Jialu Liu
Research Subjects
Jialu Liu has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Jiaming Shen
Google, New York, USA
2 shared publications - Marc Najork
Google DeepMind, Mountain View, California, USA
2 shared publications - Michael Bendersky
Google, Mountain View, CA, USA
2 shared publications - Chao Zhang
Georgia Institute of Technology, Atlanta, GA, USA
1 shared publication - Dan Finnie
Google, USA
1 shared publication - Di Bai
Google LLC, Mountain View, CA, USA
1 shared publication
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8129-8136
Decomposing Staleness in Recommender Systems: A Dual-Filter Framework for Supersession and Decay
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8129-8136
Open AccessDecomposing Staleness in Recommender Systems: A Dual-Filter Framework for Supersession and Decay
- Open Access
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 4278-4289
Knowledge Distillation with Perturbed Loss: From a Vanilla Teacher to a Proxy Teacher
Knowledge distillation is a popular technique to transfer knowledge from a large teacher model to a small student model. Typically, the student learns to imitate the teacher by minimizing the KL divergence of its output distribution with the teacher's output distribution. In this work, we argue that such a learning objective is sub-optimal because there exists a discrepancy between the teacher's output distribution and the ground truth label distribution. Therefore, forcing the student to blindly imitate the unreliable teacher output distribution leads to inferior performance. To this end, we propose a novel knowledge distillation objective PTLoss by first representing the vanilla KL-based distillation loss function via a Maclaurin series and then perturbing the leading-order terms in this series. This perturbed loss implicitly transforms the original teacher into a proxy teacher with a distribution closer to the ground truth distribution. We establish the theoretical connection between this "distribution closeness'' and the student model generalizability, which enables us to select the PTLoss's perturbation coefficients in a principled way. Extensive experiments on six public benchmark datasets demonstrate the effectiveness of PTLoss with teachers of different scales.
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 4278-4289
Open AccessKnowledge Distillation with Perturbed Loss: From a Vanilla Teacher to a Proxy Teacher
Knowledge distillation is a popular technique to transfer knowledge from a large teacher model to a small student model. Typically, the student learns to imitate the teacher by minimizing the KL divergence of its output distribution with the teacher's output distribution. In this work, we argue that such a learning objective is sub-optimal because there exists a discrepancy between the teacher's output distribution and the ground truth label distribution. Therefore, forcing the student to blindly imitate the unreliable teacher output distribution leads to inferior performance. To this end, we propose a novel knowledge distillation objective PTLoss by first representing the vanilla KL-based distillation loss function via a Maclaurin series and then perturbing the leading-order terms in this series. This perturbed loss implicitly transforms the original teacher into a proxy teacher with a distribution closer to the ground truth distribution. We establish the theoretical connection between this "distribution closeness'' and the student model generalizability, which enables us to select the PTLoss's perturbation coefficients in a principled way. Extensive experiments on six public benchmark datasets demonstrate the effectiveness of PTLoss with teachers of different scales.
- Open Access
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1662-1672
“Why is this misleading?”: Detecting News Headline Hallucinations with Explanations
Automatic headline generation enables users to comprehend ongoing news events promptly and has recently become an important task in web mining and natural language processing. With the growing need for news headline generation, we argue that the hallucination issue, namely the generated headlines being not supported by the original news stories, is a critical challenge for the deployment of this feature in web-scale systems Meanwhile, due to the infrequency of hallucination cases and the requirement of careful reading for raters to reach the correct consensus, it is difficult to acquire a large dataset for training a model to detect such hallucinations through human curation. In this work, we present a new framework named ExHalder to address this challenge for headline hallucination detection. ExHalder adapts the knowledge from public natural language inference datasets into the news domain and learns to generate natural language sentences to explain the hallucination detection results. To evaluate the model performance, we carefully collect a dataset with more than six thousand labeled ⟨ article, headline⟩ pairs. Extensive experiments on this dataset and another six public ones demonstrate that ExHalder can identify hallucinated headlines accurately and justifies its predictions with human-readable natural language explanations.
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1662-1672
Open Access“Why is this misleading?”: Detecting News Headline Hallucinations with Explanations
Automatic headline generation enables users to comprehend ongoing news events promptly and has recently become an important task in web mining and natural language processing. With the growing need for news headline generation, we argue that the hallucination issue, namely the generated headlines being not supported by the original news stories, is a critical challenge for the deployment of this feature in web-scale systems Meanwhile, due to the infrequency of hallucination cases and the requirement of careful reading for raters to reach the correct consensus, it is difficult to acquire a large dataset for training a model to detect such hallucinations through human curation. In this work, we present a new framework named ExHalder to address this challenge for headline hallucination detection. ExHalder adapts the knowledge from public natural language inference datasets into the news domain and learns to generate natural language sentences to explain the hallucination detection results. To evaluate the model performance, we carefully collect a dataset with more than six thousand labeled ⟨ article, headline⟩ pairs. Extensive experiments on this dataset and another six public ones demonstrate that ExHalder can identify hallucinated headlines accurately and justifies its predictions with human-readable natural language explanations.