6 papers · 1 filter
Leveraging Parameter Space Symmetries for Reasoning Skill Transfer in LLMs
Stefan Horoi, Sangwoo Cho, Supriyo Chakraborty +4
Task arithmetic is a powerful technique for transferring skills between Large Language Models (LLMs), but it often suffers from negative interference when models have diverged duri…
SPEAR-MM: Selective Parameter Evaluation and Restoration via Model Merging for Efficient Financial LLM Adaptation
Berkcan Kapusuzoglu, Supriyo Chakraborty, Renkun Ni +2
Large language models (LLMs) adapted to financial domains often suffer from catastrophic forgetting of general reasoning capabilities essential for customer interactions and comple…
Optimizing Reasoning Efficiency through Prompt Difficulty Prediction
Bo Zhao, Berkcan Kapusuzoglu, Kartik Balasubramaniam +3
Reasoning language models perform well on complex tasks but are costly to deploy due to their size and long reasoning traces. We propose a routing approach that assigns each proble…
T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic Planning
Amartya Chakraborty, Paresh Dashore, Nadia Bathaee +6
Large Language Models (LLMs) have demonstrated impressive capabilities as intelligent agents capable of solving complex problems. However, effective planning in scenarios involving…
Dense Backpropagation Improves Training for Sparse Mixture-of-Experts
Ashwinee Panda, Vatsal Baherwani, Zain Sarwar +4
Mixture of Experts (MoE) pretraining is more scalable than dense Transformer pretraining, because MoEs learn to route inputs to a sparse set of their feedforward parameters. Howeve…
Continual Pre-training of MoEs: How robust is your router?
Benjamin Thérien, Charles-Étienne Joseph, Zain Sarwar +7
Sparsely-activated Mixture of Experts (MoE) transformers are promising architectures for foundation models. Compared to dense transformers that require the same amount of floating-…