6 papers
Leveraging Routing Dynamics in Mixture-of-Experts Models for Efficient Language Adaptation
Aditi Khandelwal, Marius Mosbach, Verna Dankers +2
Mixture-of-Experts (MoE) models are widely used to scale language models, yet their expert routing behavior and adaptation in a multilingual setting remain underexplored. In this w…
DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning
Sara Vera MarjanoviÄ, Arkil Patel, Vaibhav Adlakha +14
Large Reasoning Models like DeepSeek-R1 mark a fundamental shift in how LLMs approach complex problems. Instead of directly producing an answer for a given input, DeepSeek-R1 creat…
Multilingual Amnesia: On the Transferability of Unlearning in Multilingual LLMs
Alireza Dehghanpour Farashah, Aditi Khandelwal, Marylou Fauchard +3
As multilingual large language models become more widely used, ensuring their safety and fairness across diverse linguistic contexts presents unique challenges. While existing rese…
The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process
Florian Carichon, Aditi Khandelwal, Marylou Fauchard +1
This position paper states that AI Alignment in Multi-Agent Systems (MAS) should be considered a dynamic and interaction-dependent process that heavily depends on the social enviro…
Cross-Lingual Multi-Hop Knowledge Editing
Aditi Khandelwal, Harman Singh, Hengrui Gu +2
Large language models are often expected to constantly adapt to new sources of knowledge and knowledge editing techniques aim to efficiently patch the outdated model knowledge, wit…
Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them in
Utkarsh Agarwal, Kumar Tanmay, Aditi Khandelwal +1
Ethical reasoning is a crucial skill for Large Language Models (LLMs). However, moral values are not universal, but rather influenced by language and culture. This paper explores h…