Jialu Liu
Jialu Liu is a senior staff software engineer working on news understanding at Google Research, New York. He received B.S. in Computer Science from Zhejiang University and graduated from University of Illinois at Urbana-Champaign (UIUC) in 2016, under the supervision of Professor Jiawei Han. [Homepage]
Authored Publications
Sort By
Knowledge Distillation with Perturbed Loss: From a Vanilla Teacher to a Proxy Teacher
Rongzhi Zhang
Chao Zhang
Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2024), ACM, pp. 4278 - 4289
Preview abstract
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.
View details
Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting
Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) (2024)
Preview abstract
Ranking documents using Large Language Models (LLMs) by directly feeding the query and candidate documents into the prompt is an interesting and practical problem. However, researchers have found it difficult to outperform fine-tuned baseline rankers on benchmark datasets. We analyze pointwise and listwise ranking prompts used by existing methods and argue that off-the-shelf LLMs do not fully understand these challenging ranking formulations. In this paper, we propose to significantly reduce the burden on LLMs by using a new technique called Pairwise Ranking Prompting (PRP). Our results are the first in the literature to achieve state-of-the-art ranking performance on standard benchmarks using moderate-sized open-sourced LLMs. On TREC-DL 2019&2020, PRP based on the Flan-UL2 model with 20B parameters performs favorably with the previous best approach in the literature, which is based on the blackbox commercial GPT-4 that has 50x (estimated) model size, while outperforming other LLM-based solutions, such as InstructGPT which has 175B parameters, by over 10% for all ranking metrics. By using the same prompt template on seven BEIR tasks, PRP outperforms supervised baselines and outperforms the blackbox commercial ChatGPT solution by 4.2% and pointwise LLM-based solutions by more than 10% on average NDCG@10. Furthermore, we propose several variants of PRP to improve efficiency and show that it is possible to achieve competitive results even with linear complexity.
View details
“Why is this misleading?”: Detecting News Headline Hallucinations with Explanations
Dan Finnie
Negar Rahmati
Proceedings of the ACM Web Conference 2023 (WWW 2023)
Preview abstract
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.
View details
Preview abstract
Multi-Task Learning (MTL) models have shown their robustness, effectiveness, and efficiency for transferring learned knowledge across tasks. In real industrial applications such as web content classification, multiple classification tasks are predicted from the same input text such as a web article. However, at the serving time, the existing multitask transformer models such as prompt or adaptor based approaches need to conduct N forward passes for N tasks with O(N) computation cost. To tackle this problem, we propose a scalable method that can achieve stronger performance with close to O(1) computation cost via only one forward pass. To illustrate real application usage, we release a multitask dataset on news topic and style classification. Our experiments show that our proposed method outperforms strong baselines on both the GLUE benchmark and our news dataset.
View details
Preview abstract
Multi-head attention plays a crucial role in the recent success of Transformer models, which leads to consistent performance improvements over conventional attention in various applications. The popular belief is that this effectiveness stems from the ability of jointly attending multiple positions. In this paper, we first demonstrate that jointly attending multiple positions is not a unique feature of multi-head attention, as multi-layer single-head attention also attends multiple positions and is more effective. Then, we suggest the main advantage of the multi-head attention is the training stability, since it has less number of layers than the single-head attention, when attending the same number of positions. For example, 24-layer 16-head Transformer (BERT-large) and 384-layer single-head Transformer has the same total attention head number and roughly the same model size, while the multi-head one is significantly shallower. Meanwhile, we show that, with recent advances in deep learning, we can successfully stabilize the training of the 384-layer Transformer. As the training difficulty is no longer a bottleneck, substantially deeper single-head Transformer achieves consistent performance improvements without tuning hyper-parameters.
View details
Preview abstract
Pre-trained text encoders such as BERT and its variants have recently achieved state-of-the-art performances on many NLP tasks. While being effective, these pre-training methods typically demand massive computation resources. To accelerate pre-training, ELECTRA trains a discriminator that predicts whether each input token is replaced by a generator. However, this new task, as a binary classification, is less semantically informative. In this study, we present a new text encoder pre-training method that improves ELECTRA based on multi-task learning. Specifically, we train the discriminator to simultaneously detect replaced tokens and select original tokens from candidate sets. We further develop two techniques to effectively combine all pre-training tasks: (1) using attention-based networks for task-specific heads, and (2) sharing bottom layers of the generator and the discriminator. Extensive experiments on GLUE and SQuAD datasets demonstrate both the effectiveness and the efficiency of our proposed method.
View details
Preview abstract
Effectively modeling text-rich fresh content such as news articles
and blog posts is a challenging problem. To ensure a content-based
model generalize well to a broad range of applications, it is critical
to have a training dataset that is large beyond the scale of human
labels while achieving desired quality. In this work, we addressing those two challenges by proposing a novel approach to mine
semantically-relevant fresh documents, and their topic labels, with
little human supervision. Specifically, we design a multitask model
that alternate trains a contrasting learning with a multi-label classification to derive an universal document encoder. We show that
this approach can provide billions of high quality organic training examples and can be naturally extended to multilingual setting
where texts in different languages are encoded in the same semantic
space. We experimentally demonstrate NewsEmbed’s competitive
performance across multiple natural language understanding tasks,
both supervised and unsupervised.
View details
Generating Representative Headlines for News Stories
Xiaotao Gu
Yuning Mao
Jiawei Han
Cong Yu
Daniel Finnie
Jiaqi Zhai
Nick Zukoski
The Web Conference 2020
Preview abstract
Millions of news articles are published online every day, which can be overwhelming for readers to follow. Grouping articles that are reporting the same event into news stories is a common way of assisting readers in their news consumption. However, it remains a challenging research problem to efficiently and effectively generate a representative headline for each story. Automatic summarization of a document set has been studied for decades, while few studies have focused on generating representative headlines for a set of articles. Unlike summaries, which aim to capture most information with least redundancy, headlines aim to capture information jointly shared by the story articles in short length, and exclude information that is too specific to each individual article. In this work, we study the problem of generating representative headlines for news stories. We develop a distant supervision approach to train large-scale generation models without any human annotation. This approach centers on two technical components. First, we propose a multi-level pre-training framework that incorporates massive unlabeled corpus with different quality-vs.-quantity balance at different levels. We show that models trained within this framework outperform those trained with pure human curated corpus. Second, we propose a novel self-voting-based article attention layer to extract salient information shared by multiple articles. We show that models that incorporate this layer are robust to potential noises in news stories and outperform existing baselines with or without noises. We can further enhance our model by incorporating human labels, and we show our distant supervision approach significantly reduces the demand on labeled data.
View details
Preview abstract
Modern search engines increasingly incorporate tabular content,
which consists of a set of entities each augmented with a small set
of facts. The facts can be obtained from multiple sources: an entity’s
knowledge base entry, the infobox on its Wikipedia page, or its row
within a WebTable. Crucially, the informativeness of a fact depends
not only on the entity but also the specific context (e.g., the query).
To the best of our knowledge, this paper is the first to study the
problem of contextual fact ranking: given some entities and a con-
text (i.e., succinct natural language description), identify the most
informative facts for the entities collectively within the context.
We propose to contextually rank the facts by exploiting deep
learning techniques. In particular, we develop pointwise and pair-
wise ranking models, using textual and statistical information for
the given entities and context derived from their sources. We en-
hance the models by incorporating entity type information from
an IsA (hypernym) database. We demonstrate that our approaches
achieve better performance than state-of-the-art baselines in terms
of MAP, NDCG, and recall. We further conduct user studies for two
specific applications of contextual fact ranking—table synthesis and
table compression—and show that our models can identify more
informative facts than the baselines.
View details
Knowledge Exploration using Tables on the Web
Fernando Chirigati
Cong Yu
Proceedings of the VLDB Endowment, 10 (2017), pp. 193-204
Preview abstract
The increasing popularity of mobile device usage has ushered in many features in modern search engines that help users with various information needs. One of those needs is Knowledge Exploration, where related documents are returned in response to a user query, either directly through right-hand side knowledge panels or indirectly through navigable sections underneath individual search results. Existing knowledge exploration features have relied on a combination of Knowledge Bases and query logs. In this paper, we propose Knowledge Carousels of two modalities, namely sideways and downwards, that facilitate exploration of IS-A and HAS-A relationships, respectively, with regard to an entity-seeking query, based on leveraging the large corpus of tables on the Web. This brings many
technical challenges, including associating correct carousels with the search entity, selecting the best carousel from the candidates, and finding titles that best describe the carousel. We describe how we address these challenges and also experimentally demonstrate through user studies that our approach produces better result sets than baseline approaches.
View details
