Nikolaos Aletras

Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates ACL 2026 Enhancing Linguistic Competence of Language Models through Pre-training with Language Learning Tasks ACL 2026 Compressing Language Models for Specialized Domains EACL 2026 PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing EACL 2026 How Private are Language Models in Abstractive Summarization? EMNLP 2025 Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation? EMNLP 2025 Vocabulary-level Memory Efficiency for Language Model Fine-tuning NAACL 2025 Self-calibration for Language Model Quantization and Pruning NAACL 2025 Fine-Tuning on Noisy Instructions: Effects on Generalization and Performance IJCNLP 2025 Deconstructing Attention: Investigating Design Principles for Effective Language Modeling IJCNLP 2025 Deconstructing Attention: Investigating Design Principles for Effective Language Modeling AACL 2025 Fine-Tuning on Noisy Instructions: Effects on Generalization and Performance AACL 2025 GreekBarBench: A Challenging Benchmark for Free-Text Legal Reasoning and Citations EMNLP 2025 Enhancing Logical Reasoning in Language Models via Symbolically-Guided Monte Carlo Process Supervision EMNLP 2025 Improving Multimodal Classification of Social Media Posts by Leveraging Image-Text Auxiliary Tasks EACL 2024 On the Impact of Calibration Data in Post-training Quantization and Pruning ACL 2024 Enhancing Data Quality through Simple De-duplication: Navigating Responsible Computational Social Science Research EMNLP 2024 Navigating Prompt Complexity for Zero-Shot Classification: A Study of Large Language Models in Computational Social Science COLING 2024 RISE: Robust Early-exiting Internal Classifiers for Suicide Risk Evaluation COLING 2024 An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Language Model Inference EMNLP 2024 Bayesian Prompt Ensembles: Model Uncertainty Estimation for Black-Box Large Language Models ACL 2024 Who Is Bragging More Online? A Large Scale Analysis of Bragging in Social Media COLING 2024 Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models NAACL 2024 Examining the Limitations of Computational Rumor Detection Models Trained on Static Datasets COLING 2024 Rethinking Semi-supervised Learning with Language Models ACL 2023 Pit One Against Many: Leveraging Attention-head Embeddings for Parameter-efficient Multi-head Attention EMNLP 2023 Active Learning Principles for In-Context Learning with Large Language Models EMNLP 2023 Understanding the Role of Input Token Characters in Language Models: How Does Information Loss Affect Performance? EMNLP 2023 Regulation and NLP (RegNLP): Taming Large Language Models EMNLP 2023 It’s about Time: Rethinking Evaluation on Rumor Detection Benchmarks using Chronological Splits EACL 2023 We Need to Talk About Classification Evaluation Metrics in NLP IJCNLP 2023 A Multimodal Analysis of Influencer Content on Twitter IJCNLP 2023 Robust Weak Supervision with Variational Auto-Encoders ICML 2023 A Multimodal Analysis of Influencer Content on Twitter AACL 2023 We Need to Talk About Classification Evaluation Metrics in NLP AACL 2023 Schema-Guided User Satisfaction Modeling for Task-Oriented Dialogues ACL 2023 Incorporating Attribution Importance for Improving Faithfulness Metrics ACL 2023 Trading Syntax Trees for Wordpieces: Target-oriented Opinion Words Extraction with Wordpieces and Aspect Enhancement ACL 2023 On the Limitations of Simulating Active Learning ACL 2023 Flexible Instance-Specific Rationalization of NLP Models AAAI 2022 Improving Graph-Based Text Representations with Character and Word Level N-grams AACL 2022 Automatic Identification and Classification of Bragging in Social Media ACL 2022 LexGLUE: A Benchmark Dataset for Legal Language Understanding in English ACL 2022 An Empirical Study on Explanations in Out-of-Domain Settings ACL 2022 How does the pre-training objective affect what large language models learn about linguistic properties? ACL 2022 On the Importance of Effectively Adapting Pretrained Language Models for Active Learning ACL 2022 Dynamically Refined Regularization for Improving Cross-corpora Hate Speech Detection ACL 2022 Translation Error Detection as Rationale Extraction ACL 2022 Domain Classification-based Source-specific Term Penalization for Domain Adaptation in Hate-speech Detection COLING 2022 HashFormers: Towards Vocabulary-independent Pre-trained Transformers EMNLP 2022 A Hierarchical N-Gram Framework for Zero-Shot Link Prediction EMNLP 2022 On the Impact of Temporal Concept Drift on Model Explanations EMNLP 2022 Improving Graph-Based Text Representations with Character and Word Level N-grams IJCNLP 2022 Combining Humor and Sarcasm for Improving Political Parody Detection NAACL 2022 Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience EMNLP 2021 An Empirical Study on Leveraging Position Embeddings for Target-oriented Opinion Words Extraction EMNLP 2021 Active Learning by Acquiring Contrastive Examples EMNLP 2021 Knowledge Distillation for Quality Estimation ACL 2021 Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification IJCNLP 2021 In Factuality: Efficient Integration of Relevant Facts for Visual Question Answering IJCNLP 2021 On the Ethical Limits of Natural Language Processing on Legal Text IJCNLP 2021 Analyzing Online Political Advertisements IJCNLP 2021 Knowledge Distillation for Quality Estimation IJCNLP 2021 Point-of-Interest Type Prediction using Text and Images EMNLP 2021 Analyzing Online Political Advertisements ACL 2021 On the Ethical Limits of Natural Language Processing on Legal Text ACL 2021 In Factuality: Efficient Integration of Relevant Facts for Visual Question Answering ACL 2021 Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification ACL 2021 Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases NAACL 2021 Modeling the Severity of Complaints in Social Media NAACL 2021 Frustratingly Simple Pretraining Alternatives to Masked Language Modeling EMNLP 2021 Point-of-Interest Type Inference from Social Media Text AACL 2020 Complaint Identification in Social Media with Transformer Networks COLING 2020 An Empirical Study on Large-Scale Multi-Label Text Classification Including Few and Zero-Shot Labels EMNLP 2020 LEGAL-BERT: The Muppets straight out of Law School EMNLP 2020 Analyzing Political Parody in Social Media ACL 2020 Automatically Identifying Complaints in Social Media ACL 2019 Journalist-in-the-Loop: Continuous Learning as a Service for Rumour Analysis EMNLP 2019 Journalist-in-the-Loop: Continuous Learning as a Service for Rumour Analysis IJCNLP 2019 Extreme Multi-Label Legal Text Classification: A Case Study in EU Legislation NAACL 2019 Neural Legal Judgment Prediction in English ACL 2019 Proceedings of the Natural Legal Language Processing Workshop 2019 NAACL 2019 Multimodal Topic Labelling EACL 2017 An analysis of the user occupational class through Twitter content ACL 2015 An analysis of the user occupational class through Twitter content IJCNLP 2015 Labelling Topics using Unsupervised Graph-based Methods ACL 2014 Measuring the Similarity between Automatically Generated Topics EACL 2014 Predicting and Characterising User Impact on Twitter EACL 2014 Representing Topics Using Images NAACL 2013 PATHS: A System for Accessing Cultural Heritage Collections ACL 2013