Mikhail Chaichuk

THunderCondOR's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 18 days ago

When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA

Paper • 2510.04849 • Published 29 days ago • 110

upvoted a paper 28 days ago

OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features

Paper • 2509.22033 • Published Sep 26 • 18

upvoted a paper about 1 month ago

The Rogue Scalpel: Activation Steering Compromises LLM Safety

Paper • 2509.22067 • Published Sep 26 • 27

upvoted a paper 3 months ago

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

Paper • 2508.11383 • Published Aug 15 • 40

upvoted a paper 4 months ago

T-LoRA: Single Image Diffusion Model Customization Without Overfitting

Paper • 2507.05964 • Published Jul 8 • 118

upvoted a paper 5 months ago

Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models

Paper • 2506.06751 • Published Jun 7 • 71

upvoted a paper 7 months ago

I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders

Paper • 2503.18878 • Published Mar 24 • 119

upvoted 2 papers 8 months ago

RuCCoD: Towards Automated ICD Coding in Russian

Paper • 2502.21263 • Published Feb 28 • 132

GHOST 2.0: generative high-fidelity one shot transfer of heads

Paper • 2502.18417 • Published Feb 25 • 67

upvoted a paper 9 months ago

SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators

Paper • 2502.06394 • Published Feb 10 • 89

upvoted 2 papers about 1 year ago

CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation

Paper • 2410.23090 • Published Oct 30, 2024 • 55

CLEAR: Character Unlearning in Textual and Visual Modalities

Paper • 2410.18057 • Published Oct 23, 2024 • 209