Alexander Panchenko
- Papers
- 28
Cite
Notes
Only stored in your browser.
Authored papers
28Detecting Overflow in Compressed Token Representations for Retrieval-Augmented Generation
arXiv 2026
Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home
arXiv 2025
LLM-Independent Adaptive RAG: Let the Question Speak for Itself
arXiv 2025
Multimodal Evaluation of Russian-language Architectures
arXiv 2025
When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA
arXiv 2025
Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA
arXiv 2025
SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators
arXiv 2025
Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images
arXiv 2025
Don't Fight Hallucinations, Use Them: Estimating Image Realism using NLI over Atomic Facts
arXiv 2025
<think> So let's replace this phrase with insult... </think> Lessons learned from generation of toxic texts with LLMs
arXiv 2025
When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs
arXiv 2025
How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?
how-much-knowledge-can-you-pack-into-a-lora
Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models
arXiv 2025
Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification
arXiv 2024
SparseGrad: A Selective Method for Efficient Fine-tuning of MLP Layers
arXiv 2024
Multilingual and Explainable Text Detoxification with Parallel Corpora
arXiv 2024
SmurfCat at SemEval-2024 Task 6: Leveraging Synthetic Data for Hallucination Detection
arXiv 2024
Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph
arXiv 2024
TaxoLLaMA: WordNet-based Model for Solving Multiple Lexical Semantic Tasks
arXiv 2024
xCOMET-lite: Bridging the Gap Between Efficiency and Quality in Learned MT Evaluation Metrics
arXiv 2024
Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion
arXiv 2023
Studying the role of named entities for content preservation in text style transfer
arXiv 2022
Exploring Cross-lingual Textual Style Transfer with Large Multilingual Language Models
arXiv 2022
Methods for Detoxification of Texts for the Russian Language
arXiv 2021
Text Detoxification using Large Pre-trained Neural Models
EMNLP 2021 11
Detecting Inappropriate Messages on Sensitive Topics that Could Harm a Company's Reputation
arXiv 2021
Every child should have parents: a taxonomy refinement algorithm based on hyperbolic term embeddings
every-child-should-have-parents-a-taxonomy-1
Watset: Local-Global Graph Clustering with Applications in Sense and Frame Induction
watset-local-global-graph-clustering-with-1
Affiliations
Frequent co-authors
10from 28 papers
Vasily Konovalov
Daniil Moskovskiy
Sergey Pletenev
Elisei Rykov
Mikhail Salnikov
Daryna Dementieva
Kseniia Petrushina
Kseniia Titova
Varvara Logacheva
Viktor Moskvoretskii