5 papers
KL for a KL: On-Policy Distillation with Control Variate Baseline
Minjae Oh, Sangjun Song, Gyubin Choi +2
On-Policy Distillation (OPD) has emerged as a dominant post-training paradigm for large language models, especially for reasoning domains. However, OPD remains unstable in practice…
TriBench-Ko: Evaluating LLM Risks in Judicial Workflows
Haesung Lee, Gyubin Choi, Eun-Ju Lee +5
Large language models (LLMs) are increasingly integrated into legal workflows. However, existing benchmarks primarily address proxy tasks, such as bar examination performance or cl…
Context-Robust Knowledge Editing for Language Models
Haewon Park, Gyubin Choi, Minjun Kim +1
Knowledge editing (KE) methods offer an efficient way to modify knowledge in large language models. Current KE evaluations typically assess editing success by considering only the…
ADOR: A Design Exploration Framework for LLM Serving with Enhanced Latency and Throughput
Junsoo Kim, Hunjong Lee, Geonwoo Ko +4
The growing adoption of Large Language Models (LLMs) across various domains has driven the demand for efficient and scalable AI-serving solutions. Deploying LLMs requires optimizat…
LPU: A Latency-Optimized and Highly Scalable Processor for Large Language Model Inference
Seungjae Moon, Jung-Hoon Kim, Junsoo Kim +14
The explosive arrival of OpenAI's ChatGPT has fueled the globalization of large language model (LLM), which consists of billions of pretrained parameters that embodies the aspects…