Publications

For most uptodate list, please check my Google Scholar profile. I will also attempt to maintain an organized list below with direct links to PDF files for my publications.

2025

• Anubrata Das, Manoj Kumar, Ninareh Mehrabi, Anil Ramakrishna, Anna Rumshisky, Kai-Wei Chang, Aram Galstyan, Morteza Ziyadi, Rahul Gupta On Localizing and Deleting Toxic Memories in Large Language Models, NAACL Findings

• Isha Chaudhary, Qian Hu, Manoj Kumar, Morteza Ziyadi, Rahul Gupta, Gagandeep Singh, Quantitative Certification of Bias in Large Language Models, ICLR

• Anil Ramakrishna, Yixin Wan, Xiaomeng Jin, Kai-Wei Chang, Zhiqi Bu, Bhanukiran Vinzamuri, Volkan Cevher, Mingyi Hong, Rahul Gupta, MUNCH: A Multitask Unlearning Benchmark for LLMs, AAAI 2025 Workshop on Preventing and Detecting LLM Misinformation

• Elan Sopher Markowitz, Anil Ramakrishna, Ninareh Mehrabi, Charith Peris, Rahul Gupta, Kai-Wei Chang, Aram Galstyan, K-Edit: Language Model Editing with Contextual Knowledge Awareness, AAAI 2025 Workshop on Preventing and Detecting LLM Misinformation

2024

• Anil Ramakrishna, Jimit Majmudar, Rahul Gupta, Devamanyu Hazarika, LLM-PIEval: A benchmark for indirect prompt injection attacks in large language models, AdvML Frontiers @NeurIPS2024

• Ninareh Mehrabi, Palash Goyal, Christophe Dupuy, Qian Hu, Shalini Ghosh, Richard Zemel, Kai-Wei Chang, Aram Galstyan, Rahul Gupta, FLIRT: Feedback Loop In-context Red Teaming, EMNLP

• Ziyi Liu, Soumya Sanyal, Isabelle Lee, Yongkang Du, Rahul Gupta, Yang Liu, Jieyu Zhao Self-contradictory reasoning evaluation and detection, EMNLP findings

• Tao Meng, Ninareh Mehrabi, Palash Goyal, Anil Ramakrishna, Aram Galstyan, Richard Zemel, Kai-Wei Chang, Rahul Gupta, Charith Peris, Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification, EMNLP

• Fei Wang, Ninareh Mehrabi, Palash Goyal, Rahul Gupta, Kai-Wei Chang, Aram Galstyan, Data advisor: Dynamic data curation for safety alignment of large language models, EMNLP

• Elan Sopher Markowitz, Anil Ramakrishna, Jwala Dhamala, Ninareh Mehrabi, Charith Peris, Rahul Gupta, Kai-Wei Chang, Aram Galstyan Tree-of-Traversals: A Zero-shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs, ACL

• Lisa Bauer, Ninareh Mehrabi, Palash Goyal, Kai-Wei Chang, Aram Galstyan and Rahul Gupta, BELIEVE: Belief-Enhanced Instruction Generation and Augmentation for Zero-Shot Bias Mitigation, TrustNLP@NAACL

• Fan Yang, Shalini Ghosh, Emre Barut, Kechen Qin, Prashan Wanigasekara, Chengwei Su, Weitong Ruan, Rahul Gupta, Masking Latent Gender Knowledge for Debiasing Image Captioning, TrustNLP@NAACL

• Tiantian Feng, Anil Ramakrishna, Jimit Majmudar, Charith Peris, Jixuan Wang, Clement Chung, Richard Zemel, Morteza Ziyadi, Rahul Gupta, Partial federated learning: Unlocking non-biometric text information sharing for federated learning, ICASSP 2024 Workshop on Trustworthy Speech Processing

• Anaelia Ovalle, Ninareh Mehrabi, Palash Goyal, Jwala Dhamala, Kai-Wei Chang, Richard Zemel, Aram Galstyan, Yuval Pinter, Rahul Gupta, Are you talking to [xem] or [x,em]? On Tokenization and Addressing Misgendering in LLMs with Pronoun Tokenization Parity, NAACL Findings

• Roy Siegelmann, Ninareh Mehrabi, Palash Goyal, Prasoon Goyal, Lisa Bauer, Jwala Dhamala, Aram Galstyan, Rahul Gupta, Reza Ghanadan, MICo: Preventative Detoxification of Large Language Models through Inhibition Control, NAACL Findings

• Zhewei Sun, Qian Hu, Rahul Gupta, Richard Zemel, Yang Xu, Toward Informal Language Processing: Knowledge of Slang in Large Language Models, NAACL

• Junyi Li, Charith Peris, Ninareh Mehrabi, Palash Goyal, Kai-Wei Chang, Aram Galstyan, Richard Zemel, Rahul Gupta, The steerability of large language models toward data-driven personas, NAACL

2023

• Qian Hu, Palash Goyal, Rahul Gupta Model Evaluation for Model-Based Metrics, EMNLP

• Anil Ramakrishna, Rahul Gupta, Jens Lehmann, Morteza Ziyadi, a Testbed of Automatically Generated Invalid Questions to Evaluate Large Language Models for Hallucinations, EMNLP Findings

• Ninareh Mehrabi, Palash Goyal, Anil Ramakrishna, Jwala Dhamala, Shalini Ghosh, Richard Zemel, Kai-Wei Chang, Aram Galstyan, Rahul Gupta, JAB: Joint Adversarial Prompting and Belief Augmentation, Socially Responsible Language Modelling Research @ Neurips.

• Junyi Li, Ninareh Mehrabi, Charith Peris, Palash Goyal, Kai-Wei Chang, Aram Galstyan, Richard Zemel, Rahul Gupta, On the steerability of large language models toward data-driven personas, CIKM workshop on Personalized Generative AI.

• Jiao Sun, Yufei Tian, Wangchunshu Zhou, Nan Xu, Qian Hu, Rahul Gupta, John Frederick Wieting, Nanyun Peng, Xuezhe Ma, Evaluating Large Language Models on Controlled Generation Tasks, EMNLP

• Jack Good, Jimit Majmudar, Christophe Dupuy, Jixuan Wang, Charith Peris, Clement Chung, Richard Zemel, Rahul Gupta Coordinated Replay Sample Selection for Continual Federated Learning, EMNLP industry track

• Tiantian Feng, Digbalay Bose, Tuo Zhang, Rajat Hebbar, Anil Ramakrishna, Rahul Gupta, Mi Zhang, Salman Avestimehr, Shrikanth Narayanan, FedMultimodal: A Benchmark For Multimodal Federated Learning, KDD

• Anaelia Ovalle, Palash Goyal, Jwala Dhamala, Zachary Jaggers, Kai-Wei Chang, Aram Galstyan, Richard Zemel, Rahul Gupta “I’m fully who I am”: Towards centering transgender and non-binary voices to measure biases in open language generation, ACM FAccT

• Ansel MacLaughlin, Anna Rumshisky, Rinat Khaziev, Anil Ramakrishna, Yuval Merhav, Rahul Gupta, Self-healing through error detection, attribution, and retraining, ICASSP

• Christophe Dupuy, Jimit Majmudar, Jixuan Wang, Tanya G Roosta, Rahul Gupta, Clement Chung, Jie Ding, Salman Avestimehr, Quantifying Catastrophic Forgetting in Continual Federated Learning, ICASSP

• Rahul Gupta, Lisa Bauer, Kai-Wei Chang, Jwala Dhamala, Aram Galstyan, Palash Goyal, Qian Hu, Avni Khatri, Rohit Parimi, Charith Peris, Apurv Verma, Richard Zemel, Prem Natarajan, Incorporating Fairness in Large Scale NLU Systems, ICDM Industry day

• Charith Peris, Christophe Dupuy, Jimit Majmudar, R Parikh, S Smaili, R Zemel, Rahul Gupta, Privacy in the Time of Language Models, ICDM Industry day

• Jwala Dhamala, Varun Kumar, Rahul Gupta, Kai-Wei Chang, Aram Galstyan, An analysis of the effects of decoding algorithms on fairness in open-ended language generation, IEEE SLT

• Ninareh Mehrabi, Palash Goyal, Apurv Verma, Jwala Dhamala, Varun Kumar, Qian Hu, Kai-Wei Chang, Richard Zemel, Aram Galstyan, Rahul Gupta Resolving ambiguities in text-to-image generative models, ACL

• Zefei Li, Anil Ramakrishna, Anna Rumshisky, Andy Rosenbaum, Saleh Soltan, Rahul Gupta Sampling bias in NLU models: Impact and mitigation, Interspeech

2022

• Caleb Ziems, William Held, Jingfeng Yang, Jwala Dhamala, Rahul Gupta, Diyi Yang Multi-VALUE: A framework for cross-dialectal English NLP, ACL

• Manoj Kumar, Anna Rumshisky, Rahul Gupta, Chasing the Tail with Domain Generalization: A Case Study on Frequency-Enriched Datasets, Asia-Pacific chapter of ACL

• Saleh Soltan, Shankar Ananthakrishnan, Jack FitzGerald, Rahul Gupta, Wael Hamza, Haidar Khan, Charith Peris, Stephen Rawls, Andy Rosenbaum, Anna Rumshisky, Chandana Satya Prakash, Mukund Sridhar, Fabian Triefenbach, Apurv Verma, Gokhan Tur, Prem Natarajan, AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model, ArXiv preprint

• Manoj Kumar, Yuval Merhav, Haidar Khan, Rahul Gupta, Anna Rumshisky, Wael Hamza, Controlled Data Generation via Insertion Operations for NLU, NAACL Industry Track

• Jimit Majmudar, Christophe Dupuy, Charith Peris, Sami Smaili, Rahul Gupta, Richard Zemel, Differentially Private Decoding in Large Language Models, TrustNLP workshop @ ACL

• Nikhita Vedula, Rahul Gupta, Alok Alok, Mukund Sridhar, Shankar Ananthakrishnan, Advin: Automatically Discovering Novel Domains and Intents from User Text Utterances, ICASSP

• Christophe Dupuy, Tanya Roosta, Leo Long, Clement Chung, Rahul Gupta, Salman Avestimehr, Learnings from Federated Learning in the Real world, ICASSP

• Christophe Dupuy, Radhika Arava, Rahul Gupta, Anna Rumshisky, An Efficient DP-SGD Mechanism for Large Scale NLU Models, ICASSP

• Rahul Sharma, Anil Ramakrishna, Ansel MacLaughlin, Anna Rumshisky, Jimit Majmudar, Clement Chung, Salman Avestimehr, Rahul Gupta, Federated Learning with Noisy User Feedback, NAACL

• Peyman Passban, Tanya Roosta, Rahul Gupta, Aman Chadha, Clement Chung, Training Mixed-Domain Translation Models via Federated Learning, NAACL

• Bill Yuchen Lin, Chaoyang He, Zihang Zeng, Hulin Wang, Yufen Huang, Christophe Dupuy, Rahul Gupta, Mahdi Soltanolkotabi, Xiang Ren, Salman Avestimehr, Fednlp: Benchmarking federated learning methods for natural language processing tasks, NAACL Findings

• Rahil Parikh, Christophe Dupuy, Rahul Gupta, Canary Extraction in Natural Language Understanding Models, ACL

• Umang Gupta, Jwala Dhamala, Varun Kumar, Apurv Verma, Yada Pruksachatkun, Satyapriya Krishna, Rahul Gupta, Kai-Wei Chang, Greg Ver Steeg, Aram Galstyan, Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal, ACL Findings

• Satyapriya Krishna, Rahul Gupta, Apurv Verma, Jwala Dhamala, Yada Pruksachatkun, Kai-Wei Chang, Measuring Fairness of Text Classifiers via Prediction Sensitivity, ACL

• Yang Trista Cao, Yada Pruksachatkun, Kai-Wei Chang, Rahul Gupta, Varun Kumar, Jwala Dhamala, Aram Galstyan, On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations, ACL

• Stefan Schroedl, Manoj Kumar, Kiana Hajebi, Morteza Ziyadi, Sriram Venkatapathy, Anil Ramakrishna, Rahul Gupta, Pradeep Natarajan Improving large-scale conversational assistants using model interpretation based training sample selection, EMNLP Industry track

2021

• Justin Payan, Yuval Merhav, He Xie, Satyapriya Krishna, Anil Ramakrishna, Mukund Sridhar, Rahul Gupta, Towards Realistic Single-Task Continuous Learning Research for NER, EMNLP Findings

• Yada Pruksachatkun, Satyapriya Krishna, Jwala Dhamala, Rahul Gupta, Kai-Wei Chang, Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification, ACL Findings

• Jwala Dhamala, Tony Sun, Varun Kumar, Satyapriya Krishna, Yada Pruksachatkun, Kai-Wei Chang, Rahul Gupta, BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation, ACM FAccT

• Satyapriya Krishna, Rahul Gupta, Christophe Dupuy, ADePT: Auto-encoder based Differentially Private Text Transformation, EACL

• Manoj Kumar, Varun Kumar, Hadrien Glaude, Cyprien de Lichy, Aman Alok, Rahul Gupta, Protoda: Efficient Transfer Learning for Few-Shot Intent Classification, IEEE SLT

• Ansel MacLaughlin, Jwala Dhamala, Anoop Kumar, Sriram Venkatapathy, Ragav Venkatesan, Rahul Gupta, Evaluating the Effectiveness of Efficient Neural Architecture Search for Sentence-Pair Tasks, Insights from Negative Results in NLP

2020

• Anil Ramakrishna, Rahul Gupta and Shrikanth Narayanan, Joint Multi-Dimensional Model for Global and Time-Series Annotations, IEEE Transaction of Affective Computing

• Saurabh Sahu, Rahul Gupta, and Carol Espy-Wilson, Modeling Feature Representations for Affective Speech using Generative Adversarial Networks. IEEE Transaction of Affective Computing

• Akshit Tyagi, Varun Sharma, Rahul Gupta, Lynn Samson, Nan Zhuang, Zihang Wang, Bill Campbell, Fast Intent Classification for Spoken Language Understanding, ICASSP

• Aman Alok, Rahul Gupta, Shankar Ananthakrishnan, Design Considerations for Hypothesis Rejection Modules in Spoken-Language-Understanding Systems, ICASSP

• Aarsh Patel, Rahul Gupta, Mukund Sridhar, Satyapriya Krishna, Alok Aman, Peng Liu Towards Classification Parity Across Cohorts, ICLR-IRL workshop

2019

• Rahul Gupta, Aman Alok, Shankar Ananthakrishnan, One-vs-All Models for Asynchronous Training: An Empirical Analysis, Interspeech

• Rahul Gupta, Data augmentation for low resource sentiment analysis using generative adversarial networks . ICASSP

• Taruna Agrawal, Rahul Gupta, Shrikanth Narayanan, evaluating CNN representations for low resource medical image classification . ICASSP

2018

• Chengwei Su, Rahul Gupta, Shankar Ananthakrishnan and Spyros Matsoukas, A Re-ranker Scheme for Integrating Large Scale NLU Models. IEEE-SLT

• Saurabh Sahu, Rahul Gupta, and Carol Espy-Wilson, On Enhancing Speech Emotion Recognition using Generative Adversarial Networks. Interspeech

• Saurabh Sahu, Rahul Gupta, Ganesh Sivaraman and Carol Espy-Wilson, Smoothing Model Predictions using Adversarial Training Procedures for Speech Based Emotion Recognition. ICASSP

• Rahul Gupta, Saurabh Sahu, Carol Espy-Wilson and Shrikanth Narayanan, Semi-supervised and Transfer learning approaches for low resource sentiment classification. ICASSP

2017

• Taruna Agrawal, Rahul Gupta , Saurabh Sahu and Carol Espy-Wilson SCL-UMD at the Medico Task-MediaEval 2017: Transfer learning based Classification of Medical Images, Medico challenge-MediaEval

• Taruna Agrawal, Rahul Gupta and, Shrikanth Narayanan, Multimodal Detection of Fake Social Media Use Through a Fusion of Classification and Pairwise Ranking Systems, EUSIPCO. Presented by the first author at WiML@NIPS-2017

• Qinyi Luo, Rahul Gupta and, Shrikanth Narayanan, Transfer Learning between Concepts for Human Behavior Modeling: An Application to Sincerity and Deception Prediction, Interspeech

• Saurabh Sahu, Rahul Gupta, Ganesh Sivaraman and Carol Espy-Wilson, Adversarial Auto-encoders for Speech Based Emotion Recognition. Interspeech

• Rahul Gupta, Saurabh Sahu, Carol Espy-Wilson and Shrikanth Narayanan, An Affect Prediction Approach through Depression Severity Parameter Incorporation in Neural Networks, Interspeech

• Rahul Gupta, and Shrikanth Narayanan, Inferring object rankings based on noisy pairwise comparisons from multiple annotators, ArXiv preprint

• Sabyasachee Baruah, Rahul Gupta, and Shrikanth Narayanan, A Knowledge Transfer and Boosting Approach to the Prediction of Affect in Movies, ICASSP

2016

• Rahul Gupta, Kartik Audhkhasi, Zach Jacokes, Agata Rozga, and Shrikanth Narayanan, Modeling multiple time series annotations based on ground truth inference and distortion, IEEE Transactions on Affective Computing

• Rahul Gupta, Daniel Bone, Sungbok Lee, and Shrikanth Narayanan, Analysis of engagement behavior in children during dyadic interactions using prosodic cues, Computer Speech and Language

• Rahul Gupta, Kartik Audhkhasi, Sungbok Lee, and Shrikanth Narayanan, Detecting paralinguistic events in audio stream using context in features and probabilistic decisions, Computer Speech and Language

• Krishna Somandepalli, Rahul Gupta, Md Nasir, Brandon Booth, Sungbok Lee and Shrikanth Narayanan, Online Affect Tracking with Multimodal Kalman Filters, AVEC workshop

• Rahul Gupta and Shrikanth Narayanan, Predicting Affective Dimensions based on Self Assessed Depression Severity, Interspeech

• Rahul Gupta, Nishant Nath, Taruna Agrawal, Panayiotis Georgiou, David Atkins and Shrikanth Narayanan,Laughter Valence Prediction in Motivational Interviewing based on Lexical and Acoustic Cues, Interspeech

• Anil Ramakrishna, Rahul Gupta, Ruth Grossman and Shrikanth Narayanan, An Expectation Maximization approach to Joint Modeling of Multidimensional labels derived from Multiple Annotators, Interspeech

• Agnes Youn, Theodora Chaspari, Rahul Gupta, Leah I. Stein Duker, Sharon A. Cermak, Shrikanth Narayanan, Capturing the Structure of Electrodermal Activity with Deep Neural Networks, International Conference of the IEEE Engineering in Medicine and Biology Society (Undergraduate student posters paper)

• Manoj Kumar, Rahul Gupta, Daniel Bone, Nikolaos Malandrakis, Somer Bishop and Shrikanth Narayanan, Objective Language Feature Analysis in Children with Neurodevelopmental Disorders during Autism Assessment, Interspeech

• Daniel Bone, Somer Bishop, Rahul Gupta, Sungbok Lee and Shrikanth Narayanan, Acoustic-Prosodic and Turn-Taking Features in Interactions with Children with Neurodevelopmental Disorders, Interspeech

• Brandon Booth, Rahul Gupta, Pavlos Papadopoulos, Ruchir Travadi and Shrikanth Narayanan, Automatic Estimation of Perceived Sincerity From Spoken Language, Interspeech

• Rahul Gupta, Theodora Chaspari, Jangwon Kim, Naveen Kumar, Daniel Bone and Shrikanth Narayanan, Pathological speech processing: state-of-the-art, current challenges, and future directions, ICASSP

2015

• Rahul Gupta, Theodora Chaspari, Panayiotis Georgiou, David Atkins and Shrikanth Narayanan, Analysis and modeling of the role of laughter in motivational interviewing based psychotherapy conversations, Interspeech

• Jangwon Kim, Md Nasir, Rahul Gupta, Maarten Van Segbroeck, Daniel Bone, Matthew Black, Zisis Iason Skordilis, Zhaojun Yang, Panayiotis Georgiou, Shrikanth Narayanan, Automatic estimation of Parkinson's disease severity from diverse speech tasks, Interspeech

• Matthew Black, Daniel Bone, Zisis Iason Skordilis, Rahul Gupta, Wei Xia, Pavlos Papadopoulos, Sandeep Nallan Chakravarthula, Bo Xiao, Maarten Van Segbroeck, Jangwon Kim, Panayiotis Georgiou, Shrikanth Narayanan, Automated Evaluation of Non-Native English Pronunciation Quality: Combining Knowledge and Data-Driven Features at Multiple Time Scales, Interspeech. Winner of Interspeech Computational Paralinguistics Challenge, 2015

• Rahul Gupta, Naveen Kumar, Shrikanth Narayanan, Affect Prediction in Music using Boosted Ensemble of Filters, EUSIPCO

• Sandeep Nallan Chakravarthula, Rahul Gupta, Brian Baucom, Panayiotis Georgiou, A Language-Based Generative Model Framework For Behavioral Analysis Of Couples’ Therapy, ICASSP

• Rahul Gupta, Kartik Audhkhasi, Shrikanth Narayanan, A Mixture Of Experts Approach Towards Intelligibility Classification Of Pathological Speech, ICASSP

• Taruna Agrawal, Rahul Gupta, Shrikanth Narayanan, Retrieving Social Images using Relevance Filtering and Diverse Selection, Retrieving diverse social images task, MediaEval Workshop

• Rahul Gupta, Shrikanth Narayanan, Predicting Affect in Music Using Regression Methods on Low Level Features, Emotion in Music Challenge, MediaEval Workshop

2014

• Rahul Gupta, Sankaranarayanan Ananthakrishnan, Zhaojun Yang, Shrikanth Narayanan, Variable Span Disfluency Detection in ASR Transcripts, Interspeech

• Rahul Gupta, Panayiotis Georgiou, David Atkins, Shrikanth Narayanan, Predicting Client's Inclination Towards Target Behavior Change in Motivational Interviewing and Investigating the Role of Laughter, Interspeech

• Rahul Gupta, Kartik Audhkhasi, Shrikanth Narayanan, Training ensemble of diverse classifiers on feature subsets, ICASSP

• Rahul Gupta, Nikolaos Malandrakis, Bo Xiao, Tanaya Guha, Maarten Van Segbroeck, Matthew P Black, Alexandros Potamianos, Shrikanth S Narayanan, Multimodal prediction of affective dimensions and depression in human-computer interactions, Audio Visual Emotion Challenge and Workshop

• Naveen Kumar, Rahul Gupta, Tanaya Guha, Colin Vaz, Maarten VanSegbroeck, Jangwon Kim, Shrikanth Narayanan, Affective Feature Design and Predicting Continuous Affective Dimensions from Music, Emotion in Music Challenge, MediaEval Workshop

2013

• Rahul Gupta, Kartik Audhkhasi, Sungbok Lee, Shrikanth Narayanan, Paralinguistic event detection from speech using probabilistic time-series smoothing and masking, Interspeech. Winner of Interspeech Computational Paralinguistics Challenge, 2013 (USC Viterbi News)

• Rahul Gupta, Chi-Chun Lee, Sungbok Lee, Shrikanth Narayanan, Assesment of a child's engagement behavior using sequence model based features, Workshop on Affective Social Speech Signals

2012

• Rahul Gupta, Chi-Chun Lee, Daniel Bone, Agata Rozga, Sungbok Lee, Shrikanth Narayanan, Acoustical analysis of engagement behavior in children, Third Workshop on Child, Computer and Interaction

• Rahul Gupta, Chi-Chun Lee, Shrikanth Narayanan, Classification of emotional content of sighs in dyadic human interactions, ICASSP