T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground Paper • 2512.10430 • Published 25 days ago • 113
Multimodal Evaluation of Russian-language Architectures Paper • 2511.15552 • Published Nov 19, 2025 • 78
LLM-Independent Adaptive RAG: Let the Question Speak for Itself Paper • 2505.04253 • Published May 7, 2025 • 14
GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms Paper • 2511.17592 • Published Nov 17, 2025 • 118
When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA Paper • 2510.04849 • Published Oct 6, 2025 • 114
<think> So let's replace this phrase with insult... </think> Lessons learned from generation of toxic texts with LLMs Paper • 2509.08358 • Published Sep 10, 2025 • 13
Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA Paper • 2505.21115 • Published May 27, 2025 • 140
Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images Paper • 2505.07704 • Published May 12, 2025 • 29
Knowledge Packing Collection Models and datasets from the paper: "How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?" https://arxiv.org/abs/2502.14502 • 9 items • Updated Feb 25, 2025 • 2
How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM? Paper • 2502.14502 • Published Feb 20, 2025 • 91
SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators Paper • 2502.06394 • Published Feb 10, 2025 • 89