40 citations · 137 across the 14 of their papers we have counts for
14 papers
ORCE: Order-Aware Alignment of Verbalized Confidence in Large Language Models
Chen Li, Xiaoling Hu, Songzhu Zheng +2
Large language models (LLMs) often produce answers with high certainty even when they are incorrect, making reliable confidence estimation essential for deployment in real-world sc…
SHARP: A Self-Evolving Human-Auditable Rubric Policy for Financial Trading Agents
Xiwen Chen, Wenhui Zhu, Songzhu Zheng +3
Large language models (LLMs) are increasingly deployed for autonomous financial trading, a domain requiring continuous adaptation to noisy, non-stationary markets. Existing self-im…
Reweighting Improves Conditional Risk Bounds
Yikai Zhang, Jiahe Lin, Fengpei Li +4
In this work, we study the weighted empirical risk minimization (weighted ERM) schema, in which an additional data-dependent weight function is incorporated when the empirical risk…
Task-Agnostic Detector for Insertion-Based Backdoor Attacks
Weimin Lyu, Xiao Lin, Songzhu Zheng +4
Textual backdoor attacks pose significant security threats. Current detection approaches, typically relying on intermediate feature representation or reconstructing potential trigg…
Attention-Enhancing Backdoor Attacks Against BERT-based Models
Weimin Lyu, Songzhu Zheng, Lu Pang +2
Recent studies have revealed that \textit{Backdoor Attacks} can threaten the safety of natural language processing (NLP) models. Investigating the strategies of backdoor attacks wi…
Learning to Abstain From Uninformative Data
Yikai Zhang, Songzhu Zheng, Mina Dalirrooyfard +5
Learning and decision-making in domains with naturally high noise-to-signal ratio, such as Finance or Healthcare, is often challenging, while the stakes are very high. In this pape…
Learning to Segment from Noisy Annotations: A Spatial Correction Approach
Jiachen Yao, Yikai Zhang, Songzhu Zheng +3
Noisy labels can significantly affect the performance of deep neural networks (DNNs). In medical image segmentation tasks, annotations are error-prone due to the high demand in ann…
Attention Hijacking in Trojan Transformers
Weimin Lyu, Songzhu Zheng, Tengfei Ma +2
Trojan attacks pose a severe threat to AI systems. Recent works on Transformer models received explosive popularity and the self-attentions are now indisputable. This raises a cent…
A Multimodal Transformer: Fusing Clinical Notes with Structured EHR Data for Interpretable In-Hospital Mortality Prediction
Weimin Lyu, Xinyu Dong, Rachel Wong +4
Deep-learning-based clinical decision support using structured electronic health records (EHR) has been an active research area for predicting risks of mortality and diseases. Mean…
A Study of the Attention Abnormality in Trojaned BERTs
Weimin Lyu, Songzhu Zheng, Tengfei Ma +1
Trojan attacks raise serious security concerns. In this paper, we investigate the underlying mechanism of Trojaned BERT models. We observe the attention focus drifting behavior of…
Topological Detection of Trojaned Neural Networks
Songzhu Zheng, Yikai Zhang, Hubert Wagner +2
Deep neural networks are known to have security issues. One particular threat is the Trojan attack. It occurs when the attackers stealthily manipulate the model's behavior through…
Learning with Feature-Dependent Label Noise: A Progressive Approach
Yikai Zhang, Songzhu Zheng, Pengxiang Wu +2
Label noise is frequently observed in real-world large-scale datasets. The noise is introduced due to a variety of reasons; it is heterogeneous and feature-dependent. Most existing…
A Topological Filter for Learning with Label Noise
Pengxiang Wu, Songzhu Zheng, Mayank Goswami +2
Noisy labels can impair the performance of deep neural networks. To tackle this problem, in this paper, we propose a new method for filtering label noise. Unlike most existing meth…
Error-Bounded Correction of Noisy Labels
Songzhu Zheng, Pengxiang Wu, Aman Goswami +3
To collect large scale annotated data, it is inevitable to introduce label noise, i.e., incorrect class labels. To be robust against label noise, many successful methods rely on th…