15 papers · 1 filter
Lizard: An Efficient Linearization Framework for Large Language Models
Chien Van Nguyen, Huy Nguyen, Ruiyi Zhang +10
We propose Lizard, a linearization framework that transforms pretrained Transformer-based Large Language Models (LLMs) into subquadratic architectures. Transformers faces severe co…
Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams
Jiyeon Kim, Hyunji Lee, Dylan Zhou +6
LLMs operating in dynamic real-world contexts often encounter knowledge that evolves continuously or emerges incrementally. To remain accurate and effective, models must adapt to n…
Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization
Subhojyoti Mukherjee, Viet Dac Lai, Raghavendra Addanki +6
Offline reinforcement learning (RL) is a variant of RL where the policy is learned from a previously collected dataset of trajectories and rewards. In our work, we propose a practi…
Steering MoE LLMs via Expert (De)Activation
Mohsen Fayyaz, Ali Modarressi, Hanieh Deilamsalehy +5
Mixture-of-Experts (MoE) in Large Language Models (LLMs) routes each token through a subset of specialized Feed-Forward Networks (FFN), known as experts. We present SteerMoE, a fra…
Instruction Tuning with and without Context: Behavioral Shifts and Downstream Impact
Hyunji Lee, Seunghyun Yoon, Yunjae Won +7
Instruction tuning is a widely used approach to improve the instruction-following ability of large language models (LLMs). Instruction-tuning datasets typically include a mixture o…
Drift No More? Context Equilibria in Multi-Turn LLM Interactions
Vardhan Dongre, Ryan A. Rossi, Viet Dac Lai +3
Large Language Models (LLMs) excel at single-turn tasks such as instruction following and summarization, yet real-world deployments require sustained multi-turn interactions where…