Elena Tutubalina

tlenusik's activity

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

authored 4 papers 5 days ago

Anatomy of Unlearning: The Dual Impact of Fact Salience and Model Fine-Tuning

Paper • 2602.19612 • Published Feb 23

Breaking the Chain: A Causal Analysis of LLM Faithfulness to Intermediate Structures

Paper • 2603.16475 • Published Mar 17 • 13

POLAR: A Benchmark for Multilingual, Multicultural, and Multi-Event Online Polarization

Paper • 2505.20624 • Published Feb 5

Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models

Paper • 2606.19297 • Published 24 days ago • 76

upvoted a paper 9 days ago

Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models

Paper • 2606.19297 • Published 24 days ago • 76

liked a model 4 months ago

andorei/BERGAMOT-multilingual-GAT

Feature Extraction • Updated Sep 3, 2024 • 408 • 3

authored 2 papers 5 months ago

Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?

Paper • 2602.14111 • Published Feb 15 • 56

RecVAE: a New Variational Autoencoder for Top-N Recommendations with Implicit Feedback

Paper • 1912.11160 • Published Dec 24, 2019 • 1

upvoted a paper 5 months ago

Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?

Paper • 2602.14111 • Published Feb 15 • 56

authored a paper 8 months ago

Global PIQA: Evaluating Physical Commonsense Reasoning Across 100+ Languages and Cultures

Paper • 2510.24081 • Published Oct 28, 2025 • 24

upvoted a paper 8 months ago

Global PIQA: Evaluating Physical Commonsense Reasoning Across 100+ Languages and Cultures

Paper • 2510.24081 • Published Oct 28, 2025 • 24

authored a paper 9 months ago

Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs

Paper • 2510.11288 • Published Oct 13, 2025 • 48

upvoted a paper 9 months ago

Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs

Paper • 2510.11288 • Published Oct 13, 2025 • 48

authored a paper 9 months ago

OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features

Paper • 2509.22033 • Published Sep 26, 2025 • 19

upvoted 2 papers 9 months ago

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

Paper • 2510.04849 • Published Oct 6, 2025 • 117

OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features

Paper • 2509.22033 • Published Sep 26, 2025 • 19

authored 2 papers 9 months ago

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

Paper • 2508.11383 • Published Aug 15, 2025 • 40

The Rogue Scalpel: Activation Steering Compromises LLM Safety

Paper • 2509.22067 • Published Sep 26, 2025 • 28

upvoted a paper 9 months ago

The Rogue Scalpel: Activation Steering Compromises LLM Safety

Paper • 2509.22067 • Published Sep 26, 2025 • 28

upvoted a paper 11 months ago

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

Paper • 2508.11383 • Published Aug 15, 2025 • 40