Mihai Surdeanu

Structured Semantic Information Helps Retrieve Better Examples for In-Context Learning Applied to Few-Shot Relation Extraction ACL 2026 A Lightweight Explainable Guardrail for Prompt Safety ACL 2026 Can LLMs Judge Debates? Evaluating Non-Linear Reasoning via Argumentation Theory Semantics EMNLP 2025 Relation-Aware Prompting Makes Large Language Models Effective Zero-shot Relation Extractors EMNLP 2025 The Alchemy of Thought: Understanding In-Context Learning Through Supervised Classification IJCNLP 2025 How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark EMNLP 2025 The Alchemy of Thought: Understanding In-Context Learning Through Supervised Classification AACL 2025 Fane at SemEval-2025 Task 10: Zero-Shot Entity Framing with Large Language Models SEMEVAL 2025 MorphNLI: A Stepwise Approach to Natural Language Inference Using Text Morphing NAACL 2025 CopySpec: Accelerating LLMs with Speculative Copy-and-Paste EMNLP 2025 Variable Layerwise Quantization: A Simple and Effective Approach to Quantize LLMs ACL 2025 The Lies Characters Tell: Utilizing Large Language Models to Normalize Adversarial Unicode Perturbations ACL 2025 Fane at SemEval-2025 Task 10: Zero-Shot Entity Framing with Large Language Models ACL 2025 A Framework to Retrieve Relevant Laws for Will Execution EMNLP 2025 Change Is the Only Constant: Dynamic LLM Slicing based on Layer Redundancy EMNLP 2024 ELLEN: Extremely Lightly Supervised Learning for Efficient Named Entity Recognition COLING 2024 Towards Realistic Few-Shot Relation Extraction: A New Meta Dataset and Evaluation COLING 2024 Retrieval Augmented Generation of Subjective Explanations for Socioeconomic Scenarios NAACL 2024 Best of Both Worlds: A Pliable and Generalizable Neuro-Symbolic Approach for Relation Classification NAACL 2024 Classify First, and Then Extract: Prompt Chaining Technique for Information Extraction EMNLP 2024 Active Learning Design Choices for NER with Transformers COLING 2024 Time Travel in LLMs: Tracing Data Contamination in Large Language Models ICLR 2024 The Grid: A semi-automated tool to support expert-driven modeling EMNLP 2024 Data Contamination Report from the 2024 CONDA Shared Task ACL 2024 When and Where Did it Happen? An Encoder-Decoder Model to Identify Scenario Context EMNLP 2024 Improving Zero-shot Relation Classification via Automatically-acquired Entailment Templates ACL 2023 NEUROSTRUCTURAL DECODING: Neural Text Generation with Structural Constraints ACL 2023 Bootstrapping Neural Relation and Explanation Classifiers ACL 2023 It’s not Sexually Suggestive; It’s Educative | Separating Sex Education from Suggestive Content on TikTok videos ACL 2023 Synthetic Dataset for Evaluating Complex Compositional Knowledge for Natural Language Inference ACL 2023 Do not Mask Randomly: Effective Domain-adaptive Pre-training by Masking In-domain Keywords ACL 2023 Annotating and Training for Population Subjective Views ACL 2023 Transferring Legal Natural Language Inference Model from a US State to Another: What Makes It So Hard? EMNLP 2023 Information Extraction from Legal Wills: How Well Does GPT-4 Do? EMNLP 2023 Hiding in Plain Sight: Tweets with Hate Speech Masked by Homoglyphs EMNLP 2023 PatternRank: Jointly Ranking Patterns and Extractions for Relation Extraction Using Graph-Based Algorithms COLING 2022 Taxonomy Builder: a Data-driven and User-centric Tool for Streamlining Taxonomy Construction NAACL 2022 BioNLI: Generating a Biomedical NLI Dataset Using Lexico-semantic Constraints for Adversarial Examples EMNLP 2022 Combining Extraction and Generation for Constructing Belief-Consequence Causal Links ACL 2022 Low Resource Causal Event Detection from Biomedical Literature ACL 2022 Learning Open Domain Multi-hop Search Using Reinforcement Learning NAACL 2022 Validity Assessment of Legal Will Statements as Natural Language Inference EMNLP 2022 A Human-machine Interface for Few-shot Rule Synthesis for Information Extraction NAACL 2022 Interpretability Rules: Jointly Bootstrapping a Neural Relation Extractorwith an Explanation Decoder NAACL 2021 Explainable Multi-hop Verbal Reasoning Through Internal Monologue NAACL 2021 Students Who Study Together Learn Better: On the Importance of Collective Knowledge Distillation for Domain Transfer in Fact Verification EMNLP 2021 How May I Help You? Using Neural Text Simplification to Improve Downstream NLP Tasks EMNLP 2021 If You Want to Go Far Go Together: Unsupervised Joint Candidate Evidence Retrieval for Multi-hop Question Answering NAACL 2021 Data and Model Distillation as a Solution for Domain-transferable Fact Verification NAACL 2021 An Unsupervised Method for Learning Representations of Multi-word Expressions for Semantic Classification COLING 2020 Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering ACL 2020 Exploring Interpretability in Event Extraction: Multitask Learning of a Neural Event Classifier and an Explanation Decoder ACL 2020 An Analysis of Capsule Networks for Part of Speech Tagging in High- and Low-resource Scenarios EMNLP 2020 Do Transformers Dream of Inference, or Can Pretrained Generative Models Learn Implicit Inferential Rules? EMNLP 2020 Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering IJCNLP 2019 Alignment over Heterogeneous Embeddings for Question Answering NAACL 2019 Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13) EMNLP 2019 Eidos, INDRA, & Delphi: From Free Text to Executable Causal Models NAACL 2019 Enabling Search and Collaborative Assembly of Causal Interactions Extracted from Multilingual and Multi-domain Free Text NAACL 2019 On the Importance of Delexicalization for Fact Verification EMNLP 2019 Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering EMNLP 2019 Lightly-supervised Representation Learning with Global Interpretability NAACL 2019 Semi-Supervised Teacher-Student Architecture for Relation Extraction NAACL 2019 What does the language of foods say about us? EMNLP 2019 University of Arizona at SemEval-2019 Task 12: Deep-Affix Named Entity Recognition of Geolocation Entities SEMEVAL 2019 Understanding the Polarity of Events in the Biomedical Literature: Deep Learning vs. Linguistically-informed Methods NAACL 2019 On the Importance of Delexicalization for Fact Verification IJCNLP 2019 Scientific Discovery as Link Prediction in Influence and Citation Graphs NAACL 2018 Detecting Diabetes Risk from Social Media Activity EMNLP 2018 A mostly unlexicalized model for recognizing textual entailment EMNLP 2018 Visual Supervision in Bootstrapped Information Extraction EMNLP 2018 An Exploration of Three Lightly-supervised Representation Learning Approaches for Named Entity Classification COLING 2018 Keep Your Bearings: Lightly-Supervised Information Extraction with Ladder Networks That Avoids Semantic Drift NAACL 2018 Tell Me Why: Using Question Answering as Distant Supervision for Answer Justification CONLL 2017 Swanson linking revisited: Accelerating literature-based discovery across domains using a conceptual influence graph ACL 2017 Learning what to read: Focused machine reading EMNLP 2017 What’s in an Explanation? Characterizing Knowledge and Inference Requirements for Elementary Science Exams COLING 2016 Creating Causal Embeddings for Question Answering with Minimal Supervision EMNLP 2016 A Domain-independent Rule-based Framework for Event Extraction ACL 2015 Diamonds in the Rough: Event Extraction from Imperfect Microblog Data NAACL 2015 Two Practical Rhetorical Structure Theory Parsers NAACL 2015 Spinning Straw into Gold: Using Free Text to Train Monolingual Alignment Models for Non-factoid Question Answering NAACL 2015 A Domain-independent Rule-based Framework for Event Extraction IJCNLP 2015 Discourse Complements Lexical Semantics for Non-factoid Answer Reranking ACL 2014 The Stanford CoreNLP Natural Language Processing Toolkit ACL 2014 Joint Entity and Event Coreference Resolution across Documents CONLL 2012 Joint Entity and Event Coreference Resolution across Documents EMNLP 2012 Multi-instance Multi-label Learning for Relation Extraction CONLL 2012 Multi-instance Multi-label Learning for Relation Extraction EMNLP 2012 Event Extraction as Dependency Parsing ACL 2011 Stanford’s Multi-Pass Sieve Coreference Resolution System at the CoNLL-2011 Shared Task CONLL 2011 Improving Semantic Role Classification with Selectional Preferences NAACL 2010 A Multi-Pass Sieve for Coreference Resolution EMNLP 2010 Ensemble Models for Dependency Parsing: Cheap and Good? NAACL 2010 Company-Oriented Extractive Summarization of Financial News EACL 2009 The CoNLL-2009 Shared Task: Syntactic and Semantic Dependencies in Multiple Languages CONLL 2009 Learning to Rank Answers on Large Online QA Collections ACL 2008 DeSRL: A Linear-Time Semantic Role Labeling System CONLL 2008 The CoNLL 2008 Shared Task on Joint Parsing of Syntactic and Semantic Dependencies CONLL 2008 UPC: Experiments with Joint Learning within SemEval Task 9 SEMEVAL 2007 Projective Dependency Parsing with Perceptron CONLL 2006 A Robust Combination Strategy for Semantic Role Labeling EMNLP 2005 Semantic Role Labeling Using Complete Syntactic Analysis CONLL 2005 Using Predicate-Argument Structures for Information Extraction ACL 2003 Performance Issues and Error Analysis in an Open-Domain Question Answering System ACL 2002 The Role of Lexico-Semantic Feedback in Open-Domain Textual Question-Answering ACL 2001