Alexander Panchenko

DimABSA: Building Multilingual and Multidomain Datasets for Dimensional Aspect-Based Sentiment Analysis ACL 2026 Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs ACL 2026 The Silence of the Facts: Popularity as a Barrier to Machine Unlearning ACL 2026 From Standard Transformers to Modern LLMs: Bringing Dialogue Models, RAG, and Agents to the Classroom EACL 2026 Detecting Overflow in Compressed Token Representations for Retrieval-Augmented Generation EACL 2026 Acceleration of Backpropagation in Linear Layers of Transformer Models Based on Gradient Structure EACL 2026 Fine-Grained Semantic Comparison of Legal Documents using LLMs ACL 2026 Boosting Self-Consistency with Ranking ACL 2026 Multimodal Evaluation of Russian-language Architectures EACL 2026 Evolutionary Search for Automated Design of Uncertainty Quantification Methods ACL 2026 When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA EMNLP 2025 Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA EMNLP 2025 LLM-Independent Adaptive RAG: Let the Question Speak for Itself EMNLP 2025 Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models EMNLP 2025 When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs EMNLP 2025 SmurfCat at SHROOM-CAP: Factual but Awkward? Fluent but Wrong? Tackling Both in LLM Scientific QA AACL 2025 SemEval-2025 Task 11: Bridging the Gap in Text-Based Emotion Detection SEMEVAL 2025 SmurfCat at SemEval-2025 Task 3: Bridging External Knowledge and Model Uncertainty for Enhanced Hallucination Detection SEMEVAL 2025 TabaQA at SemEval-2025 Task 8: Column Augmented Generation for Question Answering over Tabular Data SEMEVAL 2025 Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home ACL 2025 BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages ACL 2025 HatePRISM: Policies, Platforms, and Research Integration. Advancing NLP for Hate Speech Proactive Mitigation ACL 2025 TabaQA at SemEval-2025 Task 8: Column Augmented Generation for Question Answering over Tabular Data ACL 2025 SmurfCat at SemEval-2025 Task 3: Bridging External Knowledge and Model Uncertainty for Enhanced Hallucination Detection ACL 2025 SemEval-2025 Task 11: Bridging the Gap in Text-Based Emotion Detection ACL 2025 How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM? NAACL 2025 SkipCLM: Enhancing Crosslingual Alignment of Decoder Transformer Models via Contrastive Learning and Skip Connection NAACL 2025 Multilingual and Explainable Text Detoxification with Parallel Corpora COLING 2025 On Reducing Factual Hallucinations in Graph-to-Text Generation Using Large Language Models COLING 2025 RAGulator: Effective RAG for Regulatory Question Answering COLING 2025 Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images NAACL 2025 SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators NAACL 2025 Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models NAACL 2025 SmurfCat at SHROOM-CAP: Factual but Awkward? Fluent but Wrong? Tackling Both in LLM Scientific QA IJCNLP 2025 TextGraphs 2024 Shared Task on Text-Graph Representations for Knowledge Graph Question Answering ACL 2024 SparseGrad: A Selective Method for Efficient Fine-tuning of MLP Layers EMNLP 2024 SmurfCat at SemEval-2024 Task 6: Leveraging Synthetic Data for Hallucination Detection NAACL 2024 MultiParaDetox: Extending Text Detoxification with Parallel Data to New Languages NAACL 2024 SmurfCat at SemEval-2024 Task 6: Leveraging Synthetic Data for Hallucination Detection SEMEVAL 2024 LLMs to Replace Crowdsourcing For Parallel Data Creation? The Case of Text Detoxification EMNLP 2024 xCOMET-lite: Bridging the Gap Between Efficiency and Quality in Learned MT Evaluation Metrics EMNLP 2024 Are Large Language Models Good at Lexical Semantics? A Case of Taxonomy Learning COLING 2024 CAM 2.0: End-to-End Open Domain Comparative Question Answering System COLING 2024 OmniDialog: A Multimodal Benchmark for Generalization Across Text, Visual, and Audio Modalities EMNLP 2024 TaxoLLaMA: WordNet-based Model for Solving Multiple Lexical Semantic Tasks ACL 2024 MERA: A Comprehensive LLM Evaluation in Russian ACL 2024 Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification ACL 2024 Super donors and super recipients: Studying cross-lingual transfer between high-resource and low-resource languages ACL 2024 Industry vs Academia: Running a Course on Transformers in Two Setups ACL 2024 Predicting Terms in IS-A Relations with Pre-trained Transformers IJCNLP 2023 Graph-Enriched Biomedical Language Models: A Research Proposal IJCNLP 2023 Exploring Methods for Cross-lingual Text Style Transfer: The Case of Text Detoxification IJCNLP 2023 Uncertainty Estimation for Debiased Models: Does Fairness Hurt Reliability? IJCNLP 2023 Uncertainty Estimation for Debiased Models: Does Fairness Hurt Reliability? AACL 2023 Kandinsky: An Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion EMNLP 2023 Exploring Methods for Cross-lingual Text Style Transfer: The Case of Text Detoxification AACL 2023 Graph-Enriched Biomedical Language Models: A Research Proposal AACL 2023 Predicting Terms in IS-A Relations with Pre-trained Transformers AACL 2023 LM-Polygraph: Uncertainty Estimation for Language Models EMNLP 2023 Team NLLG submission for Eval4NLP 2023 Shared Task: Retrieval-Augmented In-Context Learning for NLG Evaluation IJCNLP 2023 Team NLLG submission for Eval4NLP 2023 Shared Task: Retrieval-Augmented In-Context Learning for NLG Evaluation AACL 2023 Efficient Out-of-Domain Detection for Sequence to Sequence Models ACL 2023 Hybrid Uncertainty Quantification for Selective Text Classification in Ambiguous Tasks ACL 2023 Semantically-Informed Regressive Encoder Score EMNLP 2023 A System for Answering Simple Questions in Multiple Languages ACL 2023 Pixel-Level BPE for Auto-Regressive Image Generation COLING 2022 ParaDetox: Detoxification with Parallel Data ACL 2022 Uncertainty Estimation of Transformer Predictions for Misclassification Detection ACL 2022 A large-scale computational study of content preservation measures for text style transfer and paraphrase generation ACL 2022 Exploring Cross-lingual Text Detoxification with Large Multilingual Language Models. ACL 2022 MEKER: Memory Efficient Knowledge Embedding Representation for Link Prediction and Question Answering ACL 2022 A Study on Manual and Automatic Evaluation for Text Style Transfer: The Case of Detoxification ACL 2022 TaxFree: a Visualization Tool for Candidate-free Taxonomy Enrichment AACL 2022 Cross-Modal Contextualized Hidden State Projection Method for Expanding of Taxonomic Graphs COLING 2022 Active Learning for Abstractive Text Summarization EMNLP 2022 TaxFree: a Visualization Tool for Candidate-free Taxonomy Enrichment IJCNLP 2022 SkoltechNLP at SemEval-2022 Task 8: Multilingual News Article Similarity via Exploration of News Texts to Vector Representations NAACL 2022 SkoltechNLP at SemEval-2022 Task 8: Multilingual News Article Similarity via Exploration of News Texts to Vector Representations SEMEVAL 2022 SkoltechNLP at SemEval-2021 Task 5: Leveraging Sentence-level Pre-training for Toxic Span Detection IJCNLP 2021 Text Detoxification using Large Pre-trained Neural Models EMNLP 2021 Evaluation of Taxonomy Enrichment on Diachronic WordNet Versions EACL 2021 Detecting Inappropriate Messages on Sensitive Topics that Could Harm a Company’s Reputation EACL 2021 Which is Better for Deep Learning: Python or MATLAB? Answering Comparative Questions in Natural Language EACL 2021 How Certain is Your Transformer? EACL 2021 Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates EACL 2021 SkoltechNLP at SemEval-2021 Task 2: Generating Cross-Lingual Training Data for the Word-in-Context Task SEMEVAL 2021 SkoltechNLP at SemEval-2021 Task 5: Leveraging Sentence-level Pre-training for Toxic Span Detection SEMEVAL 2021 SkoltechNLP at SemEval-2021 Task 5: Leveraging Sentence-level Pre-training for Toxic Span Detection ACL 2021 SkoltechNLP at SemEval-2021 Task 2: Generating Cross-Lingual Training Data for the Word-in-Context Task ACL 2021 Documents Representation via Generalized Coupled Tensor Chain with the Rotation Group constraint ACL 2021 Cross-lingual Evidence Improves Monolingual Fake News Detection ACL 2021 Cross-lingual Evidence Improves Monolingual Fake News Detection IJCNLP 2021 Documents Representation via Generalized Coupled Tensor Chain with the Rotation Group constraint IJCNLP 2021 SkoltechNLP at SemEval-2021 Task 2: Generating Cross-Lingual Training Data for the Word-in-Context Task IJCNLP 2021 SkoltechNLP at SemEval-2020 Task 11: Exploring Unsupervised Text Augmentation for Propaganda Detection SEMEVAL 2020 Studying Taxonomy Enrichment on Diachronic WordNet Versions COLING 2020 SkoltechNLP at SemEval-2020 Task 11: Exploring Unsupervised Text Augmentation for Propaganda Detection COLING 2020 Always Keep your Target in Mind: Studying Semantics and Improving Performance of Neural Lexical Substitution COLING 2020 TARGER: Neural Argument Mining at Your Fingertips ACL 2019 Improving Neural Entity Disambiguation with Graph Embeddings ACL 2019 Neural GRANNy at SemEval-2019 Task 2: A combined approach for better modeling of semantic relationships in semantic frame induction SEMEVAL 2019 HHMM at SemEval-2019 Task 2: Unsupervised Frame Induction using Contextualized Word Embeddings SEMEVAL 2019 Categorizing Comparative Sentences ACL 2019 Every Child Should Have Parents: A Taxonomy Refinement Algorithm Based on Hyperbolic Term Embeddings ACL 2019 Making Fast Graph-based Algorithms with Graph Metric Embeddings ACL 2019 On the Compositionality Prediction of Noun Phrases using Poincaré Embeddings ACL 2019 A Dataset for Noun Compositionality Detection for a Slavic Language ACL 2019 Unsupervised Semantic Frame Induction using Triclustering ACL 2018 Watset: Automatic Induction of Synsets from a Graph of Synonyms ACL 2017 The ContrastMedium Algorithm: Taxonomy Induction From Noisy Knowledge Graphs With Just A Few Links EACL 2017 Negative Sampling Improves Hypernymy Extraction Based on Projection Learning EACL 2017 Unsupervised, Knowledge-Free, and Interpretable Word Sense Disambiguation EMNLP 2017 Unsupervised Does Not Mean Uninterpretable: The Case for Word Sense Induction and Disambiguation EACL 2017 new/s/leak – Information Extraction and Visualization for Investigative Data Journalists ACL 2016 TAXI at SemEval-2016 Task 13: a Taxonomy Induction Method based on Lexico-Syntactic Patterns, Substrings and Focused Crawling SEMEVAL 2016 A Graph-Based Approach to Skill Extraction from Text EMNLP 2013