8 papers
Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning
Renliang Sun, Wei Cheng, Dawei Li +2
Chain-of-Thought (CoT) reasoning has driven recent gains of large language models (LLMs) on reasoning-intensive tasks by externalizing intermediate steps. However, excessive or red…
Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection
Cong Zeng, Shengkun Tang, Yuanzhou Chen +6
The rapid advancement of large language models (LLMs) such as ChatGPT, DeepSeek, and Claude has significantly increased the presence of AI-generated text in digital communication.…
Where's the liability in the Generative Era? Recovery-based Black-Box Detection of AI-Generated Content
Haoyue Bai, Yiyou Sun, Wei Cheng +1
The recent proliferation of photorealistic images created by generative models has sparked both excitement and concern, as these images are increasingly indistinguishable from real…
TimeCAP: Learning to Contextualize, Augment, and Predict Time Series Events with Large Language Model Agents
Geon Lee, Wenchao Yu, Kijung Shin +2
Time series data is essential in various applications, including climate modeling, healthcare monitoring, and financial analytics. Understanding the contextual information associat…
MixLLM: Dynamic Routing in Mixed Large Language Models
Xinyuan Wang, Yanchi Liu, Wei Cheng +5
Large Language Models (LLMs) exhibit potential artificial generic intelligence recently, however, their usage is costly with high response latency. Given mixed LLMs with their own…
DISC: Dynamic Decomposition Improves LLM Inference Scaling
Jonathan Light, Wei Cheng, Benjamin Riviere +6
Inference scaling methods for LLMs often rely on decomposing problems into steps (or groups of tokens), followed by sampling and selecting the best next steps. However, these steps…