Lili Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Lili Zhao has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Wei Chen
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China
3 shared publications - Linan Yue
School of Computer Science and Engineering, Southeast University & Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education, Nanjing, China
2 shared publications - Qi Liu
University of Science and Technology of China
2 shared publications - Tong Xu
University of Science and Technology of China, Hefei, China
2 shared publications - Chao Song
OPPO, Shenzhen, China
1 shared publication - Enhong Chen
University of Science and Technology of China
1 shared publication
Latest Publications
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 202-212
STRIDE: Strategic Iterative Decision-Making for Retrieval-Augmented Multi-Hop Question Answering
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 202-212
Open AccessSTRIDE: Strategic Iterative Decision-Making for Retrieval-Augmented Multi-Hop Question Answering
- Open Access
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 218-228
COMI: COrrect and MItigate Shortcut Learning Behavior in Deep Neural Networks
Deep Neural Networks (DNNs), despite their notable progress across information retrieval tasks, encounter the issues of shortcut learning and struggle with poor generalization due to their reliance on spurious correlations between features and labels. Current research mainly mitigates shortcut learning behavior using augmentation and distillation techniques, but these methods could be laborious and introduce unwarranted biases. To tackle these, in this paper, we propose COMI, a novel method to COrrect and MItigate shortcut learning behavior. Inspired by the ways students solve shortcuts in educational scenarios, we aim to reduce model's reliance on shortcuts and enhance its ability to extract underlying information integrated with standard Empirical Risk Minimization (ERM). Specifically, we first design Correct Habit (CoHa) strategy to retrieve the top m challenging samples for priority training, which encourages model to rely less on shortcuts in the early training. Then, to extract more meaningful underlying information, the information derived from ERM is separated into task-relevant and task-irrelevant information, the former serves as the primary basis for model predictions, while the latter is considered non-essential. However, within task-relevant information, certain potential shortcuts contribute to overconfident predictions. To mitigate this, we design Deep Mitigation (DeMi) network with shortcut margin loss to adaptively control the feature weights of shortcuts and eliminate their influence. Besides, to counteract unknown shortcut tokens issue in NLP, we adopt locally interpretable module-LIME to help recognize shortcut tokens. Finally, extensive experiments conducted on NLP and CV tasks demonstrate the effectiveness of COMI, which can perform well on both IID and OOD samples.
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 218-228
Open AccessCOMI: COrrect and MItigate Shortcut Learning Behavior in Deep Neural Networks
Deep Neural Networks (DNNs), despite their notable progress across information retrieval tasks, encounter the issues of shortcut learning and struggle with poor generalization due to their reliance on spurious correlations between features and labels. Current research mainly mitigates shortcut learning behavior using augmentation and distillation techniques, but these methods could be laborious and introduce unwarranted biases. To tackle these, in this paper, we propose COMI, a novel method to COrrect and MItigate shortcut learning behavior. Inspired by the ways students solve shortcuts in educational scenarios, we aim to reduce model's reliance on shortcuts and enhance its ability to extract underlying information integrated with standard Empirical Risk Minimization (ERM). Specifically, we first design Correct Habit (CoHa) strategy to retrieve the top m challenging samples for priority training, which encourages model to rely less on shortcuts in the early training. Then, to extract more meaningful underlying information, the information derived from ERM is separated into task-relevant and task-irrelevant information, the former serves as the primary basis for model predictions, while the latter is considered non-essential. However, within task-relevant information, certain potential shortcuts contribute to overconfident predictions. To mitigate this, we design Deep Mitigation (DeMi) network with shortcut margin loss to adaptively control the feature weights of shortcuts and eliminate their influence. Besides, to counteract unknown shortcut tokens issue in NLP, we adopt locally interpretable module-LIME to help recognize shortcut tokens. Finally, extensive experiments conducted on NLP and CV tasks demonstrate the effectiveness of COMI, which can perform well on both IID and OOD samples.
- Open Access
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2221-2230
Event Grounded Criminal Court View Generation with Cooperative (Large) Language Models
With the development of legal intelligence, Criminal Court View Generation has attracted much attention as a crucial task of legal intelligence, which aims to generate concise and coherent texts that summarize case facts and provide explanations for verdicts. Existing researches explore the key information in case facts to yield the court views. Most of them employ a coarse-grained approach that partitions the facts into broad segments (e.g., verdict-related sentences) to make predictions. However, this approach fails to capture the complex details present in the case facts, such as various criminal elements and legal events. To this end, in this paper, we propose an Event Grounded Generation (EGG) method for criminal court view generation with cooperative (Large) Language Models, which introduces the fine-grained event information into the generation. Specifically, we first design a LLMs-based extraction method that can extract events in case facts without massive annotated events. Then, we incorporate the extracted events into court view generation by merging case facts and events. Besides, considering the computational burden posed by the use of LLMs in the extraction phase of EGG, we propose a LLMs-free EGG method that can eliminate the requirement for event extraction using LLMs in the inference phase. Extensive experimental results on a real-world dataset clearly validate the effectiveness of our proposed method.
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2221-2230
Open AccessEvent Grounded Criminal Court View Generation with Cooperative (Large) Language Models
With the development of legal intelligence, Criminal Court View Generation has attracted much attention as a crucial task of legal intelligence, which aims to generate concise and coherent texts that summarize case facts and provide explanations for verdicts. Existing researches explore the key information in case facts to yield the court views. Most of them employ a coarse-grained approach that partitions the facts into broad segments (e.g., verdict-related sentences) to make predictions. However, this approach fails to capture the complex details present in the case facts, such as various criminal elements and legal events. To this end, in this paper, we propose an Event Grounded Generation (EGG) method for criminal court view generation with cooperative (Large) Language Models, which introduces the fine-grained event information into the generation. Specifically, we first design a LLMs-based extraction method that can extract events in case facts without massive annotated events. Then, we incorporate the extracted events into court view generation by merging case facts and events. Besides, considering the computational burden posed by the use of LLMs in the extraction phase of EGG, we propose a LLMs-free EGG method that can eliminate the requirement for event extraction using LLMs in the inference phase. Extensive experimental results on a real-world dataset clearly validate the effectiveness of our proposed method.
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 296-305
HEProto: A Hierarchical Enhancing ProtoNet based on Multi-Task Learning for Few-shot Named Entity Recognition
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 296-305
Open AccessHEProto: A Hierarchical Enhancing ProtoNet based on Multi-Task Learning for Few-shot Named Entity Recognition