Hi there!
I'm Amrita or Amy

Applied Scientist II at Amazon Rufus, working on Personalization and Trust & Safety. Ph.D. in Computer Science from Arizona State University.

🧠 LLMs 🛡️ AI Safety 📝 NLP 🔄 Domain Adaptation 🔍 AI-Generated Text Detection
Google Scholar ↗ GitHub ↗ Speaker Profile ↗
Amrita Bhattacharjee

I obtained my Ph.D. in Computer Science from the School of CS & AI at Arizona State University, working under Dr. Huan Liu at the Data Mining and Machine Learning Lab. My research focuses on leveraging large language models for human-intensive tasks in ML pipelines, robust detection of AI-generated content, and NLP applications in domain adaptation and generalization.

During Summer 2024, I was an Applied Research Intern at NVIDIA NeMo Guardrails, working on inference-time safety steering of LLMs. During Summer 2022, I interned at Nokia Bell Labs on continual learning and low-resource learning. When I'm not working, I enjoy traveling, hiking, kayaking, camping, and chilling with my cat Luna!

📢 News

Nov 2025
One paper accepted at IEEE BigData 2025!
Oct 2025
One paper accepted at SBP-BRiMS 2025!
Aug 2025
Two papers accepted at EMNLP 2025, Main track!
Apr 2025
Moved to the beautiful California Bay Area and started at Amazon, Palo Alto, CA.
Mar 2025
Successfully defended my PhD dissertation titledBuilding Trust in AI via Safe and Responsible Use of LLMs!
Feb 2025
Invited to be a Program Committee Member for SIGIR 2025.
Feb 2025
Speaking at CactusCon 13 on Building Trust in AI: On Safe and Responsible Use of LLMs. [Slides]
Jan 2025
Accepted a full-time offer as an Applied Scientist II at Amazon, Palo Alto, CA — working on LLM post-training and alignment!
Nov 2024
Received the NSF Travel Award for attending IEEE BigData 2024!
Oct 2024
Paper Zero-shot LLM-guided Counterfactual Generation accepted to IEEE BigData 2024!
Oct 2024
Paper Towards Inference-time Category-wise Safety Steering for LLMs accepted to the Safe Generative AI Workshop at NeurIPS 2024! [Work done at NVIDIA]
Sep 2024
Two papers accepted at EMNLP 2024 Main Track: (1) Defending Against Social Engineering Attacks in the Age of LLMs, (2) Large Language Models for Data Annotation: A Survey.
Sep 2024
Delivered an in-person tutorial on Defending Against Generative AI Threats in NLP at SBP-BRiMS 2024, Pittsburgh, PA.
Jun 2024
Received the SIGIR 2024 NSF Travel Award!
May 2024
My chat with ScienceNewsExplores got featured in this SNE news story.
Apr 2024
Paper Towards Interpretable Hate Speech Detection using LLM-extracted Rationales accepted to NAACL WOAH 2024!
Mar 2024
Demo paper ResumeFlow accepted at SIGIR 2024! [Paper]
Jan 2024
Accepted an offer to join NVIDIA as an Applied Research Intern for Summer 2024, working on LLM Safety!
Jan 2024
Paper Adversarial Text Purification accepted at PAKDD 2024! [Paper]
Nov 2023
🏆 Paper ConDA: Contrastive Domain Adaptation for AI-generated Text Detection won the Outstanding Paper Award at IJCNLP-AACL 2023 in Bali! [Paper]

Meet my wonderful rescue cat, Luna 🐈‍⬛

Luna the cat Luna the cat Luna the cat

Selected Publications

View all on Google Scholar ↗

Recent Preprints

Preprint
EAGLE: A Domain Generalization Framework for AI-generated Text Detection
Amrita Bhattacharjee, Raha Moraffah, Joshua Garland, Huan Liu
Read paper →

Accepted Publications

NeurIPS 2024 — Safe Generative AI
Towards Inference-time Category-wise Safety Steering for Large Language Models
Amrita Bhattacharjee*, Shaona Ghosh*, Traian Rebedea, Christopher Parisien  [Work done at NVIDIA]
Read paper →
EMNLP 2024
Defending Against Social Engineering Attacks in the Age of LLMs
Lin Ai*, Tharindu Kumarage*, Amrita Bhattacharjee*, Zizhou Liu, Zheng Hui, et al.
Read paper →
EMNLP 2024
Large Language Models for Data Annotation: A Survey
Zhen Tan*, Dawei Li*, Song Wang*, Alimohammad Beigi, Bohan Jiang, Amrita Bhattacharjee, et al.
Read paper →
IEEE BigData 2024
Zero-shot LLM-guided Counterfactual Generation: A Case Study on NLP Model Evaluation
Amrita Bhattacharjee, Raha Moraffah, Joshua Garland, Huan Liu
Read paper →
AAAI ReLM 2024
Towards LLM-guided Causal Explainability for Black-box Text Classifiers
Amrita Bhattacharjee, Raha Moraffah, Joshua Garland, Huan Liu
Read paper →
PAKDD 2024
Adversarial Text Purification: A Large Language Model Approach for Defense
Raha Moraffah, Shubh Khandelwal, Amrita Bhattacharjee, Huan Liu
Read paper →
IJCNLP-AACL 2023 🏆 Outstanding Paper Award
ConDA: Contrastive Domain Adaptation for AI-generated Text Detection
Amrita Bhattacharjee, Tharindu Kumarage, Raha Moraffah, Huan Liu
Read paper →
NAACL WOAH 2024
Towards Interpretable Hate Speech Detection using Large Language Model-extracted Rationales
Ayushi Nirmal*, Amrita Bhattacharjee*, Paras Sheth, Huan Liu
Read paper →
SIGIR 2024
ResumeFlow: An LLM-facilitated Pipeline for Personalized Resume Generation and Refinement
Amrita Bhattacharjee et al.
Read paper →
ACM SIGKDD Explorations
Fighting Fire with Fire: Can ChatGPT Detect AI-generated Text?
Amrita Bhattacharjee, Huan Liu
Read paper →
IJCAI 2022 — Survey
Text Transformations in Contrastive Self-Supervised Learning: A Review
Amrita Bhattacharjee*, Mansooreh Karami*, Huan Liu
Read paper →

Teaching & Service

🤝 Mentoring

Current Mentees

SZ
Saurabh Bhausaheb Zinjad
MS CS
LinkedIn ↗
AK
Aryan Vinod Keluskar
FURI Undergrad
LinkedIn ↗

Past Mentees

AN
Ayushi Nirmal
MS CS
LinkedIn ↗
PA
Punit Sai Arani
Undergrad — Honors Thesis
LinkedIn ↗
NB
Neha Balamurugan
Undergrad — Honors Thesis
LinkedIn ↗

Mentored 3 women for pursuing a research career in Computer Science via Women in Machine Learning (WiML) (Fall 2022)

🎓 Teaching

Fall 2024 — CSE 472: Social Media Mining

Project Coordinator and Guest Lecturer. Guest lectures on Data Mining and Introduction to Large Language Models: The Good, Bad and the Ugly. [Slides]

Fall 2023 — Barrett Honors College

Project Coordinator. Designed and developed a project on Political Bias and Strategic Influence Operations in Large Language Models. Mentored 4 undergraduate students.

Fall 2023 — CSE 472: Social Media Mining

Project Coordinator & Invited Speaker. Designed project on LLMs as Components in a ML Pipeline. Invited lecture on: A Primer on Large Language Models.

Fall 2021 — CSE 472: Social Media Mining

Project Coordinator. Designed project on Machine Generated Text Detection.

Fall 2019 & Spring 2020 — W.P. Carey School of Business

CIS Research Aide under Prof. Daniel Mazzola. Assisted with CIS 430, CIS 505, and CIS 506.

Fall 2019 — CSE 110: Principles of Programming (Java)

Teaching Assistant. Taught recitals (labs), grading, and held office hours.

📋 Reviewing & Conference Duties

Program Committee: IJCAI-ECAI 2026 (Survey, Human-centered AI track), IJCAI 2025 (Survey), SIGIR 2025, SDM 2025, AAAI 2025, AAAI 2024, AAAI 2023, IJCAI 2024 (Survey), SBP-BRiMS 2024, SBP-BRiMS 2023
External Reviewer: SNAM, JNCA, IPM, CogSys, Behavior & IT, MINT Workshop (NeurIPS 2024), SSHO (Elsevier), ACL SRW 2025, IJCAI HAI 2025
Student Volunteer: 15th ACM International WSDM Conference (WSDM 2022)
Panel Facilitator: ASU-Mayo Workshop on Generative AI and LLMs for Healthcare 2023 — facilitated panels on Clinical Decision Support with LLMs and Validation of AI-generated Medical Research

🌍 Travel Glimpses

When I'm not working on NLP and AI safety, I love exploring new places — from desert hikes in Arizona to kayaking trips and everything in between. Here's where my adventures take me.

Glacier National Park, Montana
Mountain Adventures
Hiking trails, summit views, and alpine landscapes.
View from the highest point in Sedona, Mt. Williams
Desert Explorations
Sunsets, red rocks, and the beauty of the Southwest.
Whitehorse Lake, Arizona
Water & Kayaking
Rivers, lakes, and paddling through serene waters.
📷

More photos coming soon!