4 papers
On the Overscaling Curse of Parallel Thinking: System Efficacy Contradicts Sample Efficiency
Yiming Wang, Zhuosheng Zhang, Rui Wang
Parallel thinking improves LLM reasoning through multi-path sampling and aggregation. In standard evaluations, due to a lack of sample-specific priors, all samples share a global b…
Spontaneous High-Order Generalization in Neural Theory-of-Mind Networks
Yiming Wang, Rui Wang
Theory-of-Mind (ToM) is a core human cognitive capacity for attributing mental states to self and others. Wimmer and Perner demonstrated that humans progress from first- to higher-…
Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation
Yiming Wang, Pei Zhang, Baosong Yang +2
LLM self-evaluation relies on the LLM's own ability to estimate response correctness, which can greatly improve its deployment reliability. In this research track, we propose the C…
AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preference
Yang Han, Yiming Wang, Rui Wang +2
Text summarization tasks commonly employ Pre-trained Language Models (PLMs) to fit diverse standard datasets. While these PLMs excel in automatic evaluations, they frequently under…