7 papers
CHILL-Harness: Counterfactual Harness Learning for Efficient Reasoning in Long-Horizon Agents
Jiarun Fu, Lizhong Ding, Sida Chen +6
Agent harnesses have become the operational infrastructure of modern large language model agents, coordinating context, tools, verification, and execution control to translate late…
DeepFaith: A Domain-Free and Model-Agnostic Unified Framework for Highly Faithful Explanations
Yuhan Guo, Lizhong Ding, Shihan Jia +6
Explainable AI (XAI) builds trust in complex systems through model attribution methods that reveal the decision rationale. However, due to the absence of a unified optimal explanat…
Unveiling and Causalizing CoT: A Causal Pespective
Jiarun Fu, Lizhong Ding, Hao Li +3
Although Chain-of-Thought (CoT) has achieved remarkable success in enhancing the reasoning ability of large language models (LLMs), the mechanism of CoT remains a ``black box''. Ev…
Testing for Causal Fairness
Jiarun Fu, LiZhong Ding, Pengqi Li +3
Causality is widely used in fairness analysis to prevent discrimination on sensitive attributes, such as genders in career recruitment and races in crime prediction. However, the c…
How phonemes contribute to deep speaker models?
Pengqi Li, Tianhao Wang, Lantian Li +2
Which phonemes convey more speaker traits is a long-standing question, and various perception experiments were conducted with human subjects. For speaker recognition, studies were…
Visualizing data augmentation in deep speaker recognition
Pengqi Li, Lantian Li, Askar Hamdulla +1
Visualization is of great value in understanding the internal mechanisms of neural networks. Previous work found that LayerCAM is a reliable visualization tool for deep speaker mod…
Reliable Visualization for Deep Speaker Recognition
Pengqi Li, Lantian Li, Askar Hamdulla +1
In spite of the impressive success of convolutional neural networks (CNNs) in speaker recognition, our understanding to CNNs' internal functions is still limited. A major obstacle…