Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Oleg Somov

Oleg Somov

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

AI×3

Frequent co-authors

Elena Tutubalina3×
Qinghua Zhou2×
Ellina Aleshina2×
Andrey Lovyagin2×
Mikhail Seleznyov2×
Alexander Panchenko2×

Research Timeline

2026
Harnessing non-adversarial robustness in large language models

The paper proposes a debiasing fine-tuning technique to efficiently enhance the robustness of Large Language Models against semantically similar but textually altered prompts.

Harnessing non-adversarial robustness in large language models

The paper proposes a debiasing fine-tuning technique to efficiently enhance the robustness of Large Language Models against semantically similar but textually altered prompts.

Structural Chain-of-Thought: Reasoning with Executable Computational Graphs

Improves accuracy and reduces generation length of large language models

Highlighted terms show continued research focus across papers

Papers

cs.AIEmpiricalRecentOct 10, 2026

Structural Chain-of-Thought: Reasoning with Executable Computational Graphs

Petr Senatorov, Karim Vafin, Elena Tutubalina, Oleg Somov

Improves accuracy and reduces generation length of large language models

View →
cs.AIRecentMay 28, 2026

Harnessing non-adversarial robustness in large language models

Qinghua Zhou, Ellina Aleshina, Andrey Lovyagin, Oleg Somov +5 more

The paper proposes a debiasing fine-tuning technique to efficiently enhance the robustness of Large Language Models against semantically similar but textually altered prompts.

View →
cs.AIRecentMay 28, 2026

Harnessing non-adversarial robustness in large language models

Qinghua Zhou, Ellina Aleshina, Andrey Lovyagin, Oleg Somov +5 more

The paper proposes a debiasing fine-tuning technique to efficiently enhance the robustness of Large Language Models against semantically similar but textually altered prompts.

View →