11 citations · 17 across the 15 of their papers we have counts for
18 papers
Group-Marginalized Self-Rewarding RL Drives Zero-Label Self-Evolving
Yiming Wang, Yikang Liu, Qingyuan Tian +4
Self-rewarding reinforcement learning (RL) enables large language models (LLMs) to self-evolve without human labels. Existing ensemble-based methods construct reward references fro…
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-…
Direct Simultaneous Translation Activation for Large Audio-Language Models
Pei Zhang, Yiming Wang, Jialong Tang +4
Simultaneous speech-to-text translation (Simul-S2TT) aims to translate speech into target text in real time, outputting translations while receiving source speech input, rather tha…
Translationese-index: Using Likelihood Ratios for Graded and Generalizable Measurement of Translationese
Yikang Liu, Wanyang Zhang, Yiming Wang +6
Translationese refers to linguistic properties that usually occur in translated texts. Previous works study translationese by framing it as a binary classification between original…
PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts
Yiming Wang, Pei Zhang, Jialong Tang +12
In this paper, we introduce PolyMath, a multilingual mathematical reasoning benchmark covering 18 languages and 4 easy-to-hard difficulty levels. Our benchmark ensures difficulty c…
Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding
Yiming Wang, Pei Zhang, Siyuan Huang +4
Test-time scaling enhances large language model performance by allocating additional compute resources during inference. Best-of-N (BoN) sampling serves as a common sampling-based…
Do Large Language Models Truly Understand Geometric Structures?
Xiaofeng Wang, Yiming Wang, Wenhong Zhu +1
Geometric ability is a significant challenge for large language models (LLMs) due to the need for advanced spatial comprehension and abstract thinking. Existing datasets primarily…
MIND: Towards Immersive Psychological Healing with Multi-agent Inner Dialogue
Yujia Chen, Changsong Li, Yiming Wang +6
Mental health issues are worsening in today's competitive society, such as depression and anxiety. Traditional healings like counseling and chatbots fail to engage effectively, the…
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…
Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoning
Yiming Wang, Pei Zhang, Baosong Yang +3
Real-world data deviating from the independent and identically distributed (i.i.d.) assumption of in-distribution training data poses security threats to deep networks, thus advanc…
R-Judge: Benchmarking Safety Risk Awareness for LLM Agents
Tongxin Yuan, Zhiwei He, Lingzhong Dong +9
Large language models (LLMs) have exhibited great potential in autonomously completing tasks across real-world applications. Despite this, these LLM agents introduce unexpected saf…
Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents
Zhuosheng Zhang, Yao Yao, Aston Zhang +8
Large language models (LLMs) have dramatically enhanced the field of language intelligence, as demonstrably evidenced by their formidable empirical performance across a spectrum of…
RetroDiff: Retrosynthesis as Multi-stage Distribution Interpolation
Yiming Wang, Yuxuan Song, Yiqun Wang +4
Retrosynthesis poses a key challenge in biopharmaceuticals, aiding chemists in finding appropriate reactant molecules for given product molecules. With reactants and products repre…
Self-Enhancement Improves Text-Image Retrieval in Foundation Visual-Language Models
Yuguang Yang, Yiming Wang, Shupeng Geng +4
The emergence of cross-modal foundation models has introduced numerous approaches grounded in text-image retrieval. However, on some domain-specific retrieval tasks, these models f…
Meta-Reasoning: Semantics-Symbol Deconstruction for Large Language Models
Yiming Wang, Zhuosheng Zhang, Pei Zhang +2
Neural-symbolic methods have demonstrated efficiency in enhancing the reasoning abilities of large language models (LLMs). However, existing methods mainly rely on syntactically ma…
Element-aware Summarization with Large Language Models: Expert-aligned Evaluation and Chain-of-Thought Method
Yiming Wang, Zhuosheng Zhang, Rui Wang
Automatic summarization generates concise summaries that contain key ideas of source documents. As the most mainstream datasets for the news sub-domain, CNN/DailyMail and BBC XSum…