collaborators

7 papers

cs.CL2026

The More Popular, The Harder to Forget: Adaptive Popularity for LLM Unlearning

Anna Borisiuk, Andrey Savchenko, Alexander Panchenko +1

Popular facts are memorised more deeply during pretraining and resist removal longer than rare ones, yet existing LLM unlearning methods apply uniform gradient pressure regardless…

cs.AI2026

Breaking the Chain: A Causal Analysis of LLM Faithfulness to Intermediate Structures

Oleg Somov, Mikhail Chaichuk, Gleb Ershov +4

In schema-guided reasoning (SGR) pipelines, LLMs produce explicit intermediate structures -- rubrics, checklists, or verification queries -- before committing to a final decision.…

cs.CL2026

Anatomy of Unlearning: The Dual Impact of Fact Salience and Model Fine-Tuning

Anna Borisiuk, Andrey Savchenko, Alexander Panchenko +1

Machine Unlearning (MU) enables Large Language Models (LLMs) to remove unsafe or outdated information. However, existing work assumes that all facts are equally forgettable and lar…

cs.CL2026

Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs

Nikita Afonin, Nikita Andriianov, Vahagn Hovhannisyan +9

Recent work has shown that narrow finetuning can produce broadly misaligned LLMs, a phenomenon termed emergent misalignment (EM). While concerning, these findings were limited to f…

cs.CL2025

When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs

Mikhail Seleznyov, Mikhail Chaichuk, Gleb Ershov +3

Large Language Models (LLMs) are highly sensitive to subtle, non-semantic variations in prompt phrasing and formatting. In this work, we present the first systematic evaluation of…

cs.CL2025

The benefits of query-based KGQA systems for complex and temporal questions in LLM era

Artem Alekseev, Mikhail Chaichuk, Miron Butko +3

Large language models excel in question-answering (QA) yet still struggle with multi-hop reasoning and temporal questions. Query-based knowledge graph QA (KGQA) offers a modular al…