5 papers
Reinforcing Chain-of-Thought Reasoning with Self-Evolving Rubrics
Leheng Sheng, Wenchang Ma, Ruixin Hong +3
Despite chain-of-thought (CoT) playing crucial roles in LLM reasoning, directly rewarding it is difficult: training a reward model demands heavy human labeling efforts, and static…
Streaming Looking Ahead with Token-level Self-reward
Hongming Zhang, Ruixin Hong, Dong Yu
Autoregressive decoding algorithms that use only past information often cannot guarantee the best performance. Recently, people discovered that looking-ahead algorithms such as Mon…
Physics Reasoner: Knowledge-Augmented Reasoning for Solving Physics Problems with Large Language Models
Xinyu Pang, Ruixin Hong, Zhanke Zhou +5
Physics problems constitute a significant aspect of reasoning, necessitating complicated reasoning ability and abundant physics knowledge. However, existing large language models (…
Abstraction-of-Thought Makes Language Models Better Reasoners
Ruixin Hong, Hongming Zhang, Xiaoman Pan +2
Abstract reasoning, the ability to reason from the abstract essence of a problem, serves as a key to generalization in human reasoning. However, eliciting language models to perfor…
CLOMO: Counterfactual Logical Modification with Large Language Models
Yinya Huang, Ruixin Hong, Hongming Zhang +6
In this study, we delve into the realm of counterfactual reasoning capabilities of large language models (LLMs). Our primary objective is to cultivate the counterfactual thought pr…