4 papers
Language steering in latent space to mitigate unintended code-switching
Andrey Goncharov, Nikolai Kondusov, Alexey Zaytsev
Multilingual Large Language Models (LLMs) often exhibit hallucinations such as unintended code-switching, reducing reliability in downstream tasks. We propose latent-space language…
Complexity-aware fine-tuning
Andrey Goncharov, Daniil Vyazhev, Petr Sychev +2
General-purpose Large Language Models (LLMs) are frequently fine-tuned through supervised fine-tuning (SFT) to enhance performance in specific domains. Better results can be achiev…
Selective Adversarial Attacks on LLM Benchmarks
Ivan Dubrovsky, Anastasia Orlova, Illarion Iov +3
Benchmarking outcomes increasingly govern trust, selection, and deployment of LLMs, yet these evaluations remain vulnerable to semantically equivalent adversarial perturbations. Pr…
When an LLM is apprehensive about its answers -- and when its uncertainty is justified
Petr Sychev, Andrey Goncharov, Daniil Vyazhev +2
Uncertainty estimation is crucial for evaluating Large Language Models (LLMs), particularly in high-stakes domains where incorrect answers result in significant consequences. Numer…