Iryna Gurevych
178 publications
17 venues
H Index 51
Affiliation
Darmstadt University of Technology, Ubiquitous Knowledge Processing Lab, GermanyLinks
DBLPGoogle Scholar
ORCID- http://www.ukp.tu-darmstadt.de/people/gurevych
- http://www.academia-net.org/profil/prof-iryna-gurevych/1133751
- https://dl.acm.org/profile/81310490167
- https://en.wikipedia.org/wiki/Iryna_Gurevych
- https://www.wikidata.org/entity/Q21262416
- https://orkg.org/resource/R73218
- https://id.loc.gov/authorities/names/n2007055249
- https://d-nb.info/gnd/129096687
| Name | Venue | Year | citations |
|---|---|---|---|
SPARE: Single-Pass Annotation with Reference-Guided Evaluation for Automatic Process Supervision and Reward Modelling.
|
AAAI | 2026 | 0 |
| The Good, the Bad and the Constructive: Automatically Measuring Peer Review's Utility for Authors.
|
EMNLP | 2025 | 6 |
| LazyReview: A Dataset for Uncovering Lazy Thinking in NLP Peer Reviews.
|
ACL | 2025 | 0 |
| From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement Learning.
|
EMNLP | 2025 | 4 |
| Cultural Learning-Based Culture Adaptation of Language Models.
|
ACL | 2025 | 11 |
| From Surveys to Narratives: Rethinking Cultural Value Adaptation in LLMs.
|
EMNLP | 2025 | 2 |
| ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding.
|
ICLR | 2025 | 3 |
| Please meet AI, Our Dear New Colleague. In other Words: Can Scientists and Machines Truly Cooperate?
|
SIGIR | 2025 | 0 |
| Uncertainty-Aware Decoding with Minimum Bayes Risk.
|
ICLR | 2025 | 9 |
| \mathsfCon Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities.
|
ACL | 2025 | 0 |
| Differentially Private Steering for Large Language Model Alignment.
|
ICLR | 2025 | 10 |
| Droid: A Resource Suite for AI-Generated Code Detection.
|
EMNLP | 2025 | 6 |
| Towards Automated Error Discovery: A Study in Conversational AI.
|
EMNLP | 2025 | 0 |
| MathTutorBench: A Benchmark for Measuring Open-ended Pedagogical Capabilities of LLM Tutors.
|
EMNLP | 2025 | 26 |
| Modular Sentence Encoders: Separating Language Specialization from Cross-Lingual Alignment.
|
ACL | 2025 | 0 |
| Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs.
|
ACL | 2025 | 0 |
| STRICTA: Structured Reasoning in Critical Text Assessment for Peer Review and Beyond.
|
ACL | 2025 | 0 |
| The Nature of NLP: Analyzing Contributions in NLP Papers.
|
ACL | 2025 | 0 |
| Robust Utility-Preserving Text Anonymization Based on Large Language Models.
|
ACL | 2025 | 0 |
| OpenFactCheck: Building, Benchmarking Customized Fact-Checking Systems and Evaluating the Factuality of Claims and LLMs.
|
COLING | 2025 | 0 |
| Preemptive Detection and Correction of Misaligned Actions in LLM Agents.
|
EMNLP | 2025 | 0 |
| Turning Logic Against Itself: Probing Model Defenses Through Contrastive Questions.
|
EMNLP | 2025 | 0 |
| Are Large Language Models Good Classifiers? A Study on Edit Intent Classification in Scientific Document Revisions.
|
EMNLP | 2024 | 9 |
| Triple-Encoders: Representations That Fire Together, Wire Together.
|
ACL | 2024 | 2 |
| IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators.
|
ACL | 2024 | 22 |
| MixGR: Enhancing Retriever Generalization for Scientific Domain through Complementary Granularity.
|
EMNLP | 2024 | 11 |
| Document Structure in Long Document Transformers.
|
EACL | 2024 | 5 |
| Systematic Task Exploration with LLMs: A Study in Citation Text Generation.
|
ACL | 2024 | 12 |
| Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs.
|
EMNLP | 2024 | 18 |
| Attribute or Abstain: Large Language Models as Long Document Assistants.
|
EMNLP | 2024 | 9 |
| Zero-shot Sentiment Analysis in Low-Resource Languages Using a Multilingual Sentiment Lexicon.
|
EACL | 2024 | 28 |
| Variational Learning is Effective for Large Deep Networks.
|
ICML | 2024 | 49 |
| Like a Good Nearest Neighbor: Practical Content Moderation and Text Classification.
|
EACL | 2024 | 5 |
| Missci: Reconstructing Fallacies in Misrepresented Science.
|
ACL | 2024 | 13 |
| M4GT-Bench: Evaluation Benchmark for Black-Box Machine-Generated Text Detection.
|
ACL | 2024 | 67 |
| The Lou Dataset - Exploring the Impact of Gender-Fair Language in German Text Classification.
|
EMNLP | 2024 | 7 |
| Predicting Client Emotions and Therapist Interventions in Psychotherapy Dialogues.
|
EACL | 2024 | 4 |
| Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors.
|
EMNLP | 2024 | 30 |
| Re3: A Holistic Framework and Dataset for Modeling Collaborative Document Revision.
|
ACL | 2024 | 11 |
| SpaRC and SpaRP: Spatial Reasoning Characterization and Path Generation for Understanding Spatial Reasoning Capability of Large Language Models.
|
ACL | 2024 | 4 |
| Efficient Performance Tracking: Leveraging Large Language Models for Automated Construction of Scientific Leaderboards.
|
EMNLP | 2024 | 13 |
| DAPR: A Benchmark on Document-Aware Passage Retrieval.
|
ACL | 2024 | 0 |
| How to Handle Different Types of Out-of-Distribution Scenarios in Computational Argumentation? A Comprehensive and Fine-Grained Field Study.
|
ACL | 2024 | 0 |
| Are Emergent Abilities in Large Language Models just In-Context Learning?
|
ACL | 2024 | 0 |
| M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated Text Detection.
|
EACL | 2024 | 0 |
| CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration.
|
EACL | 2024 | 0 |
| Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting.
|
EACL | 2024 | 0 |
| Model Merging by Uncertainty-Based Gradient Matching.
|
ICLR | 2024 | 0 |
| "Image, Tell me your story!" Predicting the original meta-context of visual misinformation.
|
EMNLP | 2024 | 0 |
| Diversity Over Size: On the Effect of Sample and Topic Sizes for Topic-Dependent Argument Mining Datasets.
|
EMNLP | 2024 | 0 |
| Learning From Free-Text Human Feedback - Collect New Datasets Or Extend Existing Ones?
|
EMNLP | 2023 | 8 |
| AdaSent: Efficient Domain-Adapted Sentence Embeddings for Few-Shot Classification.
|
EMNLP | 2023 | 4 |
| A Diachronic Analysis of Paradigm Shifts in NLP Research: When, How, and Why?
|
EMNLP | 2023 | 9 |
| Exploring Jiu-Jitsu Argumentation for Writing Peer Review Rebuttals.
|
EMNLP | 2023 | 18 |
| A Dataset of Argumentative Dialogues on Scientific Papers.
|
ACL | 2023 | 19 |
| SPRINT: A Unified Toolkit for Evaluating and Demystifying Zero-shot Neural Sparse Retrieval.
|
SIGIR | 2023 | 5 |
| Lessons Learned from a Citizen Science Project for Natural Language Processing.
|
EACL | 2023 | 4 |
| Opportunities and Challenges in Neural Dialog Tutoring.
|
EACL | 2023 | 39 |
| NLPeer: A Unified Resource for the Computational Study of Peer Review.
|
ACL | 2023 | 0 |
| An Inclusive Notion of Text.
|
ACL | 2023 | 0 |
| Python Code Generation by Asking Clarification Questions.
|
ACL | 2023 | 0 |
| The Devil is in the Details: On Models and Training Regimes for Few-Shot Intent Classification.
|
EACL | 2023 | 0 |
| MetaQA: Combining Expert Agents for Multi-Skill Question Answering.
|
EACL | 2023 | 0 |
| Semantic Similarity Models for Depression Severity Estimation.
|
EMNLP | 2023 | 0 |
| CiteBench: A Benchmark for Scientific Citation Text Generation.
|
EMNLP | 2023 | 0 |
| Missing Counter-Evidence Renders NLP Fact-Checking Unrealistic for Misinformation.
|
EMNLP | 2022 | 61 |
| Incorporating Relevance Feedback for Information-Seeking Retrieval using Few-Shot Document Re-Ranking.
|
EMNLP | 2022 | 7 |
| FigMemes: A Dataset for Figurative Language Identification in Politically-Opinionated Memes.
|
EMNLP | 2022 | 32 |
| IMPLI: Investigating NLI Models' Performance on Figurative Language.
|
ACL | 2022 | 0 |
| Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning.
|
EMNLP | 2021 | 37 |
| Event Coreference Data (Almost) for Free: Mining Hyperlinks from Online News.
|
EMNLP | 2021 | 10 |
| Improving Factual Consistency Between a Response and Persona Facts.
|
EACL | 2021 | 32 |
| Exploring Metaphoric Paraphrase Generation.
|
CoNLL | 2021 | 31 |
| Structural Adapters in Pretrained Language Models for AMR-to-Text Generation.
|
EMNLP | 2021 | 80 |
| What to Pre-Train on? Efficient Intermediate Task Selection.
|
EMNLP | 2021 | 107 |
| Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation.
|
EMNLP | 2021 | 12 |
| AdapterFusion: Non-Destructive Task Composition for Transfer Learning.
|
EACL | 2021 | 0 |
| AdapterDrop: On the Efficiency of Adapters in Transformers.
|
EMNLP | 2021 | 0 |
| UNKs Everywhere: Adapting Multilingual Language Models to New Scripts.
|
EMNLP | 2021 | 0 |
| A matter of framing: The impact of linguistic formalism on probing results.
|
EMNLP | 2020 | 28 |
| Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation.
|
EMNLP | 2020 | 1246 |
| Low Resource Sequence Tagging with Weak Labels.
|
AAAI | 2020 | 14 |
| MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer.
|
EMNLP | 2020 | 716 |
| How to Probe Sentence Embeddings in Low-Resource Languages: On Structural Design Choices for Probing Task Evaluation.
|
CoNLL | 2020 | 12 |
| Empowering Active Learning to Jointly Optimize System and User Demands.
|
ACL | 2020 | 11 |
| Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance.
|
ACL | 2020 | 134 |
| From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains.
|
ACL | 2020 | 54 |
| MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale.
|
EMNLP | 2020 | 39 |
| PuzzLing Machines: A Challenge on Learning From Small Data.
|
ACL | 2020 | 23 |
| Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings.
|
ICLR | 2020 | 38 |
| Towards Debiasing NLU Models from Unknown Biases.
|
EMNLP | 2020 | 165 |
| Fine-Grained Argument Unit Recognition and Classification.
|
AAAI | 2020 | 0 |
| Two Birds with One Stone: Investigating Invertible Neural Networks for Inverse Problems in Morphology.
|
AAAI | 2020 | 0 |
| Dialogue Coherence Assessment Without Explicit Dialogue Act Labels.
|
ACL | 2020 | 0 |
| Scalable Bayesian preference learning for crowds.
|
MLJ | 2020 | 0 |
| Analysis of Automatic Annotation Suggestions for Hard Discourse-Level Tasks in Expert Domains.
|
ACL | 2019 | 19 |
| Reward Learning for Efficient Reinforcement Learning in Extractive Document Summarisation.
|
IJCAI | 2019 | 26 |
| A Richly Annotated Corpus for Different Tasks in Automated Fact-Checking.
|
CoNLL | 2019 | 133 |
| Improved Cross-Lingual Question Retrieval for Community Question Answering.
|
WWW | 2019 | 27 |
| Classification and Clustering of Arguments with Contextualized Word Embeddings.
|
ACL | 2019 | 189 |
| Ranking Generated Summaries by Correctness: An Interesting but Challenging Application for Natural Language Inference.
|
ACL | 2019 | 334 |
| Predicting Humorousness and Metaphor Novelty with Gaussian Process Preference Learning.
|
ACL | 2019 | 36 |
| COALA: A Neural Coverage-Based Approach for Long Answer Selection with Small Data.
|
AAAI | 2019 | 22 |
| Challenges in the Automatic Analysis of Students' Diagnostic Reasoning.
|
AAAI | 2019 | 0 |
| Is it Time to Swish? Comparing Deep Learning Activation Functions Across NLP tasks.
|
EMNLP | 2018 | 83 |
| Corpus-Driven Thematic Hierarchy Induction.
|
CoNLL | 2018 | 2 |
| Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answering.
|
COLING | 2018 | 103 |
| APRIL: Interactively Learning to Summarise by Combining Active Preference Learning and Reinforcement Learning.
|
EMNLP | 2018 | 34 |
| From Text to Lexicon: Bridging the Gap between Word Embeddings and Lexical Resources.
|
COLING | 2018 | 9 |
| Killing Four Birds with Two Stones: Multi-Task Learning for Non-Literal Language Detection.
|
COLING | 2018 | 9 |
| Cross-topic Argument Mining from Heterogeneous Sources.
|
EMNLP | 2018 | 212 |
| A Retrospective Analysis of the Fake News Challenge Stance-Detection Task.
|
COLING | 2018 | 261 |
| Weeding out Conventionalized Metaphors: A Corpus of Novel Metaphor Annotations.
|
EMNLP | 2018 | 33 |
| Multimodal Grounding for Language Processing.
|
COLING | 2018 | 37 |
| Cross-lingual Argumentation Mining: Machine Translation (and a bit of Projection) is All You Need!
|
COLING | 2018 | 53 |
| Integrating Deep Linguistic Features in Factuality Prediction over Unified Datasets.
|
ACL | 2017 | 45 |
| Metaheuristic Approaches to Lexical Substitution and Simplification.
|
EACL | 2017 | 8 |
| Out-of-domain FrameNet Semantic Role Labeling.
|
EACL | 2017 | 62 |
| Context-Aware Representations for Knowledge Base Relation Extraction.
|
EMNLP | 2017 | 163 |
| Bringing Structure into Summaries: Crowdsourcing a Benchmark Corpus of Concept Maps.
|
EMNLP | 2017 | 34 |
| Neural End-to-End Learning for Computational Argumentation Mining.
|
ACL | 2017 | 213 |
| Recognizing Insufficiently Supported Arguments in Argumentative Essays.
|
EACL | 2017 | 90 |
| Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Tagging.
|
EMNLP | 2017 | 454 |
| What is the Essence of a Claim? Cross-Domain Claim Identification.
|
EMNLP | 2017 | 101 |
| Argumentation Quality Assessment: Theory vs. Practice.
|
ACL | 2017 | 75 |
| Modeling Extractive Sentence Intersection via Subtree Entailment.
|
COLING | 2016 | 3 |
| Supersense Embeddings: A Unified Model for Supersense Interpretation, Prediction, and Utilization.
|
ACL | 2016 | 60 |
| What makes a convincing argument? Empirical analysis and detecting attributes of convincingness in Web argumentation.
|
EMNLP | 2016 | 126 |
| Which argument is more convincing? Analyzing and predicting convincingness of Web arguments using bidirectional LSTM.
|
ACL | 2016 | 239 |
| Still not there? Comparing Traditional Sequence-to-Sequence Models to Encoder-Decoder Neural Networks on Monotone String Translation Tasks.
|
COLING | 2016 | 37 |
| Semi-automatic Detection of Cross-lingual Marketing Blunders based on Pragmatic Label Propagation in Wiktionary.
|
COLING | 2016 | 2 |
| CNN- and LSTM-based Claim Classification in Online User Comments.
|
COLING | 2016 | 75 |
| New Collection Announcement: Focused Retrieval Over the Web.
|
SIGIR | 2016 | 18 |
| Bridging the gap between extractive and abstractive summaries: Creation and evaluation of coherent extracts from heterogeneous sources.
|
COLING | 2016 | 22 |
| Task-Oriented Intrinsic Evaluation of Semantic Textual Similarity.
|
COLING | 2016 | 74 |
| Porting an Open Information Extraction System from English to German.
|
EMNLP | 2016 | 19 |
| Temporal Anchoring of Events for the TimeBank Corpus.
|
ACL | 2016 | 43 |
| On the Role of Discourse Markers for Discriminating Claims and Premises in Argumentative Discourse.
|
EMNLP | 2015 | 98 |
| Exploiting Debate Portals for Semi-Supervised Argumentation Mining in User-Generated Web Discourse.
|
EMNLP | 2015 | 90 |
| Personality Profiling of Fictional Characters using Sense-Level Links between Lexical Resources.
|
EMNLP | 2015 | 55 |
| Automatic disambiguation of English puns.
|
ACL | 2015 | 64 |
| Noise or additional information? Leveraging crowdsource annotation item agreement for natural language tasks.
|
EMNLP | 2015 | 0 |
| What makes a good biography?: multidimensional quality analysis based on wikipedia article feedback data.
|
WWW | 2014 | 27 |
| Automatically Detecting Corresponding Edit-Turn-Pairs in Wikipedia.
|
ACL | 2014 | 7 |
| High Performance Word Sense Alignment by Joint Modeling of Sense Distance and Gloss Similarity.
|
COLING | 2014 | 9 |
| Identifying Argumentative Discourse Structures in Persuasive Essays.
|
EMNLP | 2014 | 420 |
| Annotating Argument Components and Relations in Persuasive Essays.
|
COLING | 2014 | 367 |
| Automated Verb Sense Labelling Based on Linked Lexical Resources.
|
EACL | 2014 | 7 |
| Large-Scale Multi-label Text Classification - Revisiting Neural Networks.
|
ECML/PKDD | 2014 | 0 |
| Automatically Classifying Edit Categories in Wikipedia Revisions.
|
EMNLP | 2013 | 64 |
| Uncertainty Detection for Natural Language Watermarking.
|
IJCNLP | 2013 | 2 |
| Recognizing Partial Textual Entailment.
|
ACL | 2013 | 40 |
| The Impact of Topic Bias on Quality Flaw Prediction in Wikipedia.
|
ACL | 2013 | 16 |
| Cognate Production using Character-based Machine Translation.
|
IJCNLP | 2013 | 48 |
| FrameNet on the Way to Babel: Creating a Bilingual FrameNet Using Wiktionary as Interlingual Connection.
|
ACL | 2013 | 23 |
| Subcat-LMF: Fleshing out a standardized format for subcategorization frame interoperability.
|
EACL | 2012 | 10 |
| A Corpus-Based Study of Edit Categories in Featured and Non-Featured Wikipedia Articles.
|
COLING | 2012 | 55 |
| UBY - A Large-Scale Unified Lexical-Semantic Resource Based on LMF.
|
EACL | 2012 | 161 |
| Using Distributional Similarity for Lexical Expansion in Knowledge-based Word Sense Disambiguation.
|
COLING | 2012 | 66 |
| To Exhibit is not to Loiter: A Multilingual, Sense-Disambiguated Wiktionary for Measuring Verb Similarity.
|
COLING | 2012 | 26 |
| Text Reuse Detection using a Composition of Text Similarity Measures.
|
COLING | 2012 | 59 |
| Behind the Article: Recognizing Dialog Acts in Wikipedia Talk Pages.
|
EACL | 2012 | 80 |
| Combining Query Translation Techniques to Improve Cross-Language Information Retrieval.
|
ECIR | 2011 | 29 |
| What Psycholinguists Know About Chemistry: Aligning Wiktionary and WordNet for Increased Domain Coverage.
|
IJCNLP | 2011 | 69 |
| A Monolingual Tree-based Translation Model for Sentence Simplification.
|
COLING | 2010 | 449 |
| Using Anaphora Resolution to Improve Opinion Target Identification in Movie Reviews.
|
ACL | 2010 | 59 |
| Extracting Opinion Targets in a Single and Cross-Domain Setting with Conditional Random Fields.
|
EMNLP | 2010 | 532 |
| Sentence and Expression Level Annotation of Opinions in User-Generated Discourse.
|
ACL | 2010 | 170 |
| Semantically Enhanced Term Frequency.
|
ECIR | 2010 | 5 |
| What helps where - and why? Semantic relatedness for knowledge transfer.
|
CVPR | 2010 | 0 |
| A Study on the Semantic Relatedness of Query and Document Terms in Information Retrieval.
|
EMNLP | 2009 | 23 |
| Using tag semantic network for keyphrase extraction in blogs.
|
CIKM | 2008 | 14 |
| Using Wiktionary for Computing Semantic Relatedness.
|
AAAI | 2008 | 186 |
| What to be? - Electronic Career Guidance Based on Semantic Relatedness.
|
ACL | 2007 | 60 |
| Automatically Assessing the Post Quality in Online Discussions on Software.
|
ACL | 2007 | 113 |
| Using the Structure of a Conceptual Network in Computing Semantic Relatedness.
|
IJCNLP | 2005 | 130 |
| Accessing GermaNet Data and Computing Semantic Relatedness.
|
ACL | 2005 | 10 |
| Semantic Similarity Applied to Spoken Dialogue Summarization.
|
COLING | 2004 | 73 |