14 papers
Rethinking Reward Models for Multi-Domain Test-Time Scaling
Dong Bok Lee, Seanie Lee, Sangwoo Park +12
The reliability of large language models (LLMs) during test-time scaling is often assessed with \emph{external verifiers} or \emph{reward models} that distinguish correct reasoning…
THINKSAFE: Self-Generated Safety Alignment for Reasoning Models
Seanie Lee, Sangwoo Park, Yumin Choi +6
Large reasoning models (LRMs) achieve remarkable performance by leveraging reinforcement learning (RL) on reasoning tasks to generate long chain-of-thought (CoT) reasoning. However…
GFlowPO: Generative Flow Network as a Language Model Prompt Optimizer
Junmo Cho, Suhan Kim, Sangjune An +5
Finding effective prompts for language models (LMs) is critical yet notoriously difficult: the prompt space is combinatorially large, rewards are sparse due to expensive target-LM…
Distilling LLM Agent into Small Models with Retrieval and Code Tools
Minki Kang, Jongwon Jeong, Seanie Lee +2
Large language models (LLMs) excel at complex reasoning tasks but remain computationally expensive, limiting their practical deployment. To address this, recent works have focused…
FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA
Seanie Lee, Sangwoo Park, Dong Bok Lee +5
Low-Rank Adaptation (LoRA), which introduces a product of two trainable low-rank matrices into frozen pre-trained weights, is widely used for efficient fine-tuning of language mode…
Cost-Sensitive Freeze-thaw Bayesian Optimization for Efficient Hyperparameter Tuning
Dong Bok Lee, Aoxuan Silvia Zhang, Byungjoo Kim +5
In this paper, we address the problem of \emph{cost-sensitive} hyperparameter optimization (HPO) built upon freeze-thaw Bayesian optimization (BO). Specifically, we assume a scenar…