Anil Ramakrishna

61 papers A* 5A 6B 1Misc 2Journal 30Unranked 17

Year	Rank	Type	Title / Venue / Authors
2026	—	`conf`	BLUR: A Bi-Level Optimization Approach for LLM Unlearning. EACL (Volume 1: Long Papers) Hadi Reisizadeh, Jinghan Jia, Zhiqi Bu, Bhanukiran Vinzamuri, Anil Ramakrishna, Kai-Wei Chang, Volkan Cevher, Sijia Liu, Mingyi Hong
2026	J	`jnl`	Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs. CoRR Efthymios Tsaprazlis, Tiantian Feng, Anil Ramakrishna, Sai Praneeth Karimireddy, Rahul Gupta, Shrikanth Narayanan
2025	J	`jnl`	Assessing Visual Privacy Risks in Multimodal AI: A Novel Taxonomy-Grounded Evaluation of Vision-Language Models. CoRR Efthymios Tsaprazlis, Tiantian Feng, Anil Ramakrishna, Rahul Gupta, Shrikanth Narayanan
2025	J	`jnl`	BLUR: A Bi-Level Optimization Approach for LLM Unlearning. CoRR Hadi Reisizadeh, Jinghan Jia, Zhiqi Bu, Bhanukiran Vinzamuri, Anil Ramakrishna, Kai-Wei Chang, Volkan Cevher, Sijia Liu, Mingyi Hong
2025	J	`jnl`	Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language Models. CoRR Taha Entesari, Arman Hatami, Rinat Khaziev, Anil Ramakrishna, Mahyar Fazlyab
2025	—	`conf`	Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs. NAACL (Findings) Duygu Nur Yaldiz, Yavuz Faruk Bakman, Baturalp Buyukates, Chenyang Tao, Anil Ramakrishna, Dimitrios Dimitriadis, Jieyu Zhao, Salman Avestimehr
2025	J	`jnl`	From Narrow Unlearning to Emergent Misalignment: Causes, Consequences, and Containment in LLMs. CoRR Erum Mushtaq, Anil Ramakrishna, Satyapriya Krishna, Sattvik Sahai, Prasoon Goyal, Kai-Wei Chang, Tao Zhang, Rahul Gupta
2025	—	`conf`	HARMONY: Hidden Activation Representations and Model Output-Aware Uncertainty Estimation for Vision-Language Models. CVPR Workshops Erum Mushtaq, Zalan Fabian, Yavuz Faruk Bakman, Anil Ramakrishna, Mahdi Soltanolkotabi, Salman Avestimehr
2025	J	`jnl`	HARMONY: Hidden Activation Representations and Model Output-Aware Uncertainty Estimation for Vision-Language Models. CoRR Erum Mushtaq, Zalan Fabian, Yavuz Faruk Bakman, Anil Ramakrishna, Mahdi Soltanolkotabi, Salman Avestimehr
2025	J	`jnl`	K-Edit: Language Model Editing with Contextual Knowledge Awareness. CoRR Elan Markowitz, Anil Ramakrishna, Ninareh Mehrabi, Charith Peris, Rahul Gupta, Kai-Wei Chang, Aram Galstyan
2025	—	`conf`	LUME: LLM Unlearning with Multitask Evaluations. EMNLP (Findings) Anil Ramakrishna, Yixin Wan, Xiaomeng Jin, Kai-Wei Chang, Zhiqi Bu, Bhanukiran Vinzamuri, Volkan Cevher, Mingyi Hong, Rahul Gupta
2025	J	`jnl`	LUME: LLM Unlearning with Multitask Evaluations. CoRR Anil Ramakrishna, Yixin Wan, Xiaomeng Jin, Kai-Wei Chang, Zhiqi Bu, Bhanukiran Vinzamuri, Volkan Cevher, Mingyi Hong, Rahul Gupta
2025	—	`conf`	Not Every Token Needs Forgetting: Selective Unlearning Balancing Forgetting and Utility in Large Language Models. EMNLP (Findings) Yixin Wan, Anil Ramakrishna, Kai-Wei Chang, Volkan Cevher, Rahul Gupta
2025	J	`jnl`	Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning. CoRR Yixin Wan, Anil Ramakrishna, Kai-Wei Chang, Volkan Cevher, Rahul Gupta
2025	—	`conf`	On Localizing and Deleting Toxic Memories in Large Language Models. NAACL (Findings) Anubrata Das, Manoj Kumar, Ninareh Mehrabi, Anil Ramakrishna, Anna Rumshisky, Kai-Wei Chang, Aram Galstyan, Morteza Ziyadi, Rahul Gupta
2025	J	`jnl`	REAL Sampling: Boosting Factuality and Diversity of Open-ended Generation by Extrapolating the Entropy of an Infinitely Large LM. Trans. Assoc. Comput. Linguistics Haw-Shiuan Chang, Nanyun Peng, Mohit Bansal, Anil Ramakrishna, Tagyoung Chung
2025	J	`jnl`	SemEval-2025 Task 4: Unlearning sensitive content from Large Language Models. CoRR Anil Ramakrishna, Yixin Wan, Xiaomeng Jin, Kai-Wei Chang, Zhiqi Bu, Bhanukiran Vinzamuri, Volkan Cevher, Mingyi Hong, Rahul Gupta
2025	A*	`conf`	Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond. ICML Chongyu Fan, Jinghan Jia, Yihua Zhang, Anil Ramakrishna, Mingyi Hong, Sijia Liu
2025	J	`jnl`	Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond. CoRR Chongyu Fan, Jinghan Jia, Yihua Zhang, Anil Ramakrishna, Mingyi Hong, Sijia Liu
2025	—	`conf`	Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation. ACL (Findings) Tharindu Kumarage, Ninareh Mehrabi, Anil Ramakrishna, Xinyan Zhao, Richard S. Zemel, Kai-Wei Chang, Aram Galstyan, Rahul Gupta, Charith Peris
2025	J	`jnl`	Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation. CoRR Tharindu Kumarage, Ninareh Mehrabi, Anil Ramakrishna, Xinyan Zhao, Richard S. Zemel, Kai-Wei Chang, Aram Galstyan, Rahul Gupta, Charith Peris
2025	—	`conf`	Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate. NAACL (Long Papers) Xiaomeng Jin, Zhiqi Bu, Bhanukiran Vinzamuri, Anil Ramakrishna, Kai-Wei Chang, Volkan Cevher, Mingyi Hong
2024	—	`conf`	Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification. EMNLP (Findings) Tao Meng, Ninareh Mehrabi, Palash Goyal, Anil Ramakrishna, Aram Galstyan, Richard S. Zemel, Kai-Wei Chang, Rahul Gupta, Charith Peris
2024	J	`jnl`	Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification. CoRR Tao Meng, Ninareh Mehrabi, Palash Goyal, Anil Ramakrishna, Aram Galstyan, Richard S. Zemel, Kai-Wei Chang, Rahul Gupta, Charith Peris
2024	—	`conf`	Correcting Language Model Outputs by Editing Salient Layers. EACL (Findings) Kshitij Mishra, Tamer Soliman, Anil Ramakrishna, Aram Galstyan, Anoop Kumar
2024	J	`jnl`	Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs. CoRR Duygu Nur Yaldiz, Yavuz Faruk Bakman, Baturalp Buyukates, Chenyang Tao, Anil Ramakrishna, Dimitrios Dimitriadis, Salman Avestimehr
2024	A*	`conf`	Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM. EMNLP Haw-Shiuan Chang, Nanyun Peng, Mohit Bansal, Anil Ramakrishna, Tagyoung Chung
2024	J	`jnl`	Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM. CoRR Haw-Shiuan Chang, Nanyun Peng, Mohit Bansal, Anil Ramakrishna, Tagyoung Chung
2024	J	`jnl`	Partial Federated Learning. CoRR Tiantian Feng, Anil Ramakrishna, Jimit Majmudar, Charith Peris, Jixuan Wang, Clement Chung, Richard S. Zemel, Morteza Ziyadi, Rahul Gupta
2024	J	`jnl`	REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy. CoRR Haw-Shiuan Chang, Nanyun Peng, Mohit Bansal, Anil Ramakrishna, Tagyoung Chung
2024	—	`conf`	Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs. ACL (1) Elan Markowitz, Anil Ramakrishna, Jwala Dhamala, Ninareh Mehrabi, Charith Peris, Rahul Gupta, Kai-Wei Chang, Aram Galstyan
2024	J	`jnl`	Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs. CoRR Elan Markowitz, Anil Ramakrishna, Jwala Dhamala, Ninareh Mehrabi, Charith Peris, Rahul Gupta, Kai-Wei Chang, Aram Galstyan
2024	J	`jnl`	Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate. CoRR Zhiqi Bu, Xiaomeng Jin, Bhanukiran Vinzamuri, Anil Ramakrishna, Kai-Wei Chang, Volkan Cevher, Mingyi Hong
2023	J	`jnl`	FedMultimodal: A Benchmark For Multimodal Federated Learning. CoRR Tiantian Feng, Digbalay Bose, Tuo Zhang, Rajat Hebbar, Anil Ramakrishna, Rahul Gupta, Mi Zhang, Salman Avestimehr, Shrikanth Narayanan
2023	A*	`conf`	FedMultimodal: A Benchmark for Multimodal Federated Learning. KDD Tiantian Feng, Digbalay Bose, Tuo Zhang, Rajat Hebbar, Anil Ramakrishna, Rahul Gupta, Mi Zhang, Salman Avestimehr, Shrikanth Narayanan
2023	—	`conf`	INVITE: a Testbed of Automatically Generated Invalid Questions to Evaluate Large Language Models for Hallucinations. EMNLP (Findings) Anil Ramakrishna, Rahul Gupta, Jens Lehmann, Morteza Ziyadi
2023	J	`jnl`	JAB: Joint Adversarial Prompting and Belief Augmentation. CoRR Ninareh Mehrabi, Palash Goyal, Anil Ramakrishna, Jwala Dhamala, Shalini Ghosh, Richard S. Zemel, Kai-Wei Chang, Aram Galstyan, Rahul Gupta
2023	A	`conf`	Sampling bias in NLU models: Impact and Mitigation. INTERSPEECH Zefei Li, Anil Ramakrishna, Anna Rumshisky, Andy Rosenbaum, Saleh Soltan, Rahul Gupta
2023	Misc	`conf`	Self-Healing Through Error Detection, Attribution, and Retraining. ICASSP Ansel MacLaughlin, Anna Rumshisky, Rinat Khaziev, Anil Ramakrishna, Yuval Merhav, Rahul Gupta
2022	—	`conf`	Federated Learning with Noisy User Feedback. NAACL-HLT Rahul Sharma, Anil Ramakrishna, Ansel MacLaughlin, Anna Rumshisky, Jimit Majmudar, Clement Chung, Salman Avestimehr, Rahul Gupta
2022	J	`jnl`	Federated Learning with Noisy User Feedback. CoRR Rahul Sharma, Anil Ramakrishna, Ansel MacLaughlin, Anna Rumshisky, Jimit Majmudar, Clement Chung, Salman Avestimehr, Rahul Gupta
2022	—	`conf`	Improving Large-Scale Conversational Assistants using Model Interpretation based Training Sample Selection. EMNLP (Industry Track) Stefan Schroedl, Manoj Kumar, Kiana Hajebi, Morteza Ziyadi, Sriram Venkatapathy, Anil Ramakrishna, Rahul Gupta, Pradeep Natarajan
2022	J	`jnl`	Joint Multi-Dimensional Model for Global and Time-Series Annotations. IEEE Trans. Affect. Comput. Anil Ramakrishna, Rahul Gupta, Shrikanth Narayanan
2021	—	`conf`	Towards Realistic Single-Task Continuous Learning Research for NER. EMNLP (Findings) Justin Payan, Yuval Merhav, He Xie, Satyapriya Krishna, Anil Ramakrishna, Mukund Sridhar, Rahul Gupta
2021	J	`jnl`	Towards Realistic Single-Task Continuous Learning Research for NER. CoRR Justin Payan, Yuval Merhav, He Xie, Satyapriya Krishna, Anil Ramakrishna, Mukund Sridhar, Rahul Gupta
2020	J	`jnl`	Joint Multi-Dimensional Model for Global and Time-Series Annotations. CoRR Anil Ramakrishna, Rahul Gupta, Shrikanth Narayanan
2020	A	`conf`	Sentence Level Estimation of Psycholinguistic Norms Using Joint Multidimensional Annotations. INTERSPEECH Anil Ramakrishna, Shrikanth Narayanan
2020	J	`jnl`	Sentence level estimation of psycholinguistic norms using joint multidimensional annotations. CoRR Anil Ramakrishna, Shrikanth Narayanan
2020	J	`jnl`	Victim or Perpetrator? Analysis of Violent Characters Portrayals from Movie Scripts. CoRR Victor R. Martinez, Krishna Somandepalli, Karan Singla, Anil Ramakrishna, Yalda T. Uhls, Shrikanth Narayanan
2019	B	`conf`	A system for the 2019 Sentiment, Emotion and Cognitive State Task of DARPA's LORELEI project. ACII Victor R. Martinez, Anil Ramakrishna, Ming-Chang Chiu, Karan Singla, Shrikanth S. Narayanan
2019	J	`jnl`	A system for the 2019 Sentiment, Emotion and Cognitive State Task of DARPAs LORELEI project. CoRR Victor R. Martinez, Anil Ramakrishna, Ming-Chang Chiu, Karan Singla, Shrikanth S. Narayanan
2019	A*	`conf`	Violence Rating Prediction from Movie Scripts. AAAI Victor R. Martinez, Krishna Somandepalli, Karan Singla, Anil Ramakrishna, Yalda T. Uhls, Shrikanth S. Narayanan
2018	A	`conf`	Computational Modeling of Conversational Humor in Psychotherapy. INTERSPEECH Anil Ramakrishna, Timothy Greer, David C. Atkins, Shrikanth S. Narayanan
2018	J	`jnl`	The ELISA Situation Frame extraction for low resource languages pipeline for LoReHLT'2016. Mach. Transl. Nikolaos Malandrakis, Anil Ramakrishna, Victor R. Martinez, Tanner Sorensen, Dogan Can, Shrikanth S. Narayanan
2017	—	`conf`	Linguistic analysis of differences in portrayal of movie characters. ACL (1) Anil Ramakrishna, Victor R. Martinez, Nikolaos Malandrakis, Karan Singla, Shrikanth S. Narayanan
2016	A	`conf`	An Expectation Maximization Approach to Joint Modeling of Multidimensional Ratings Derived from Multiple Annotators. INTERSPEECH Anil Ramakrishna, Rahul Gupta, Ruth B. Grossman, Shrikanth S. Narayanan
2015	A*	`conf`	A quantitative analysis of gender differences in movies using psycholinguistic normatives. EMNLP Anil Ramakrishna, Nikolaos Malandrakis, Elizabeth Staruk, Shrikanth S. Narayanan
2015	A	`conf`	Acoustic-prosodic correlates of 'awkward' prosody in story retellings from adolescents with autism. INTERSPEECH Daniel Bone, Matthew P. Black, Anil Ramakrishna, Ruth B. Grossman, Shrikanth S. Narayanan
2015	A	`conf`	Hierarchical Active Transfer Learning. SDM David C. Kale, Marjan Ghazvininejad, Anil Ramakrishna, Jingrui He, Yan Liu
2015	Misc	`conf`	On quantifying facial expression-related atypicality of children with Autism Spectrum Disorder. ICASSP Tanaya Guha, Zhaojun Yang, Anil Ramakrishna, Ruth B. Grossman, Darren Hedley, Sungbok Lee, Shrikanth S. Narayanan
2013	—	`conf`	An Interactive Web Based Spatio-Temporal Visualization System. ISVC (2) Anil Ramakrishna, Yu-Han Chang, Rajiv T. Maheswaran