Ivan Lazichny

4 papers · 2022–2025 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12) 🐣 Hot Topic Early Bird

Venues

EMNLP (3) NAACL (1)

Top co-authors

Artem Shelmanov (4) Artem Vazhentsev (3) Alexander Panchenko (3) Maxim Panov (3) Leonid Sanochkin (2) Gleb Kuzmin (2) Akim Tsvigun (2) Timothy Baldwin (2) Daniil Larionov (1) Artemy Belousov (1)

Research topics

Machine Learning (4) Learning Types (4) Artificial Intelligence (2) Natural Language Processing (2) Core AI (2) Optimization & Theory (2) Applications (1) Core Methods (1) Generation (1)

Keywords

query strategy (2) uncertainty quantification (2) large language model (2) selective generation (2) active learning (2) autoregressive generation (1) text summarization (1) sequence tagging (1) mahalanobis distance (1) autoregressive model (1) diversity sampling (1) hallucination detection (1) attention map (1) abstractive summarization (1) token-level prediction (1) abstractive text summarization (1) annotation tool (1) token embedding (1) recurrent uncertainty (1) text classification (1)

Papers

Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models NAACL 2025 Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models EMNLP 2025 Active Learning for Abstractive Text Summarization EMNLP 2022 ALToolbox: A Set of Tools for Active Learning Annotation of Natural Language Texts EMNLP 2022