5 papers · 1 filter
Learning Ordinal Probabilistic Reward from Preferences
Longze Chen, Lu Wang, Renke Shan +6
Reward models are crucial for aligning large language models (LLMs) with human values and intentions. Existing approaches follow either Generative (GRMs) or Discriminative (DRMs) p…
Skill-Aware Data Selection and Fine-Tuning for Data-Efficient Reasoning Distillation
Lechen Zhang, Yunxiang Zhang, Wei Hu +1
Large reasoning models such as DeepSeek-R1 and their distilled variants achieve strong performance on complex reasoning tasks. Yet, distilling these models often demands large-scal…
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
5 Team, Aohan Zeng, Xin Lv +167
We present GLM-4.5, an open-source Mixture-of-Experts (MoE) large language model with 355B total parameters and 32B activated parameters, featuring a hybrid reasoning method that s…
Do Language Models Think Consistently? A Study of Value Preferences Across Varying Response Lengths
Inderjeet Nair, Lu Wang
Evaluations of LLMs' ethical risks and value inclinations often rely on short-form surveys and psychometric tests, yet real-world use involves long-form, open-ended responses -- le…
MIDGARD: Self-Consistency Using Minimum Description Length for Structured Commonsense Reasoning
Inderjeet Nair, Lu Wang
We study the task of conducting structured reasoning as generating a reasoning graph from natural language input using large language models (LLMs). Previous approaches have explor…