11 papers
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…
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…
CoRoVA: Compressed Representations for Vector-Augmented Code Completion
Daria Cherniuk, Nikita Sukhorukov, Danil Gusak +4
Retrieval-augmented generation has emerged as one of the most effective approaches for code completion enhancement, especially when repository-level context is important. However,…
Evolutionary Search for Automated Design of Uncertainty Quantification Methods
Mikhail Seleznyov, Daniil Korbut, Viktor Moskvoretskii +3
Uncertainty quantification (UQ) methods for large language models are predominantly designed by hand based on domain knowledge and heuristics, limiting their scalability and genera…
The Chronicles of RiDiC: Generating Datasets with Controlled Popularity Distribution for Long-form Factuality Evaluation
Pavel Braslavski, Dmitrii Iarosh, Nikita Sushko +4
We present a configurable pipeline for generating multilingual sets of entities with specified characteristics, such as domain, geographical location and popularity, using data fro…
Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval
Artem Vazhentsev, Maria Marina, Daniil Moskovskiy +8
Trustworthiness is a core research challenge for agentic AI systems built on Large Language Models (LLMs). To enhance trust, natural language claims from diverse sources, including…