7 papers
TIAR: Trajectory-Informed Advantage Reweighting for LLM Abstention Learning
Muyu Pan, Shu Zhao, Nan Zhang +4
This paper investigates large language model (LLM) abstention learning, specifically using ternary reward, which incentivize truthfulness in large language models. This paper exten…
From Correctness to Preference: A Framework for Personalized Agentic Reinforcement Learning
Ranxu zhang, zeyang li, Jiacheng Huang +5
Agentic reinforcement learning (Agentic RL) has achieved strong progress in tasks with clear success signals. However, many real-world agent applications require user-conditioned b…
Why Do Reasoning Models Lose Coverage? The Role of Data and Forks in the Road
Ngoc-Hieu Nguyen, Parshin Shojaee, Phuc Minh Nguyen +4
Recent progress in large language models has led to the emergence of reasoning models, which have shown strong performance on complex tasks through specialized fine-tuning procedur…
When Reasoning Meets Compression: Understanding the Effects of LLMs Compression on Large Reasoning Models
Nan Zhang, Eugene Kwek, Yusen Zhang +3
Compression methods, including quantization, distillation, and pruning, improve the computational efficiency of large reasoning models (LRMs). However, existing studies either fail…
QuantLRM: Quantization of Large Reasoning Models via Fine-Tuning Signals
Nan Zhang, Eugene Kwek, Yusen Zhang +4
Weight-only quantization is important for compressing Large Language Models (LLMs). Inspired by the spirit of classical magnitude pruning, we study whether the magnitude of weight…
TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora
Priyanka Kargupta, Nan Zhang, Yunyi Zhang +3
The rapid evolution of scientific fields introduces challenges in organizing and retrieving scientific literature. While expert-curated taxonomies have traditionally addressed this…