activity
20242026
collaborators

9 papers

cs.LG2026

Knowledge Offloading: Decomposing LLMs into Sparse Backbones and Memory Modules

Karim Galliamov, Rochelle Choenni, Ivan Titov

LLMs encode both general capabilities and domain-specific knowledge in a single set of parameters. We ask whether this capacity can be reorganized: keeping broadly useful computati…

cs.LG2026

Finding Culture-Sensitive Neurons in Vision-Language Models

Xiutian Zhao, Rochelle Choenni, Rohit Saxena +1

Despite their impressive performance, vision-language models (VLMs) still struggle on culturally situated inputs. To understand how VLMs process culturally grounded information, we…

cs.CL2025

Best-of-L: Cross-Lingual Reward Modeling for Mathematical Reasoning

Sara Rajaee, Rochelle Choenni, Ekaterina Shutova +1

While the reasoning abilities of large language models (LLMs) continue to advance, it remains unclear how such ability varies across languages in multilingual LLMs and whether diff…

cs.CL2025

Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learning

Rochelle Choenni, Ekaterina Shutova

Improving the alignment of Large Language Models (LLMs) with respect to the cultural values that they encode has become an increasingly important topic. In this work, we study whet…

cs.CL2025

M-Wanda: Improving One-Shot Pruning for Multilingual LLMs

Rochelle Choenni, Ivan Titov

Multilingual LLM performance is often critically dependent on model size. With an eye on efficiency, this has led to a surge in interest in one-shot pruning methods that retain the…

cs.CL2024

Local Contrastive Editing of Gender Stereotypes

Marlene Lutz, Rochelle Choenni, Markus Strohmaier +1

Stereotypical bias encoded in language models (LMs) poses a threat to safe language technology, yet our understanding of how bias manifests in the parameters of LMs remains incompl…