Aram Galstyan

SWAN: Semantic Watermarking with Abstract Meaning Representation ACL 2026 ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System ACL 2026 SeRA: Self-Reviewing and Alignment of LLMs using Implicit Reward Margins ICLR 2025 Think Clearly: Improving Reasoning via Redundant Token Pruning EMNLP 2025 Mamba Drafters for Speculative Decoding EMNLP 2025 Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation ACL 2025 Accelerated Test-Time Scaling with Model-Free Speculative Sampling EMNLP 2025 Context Length Alone Hurts LLM Performance Despite Perfect Retrieval EMNLP 2025 On Localizing and Deleting Toxic Memories in Large Language Models NAACL 2025 Wanda++: Pruning Large Language Models via Regional Gradients ACL 2025 Tokenization Matters: Navigating Data-Scarce Tokenization for Gender Inclusive Language Technologies NAACL 2024 MICo: Preventative Detoxification of Large Language Models through Inhibition Control NAACL 2024 Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language Models EMNLP 2024 Correcting Language Model Outputs by Editing Salient Layers EACL 2024 Prompt Perturbation Consistency Learning for Robust Language Models EACL 2024 Ensembled Prediction Intervals for Causal Outcomes Under Hidden Confounding CLEAR 2024 BELIEVE: Belief-Enhanced Instruction Generation and Augmentation for Zero-Shot Bias Mitigation NAACL 2024 Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs ACL 2024 Contrastive Instruction Tuning ACL 2024 FLIRT: Feedback Loop In-context Red Teaming EMNLP 2024 Leveraging LLMs for Dialogue Quality Measurement NAACL 2024 The steerability of large language models toward data-driven personas NAACL 2024 Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification EMNLP 2024 Policy Learning for Localized Interventions from Observational Data AISTATS 2024 Agenda-Driven Question Generation: A Case Study in the Courtroom Domain COLING 2024 Domain Adaptation for Sentiment Analysis Using Robust Internal Representations EMNLP 2023 Graph Meets LLM: A Novel Approach to Collaborative Filtering for Robust Conversational Understanding EMNLP 2023 Overcoming Concept Shift in Domain-Aware Settings through Consolidated Internal Distributions AAAI 2023 Cognitively Inspired Learning of Incremental Drifting Concepts IJCAI 2023 ACCENT: An Automatic Event Commonsense Evaluation Metric for Open-Domain Dialogue Systems ACL 2023 ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation ACL 2023 Resolving Ambiguities in Text-to-Image Generative Models ACL 2023 Toward More Accurate and Generalizable Evaluation Metrics for Task-Oriented Dialogs ACL 2023 Measuring and Mitigating Local Instability in Deep Neural Networks ACL 2023 History repeats: Overcoming catastrophic forgetting for event-centric temporal knowledge graph completion ACL 2023 Neural Architecture Search for Parameter-Efficient Fine-tuning of Large Pre-trained Language Models ACL 2023 Jointly Reparametrized Multi-Layer Adaptation for Efficient and Private Tuning ACL 2023 Partial identification of dose responses with hidden confounders UAI 2023 Learning Under Label Noise for Robust Spoken Language Understanding systems INTERSPEECH 2022 DEAM: Dialogue Coherence Evaluation using AMR-based Semantic Manipulations ACL 2022 On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations ACL 2022 Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal ACL 2022 Attributing Fair Decisions with Attention Interventions NAACL 2022 StATIK: Structure and Text for Inductive Knowledge Graph Completion NAACL 2022 Temporal Generalization for Spoken Language Understanding NAACL 2022 Failure Modes of Domain Generalization Algorithms CVPR 2022 Robust Conversational Agents against Imperceptible Toxicity Triggers NAACL 2022 Unsupervised Syntactically Controlled Paraphrase Generation with Abstract Meaning Representations EMNLP 2022 Zero-Shot Cross-Lingual Sequence Tagging as Seq2Seq Generation for Joint Intent Classification and Slot Filling EMNLP 2022 Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources EMNLP 2021 Influence Decompositions For Neural Network Attribution AISTATS 2021 Layer-Wise Neural Network Compression via Layer Fusion ACML 2021 ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text Data ACL 2021 Exacerbating Algorithmic Bias through Fairness Attacks AAAI 2021 Information-theoretic generalization bounds for black-box learning algorithms NIPS 2021 Hamiltonian Dynamics with Non-Newtonian Momentum for Rapid Sampling NIPS 2021 Implicit SVD for Graph Representation Learning NIPS 2021 q-Paths: Generalizing the geometric annealing path using power means UAI 2021 Partner-Assisted Learning for Few-Shot Image Classification ICCV 2021 Graph Traversal with Tensor Functionals: A Meta-Algorithm for Scalable Learning ICLR 2021 ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text Data IJCNLP 2021 DiSCoL: Toward Engaging Dialogue Systems through Conversational Line Guided Response Generation NAACL 2021 Plot-guided Adversarial Example Construction for Evaluating Open-domain Story Generation NAACL 2021 MUSCLE: Strengthening Semi-Supervised Learning via Concurrent Unsupervised Learning Using Mutual Information Maximization WACV 2021 Predictive Engagement: An Efficient Metric for Automatic Evaluation of Open-Domain Dialogue Systems AAAI 2020 Modeling Dialogues with Hashcode Representations: A Nonparametric Approach AAAI 2020 All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference ICML 2020 Improving generalization by controlling label-noise information in neural network weights ICML 2020 Exact Rate-Distortion in Autoencoders via Echo Noise NIPS 2019 Fast structure learning with modular regularization NIPS 2019 Auto-Encoding Total Correlation Explanation AISTATS 2019 Nearly-Unsupervised Hashcode Representations for Biomedical Relation Extraction IJCNLP 2019 SAGE: A Hybrid Geopolitical Event Forecasting System IJCAI 2019 BioRelEx 1.0: Biological Relation Extraction Benchmark ACL 2019 Kernelized Hashcode Representations for Relation Extraction AAAI 2019 MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing ICML 2019 Better Automatic Evaluation of Open-Domain Dialogue Systems with Contextualized Embeddings NAACL 2019 Nearly-Unsupervised Hashcode Representations for Biomedical Relation Extraction EMNLP 2019 Deep Structured Neural Network for Event Temporal Relation Extraction CONLL 2019 Invariant Representations without Adversarial Training NIPS 2018 Sifting Common Information from Many Variables IJCAI 2017 Modeling Concept Dependencies in a Scientific Corpus ACL 2016 The Information Sieve ICML 2016 Variational Information Maximization for Feature Selection NIPS 2016 Efficient Estimation of Mutual Information for Strongly Dependent Variables AISTATS 2015 Maximally Informative Hierarchical Representations of High-Dimensional Data AISTATS 2015 Demystifying Information-Theoretic Clustering ICML 2014 Discovering Structure in High-Dimensional Data Through Correlation Explanation NIPS 2014 Statistical Tests for Contagion in Observational Social Network Studies AISTATS 2013 Comparative Analysis of Viterbi Training and Maximum Likelihood Estimation for HMMs NIPS 2011