Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
Mitigating Shortcut Reasoning in Language Models: A Gradient-Aware Training Approach
Hongyu Cao, Kunpeng Liu, Dongjie Wang +1
Large language models exhibit strong reasoning capabilities, yet often rely on shortcuts such as surface pattern matching and answer memorization rather than genuine logical infere…
cs.CL2026
Evolving Demonstration Optimization for Chain-of-Thought Feature Transformation
Xinyuan Wang, Kunpeng Liu, Arun Vignesh Malarkkan +1
Feature Transformation (FT) is a core data-centric AI task that improves feature space quality to advance downstream predictive performance. However, discovering effective transfor…
cs.CL2025
Efficient Post-Training Refinement of Latent Reasoning in Large Language Models
Xinyuan Wang, Dongjie Wang, Wangyang Ying +5
Reasoning is a key component of language understanding in Large Language Models. While Chain-of-Thought prompting enhances performance via explicit intermediate steps, it suffers f…