as a Machine Learning Intern at the Comcast Media Analytics Team.
2021  Nov Attended the ProperData Symposium at UC Irvine.
2021  Sep Joined the PhD program at UC Davis.

Publications

LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions

H Askari S Gupta F Wang A Chhabra M Chen

Neurips 2025, 2025

Unraveling Indirect In-Context Learning Using Influence Functions

H Askari S Gupta T Tong F Wang A Chhabra M Chen

arXiv preprint, 2025

Test-time backdoor mitigation for black-box large language models with defensive demonstrations

W Mo J Xu Q Liu J Wang J Yan H Askari C Xiao M Chen

NAACL-Findings, 2025

Assessing LLMs for Zero-shot Abstractive Summarization Through the Lens of Relevance Paraphrasing

H Askari A Chhabra M Chen P Mohapatra

NAACL-Findings, 2025

Incentivizing News Consumption on Social Media Platforms Using Large Language Models and Realistic Bot Accounts

H Askari A Chhabra BC von Hohenberg M Heseltine M Wojcieszak

PNAS Nexus, 2024

Revisiting Zero-Shot Abstractive Summarization in the Era of Large Language Models from the Perspective of Position Bias

A Chhabra H Askari P Mohapatra

NAACL, 2024

A Utility-Preserving Obfuscation Approach for YouTube Recommendations

J Zhang H Askari K Psounis Z Shafiq

23rd Privacy Enhancing Technologies Symposium, 2023