Anil Ramakrishna

25 papers · 2015–2026 · 8 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (13) 🐣 Hot Topic Early Bird 🗺️ Taxonomy Completionist (64) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (8) 🏃 Academic Marathon (10) 🌈 Renaissance Researcher (7) 🤝 Dynamic Duo (14) 🧬 Topic Evolution 💎 Century Club (24) ⚡ Prolific Year (9) 🚀 Conference Pioneer 🗃️ Keyword Collector (104) 🔥 Unstoppable (11)

Conferences

EMNLP (8) ACL (4) INTERSPEECH (4) NAACL (4) EACL (2) AAAI (1) ICML (1) SEMEVAL (1)

Top co-authors

Rahul Gupta (14) Kai-Wei Chang (10) Mingyi Hong (6) Volkan Cevher (6) Zhiqi Bu (5) Bhanukiran Vinzamuri (5) Shrikanth Narayanan (5) Aram Galstyan (5) Ninareh Mehrabi (4) Xiaomeng Jin (4)

Research topics

Linguistics (1)

Keywords

large language model (9) machine unlearning (6) model editing (5) text classification (3) sentiment analysis (2) text generation (2) question answering (2) personally identifiable information (2) knowledge removal (2) model utility (2) dialogue system (2) data privacy (2) abusive language detection (1) natural language processing (1) named entity recognition (1) continual learning (1) kl divergence (1) responsible ai (1) text mining (1) sequence labeling (1)

Papers

BLUR: A Bi-Level Optimization Approach for LLM Unlearning EACL 2026

Not Every Token Needs Forgetting: Selective Unlearning Balancing Forgetting and Utility in Large Language Models EMNLP 2025

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation ACL 2025

SemEval-2025 Task 4: Unlearning sensitive content from Large Language Models ACL 2025

LUME: LLM Unlearning with Multitask Evaluations EMNLP 2025

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond ICML 2025

Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate NAACL 2025

Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs NAACL 2025

On Localizing and Deleting Toxic Memories in Large Language Models NAACL 2025

SemEval-2025 Task 4: Unlearning sensitive content from Large Language Models SEMEVAL 2025

Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM EMNLP 2024

Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification EMNLP 2024

Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs ACL 2024

Correcting Language Model Outputs by Editing Salient Layers EACL 2024

Sampling bias in NLU models: Impact and Mitigation INTERSPEECH 2023

INVITE: a Testbed of Automatically Generated Invalid Questions to Evaluate Large Language Models for Hallucinations EMNLP 2023

Federated Learning with Noisy User Feedback NAACL 2022

Improving Large-Scale Conversational Assistants using Model Interpretation based Training Sample Selection EMNLP 2022

Towards Realistic Single-Task Continuous Learning Research for NER EMNLP 2021

Sentence Level Estimation of Psycholinguistic Norms Using Joint Multidimensional Annotations INTERSPEECH 2020

Violence Rating Prediction from Movie Scripts AAAI 2019

Computational Modeling of Conversational Humor in Psychotherapy INTERSPEECH 2018

Linguistic analysis of differences in portrayal of movie characters ACL 2017

An Expectation Maximization Approach to Joint Modeling of Multidimensional Ratings Derived from Multiple Annotators INTERSPEECH 2016

A quantitative analysis of gender differences in movies using psycholinguistic normatives EMNLP 2015