4 papers · 1 filter
The Readout Shortcut: Positional Number Copying Dominates Arithmetic CoT Readout in Small Language Models
Ming Liu
Chain-of-thought (CoT) prompting is necessary for arithmetic in small language models, yet shuffling its steps preserves most performance. What does CoT contribute if not logical s…
In-Context Fixation: When Demonstrated Labels Override Semantics in Few-Shot Classification
Ming Liu
While random demonstration labels barely hurt in-context learning (Min et al., 2022), we show that homogeneous labels--even semantically valid ones--collapse accuracy to <=12% acro…
Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math Learner
Tao He, Rongchuan Mu, Lizi Liao +3
Large reasoning models (LRMs) have recently shown promise in solving complex math problems when optimized with Reinforcement Learning (RL). But conventional approaches rely on outc…
Improved Diffusion-based Generative Model with Better Adversarial Robustness
Zekun Wang, Mingyang Yi, Shuchen Xue +4
Diffusion Probabilistic Models (DPMs) have achieved significant success in generative tasks. However, their training and sampling processes suffer from the issue of distribution mi…