Publications (58)
Topic Taxonomy Expansion via Hierarchy-Aware Topic Phrase Generation
Dongha Lee, Jiaming Shen, Seonghyeon Lee +3
Topic taxonomies display hierarchical topic structures of a text corpus and provide topical knowledge to enhance various NLP applications. To dynamically incorporate new topic info…
Weakly-Supervised Hierarchical Text Classification
Yu Meng, Jiaming Shen, Chao Zhang +1
Hierarchical text classification, which aims to classify text documents into a given hierarchy, is an important task in many real-world applications. Recently, deep neural models a…
TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusters
Dongha Lee, Jiaming Shen, SeongKu Kang +3
Topic taxonomies, which represent the latent topic (or category) structure of document collections, provide valuable knowledge of contents in many applications such as web search a…
TaxoExpan: Self-supervised Taxonomy Expansion with Position-Enhanced Graph Neural Network
Jiaming Shen, Zhihong Shen, Chenyan Xiong +3
Taxonomies consist of machine-interpretable semantics and provide valuable knowledge for many web applications. For example, online retailers (e.g., Amazon and eBay) use taxonomies…
SetExpan: Corpus-Based Set Expansion via Context Feature Selection and Rank Ensemble
Jiaming Shen, Zeqiu Wu, Dongming Lei +3
Corpus-based set expansion (i.e., finding the "complete" set of entities belonging to the same semantic class, based on a given corpus and a tiny set of seeds) is a critical task i…
End-to-End Reinforcement Learning for Automatic Taxonomy Induction
Yuning Mao, Xiang Ren, Jiaming Shen +2
We present a novel end-to-end reinforcement learning approach to automatic taxonomy induction from a set of terms. While prior methods treat the problem as a two-phase task (i.e.,…
HiPrompt: Few-Shot Biomedical Knowledge Fusion via Hierarchy-Oriented Prompting
Jiaying Lu, Jiaming Shen, Bo Xiong +3
Medical decision-making processes can be enhanced by comprehensive biomedical knowledge bases, which require fusing knowledge graphs constructed from different sources via a unifor…
"Why is this misleading?": Detecting News Headline Hallucinations with Explanations
Jiaming Shen, Jialu Liu, Dan Finnie +3
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…
Building Math Agents with Multi-Turn Iterative Preference Learning
Wei Xiong, Chengshuai Shi, Jiaming Shen +10
Recent studies have shown that large language models' (LLMs) mathematical problem-solving capabilities can be enhanced by integrating external tools, such as code interpreters, and…
FUSE: Multi-Faceted Set Expansion by Coherent Clustering of Skip-grams
Wanzheng Zhu, Hongyu Gong, Jiaming Shen +4
Set expansion aims to expand a small set of seed entities into a complete set of relevant entities. Most existing approaches assume the input seed set is unambiguous and completely…
Investigating Rumor News Using Agreement-Aware Search
Jingbo Shang, Tianhang Sun, Jiaming Shen +6
Recent years have witnessed a widespread increase of rumor news generated by humans and machines. Therefore, tools for investigating rumor news have become an urgent necessity. One…
Text Network Exploration via Heterogeneous Web of Topics
Junxian He, Ying Huang, Changfeng Liu +3
A text network refers to a data type that each vertex is associated with a text document and the relationship between documents is represented by edges. The proliferation of text n…
Taxonomy Completion via Triplet Matching Network
Jieyu Zhang, Xiangchen Song, Ying Zeng +4
Automatically constructing taxonomy finds many applications in e-commerce and web search. One critical challenge is as data and business scope grow in real applications, new concep…
Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias
Yue Yu, Yuchen Zhuang, Jieyu Zhang +5
Large language models (LLMs) have been recently leveraged as training data generators for various natural language processing (NLP) tasks. While previous research has explored diff…
Near-imperceptible Neural Linguistic Steganography via Self-Adjusting Arithmetic Coding
Jiaming Shen, Heng Ji, Jiawei Han
Linguistic steganography studies how to hide secret messages in natural language cover texts. Traditional methods aim to transform a secret message into an innocent text via lexica…
Multilingual Fine-Grained News Headline Hallucination Detection
Jiaming Shen, Tianqi Liu, Jialu Liu +4
The popularity of automated news headline generation has surged with advancements in pre-trained language models. However, these models often suffer from the ``hallucination'' prob…
CubeNet: Multi-Facet Hierarchical Heterogeneous Network Construction, Analysis, and Mining
Carl Yang, Dai Teng, Siyang Liu +8
Due to the ever-increasing size of data, construction, analysis and mining of universal massive networks are becoming forbidden and meaningless. In this work, we outline a novel fr…
Wikidata Vandalism Detection - The Loganberry Vandalism Detector at WSDM Cup 2017
Qi Zhu, Hongwei Ng, Liyuan Liu +4
Wikidata is the new, large-scale knowledge base of the Wikimedia Foundation. As it can be edited by anyone, entries frequently get vandalized, leading to the possibility that it mi…
Bridging the Gap: Sketch-Aware Interpolation Network for High-Quality Animation Sketch Inbetweening
Jiaming Shen, Kun Hu, Wei Bao +2
Hand-drawn 2D animation workflow is typically initiated with the creation of sketch keyframes. Subsequent manual inbetweens are crafted for smoothness, which is a labor-intensive p…
Corpus-based Open-Domain Event Type Induction
Jiaming Shen, Yunyi Zhang, Heng Ji +1
Traditional event extraction methods require predefined event types and their corresponding annotations to learn event extractors. These prerequisites are often hard to be satisfie…
Unsupervised Key Event Detection from Massive Text Corpora
Yunyi Zhang, Fang Guo, Jiaming Shen +1
Automated event detection from news corpora is a crucial task towards mining fast-evolving structured knowledge. As real-world events have different granularities, from the top-lev…
Guiding Corpus-based Set Expansion by Auxiliary Sets Generation and Co-Expansion
Jiaxin Huang, Yiqing Xie, Yu Meng +3
Given a small set of seed entities (e.g., ``USA'', ``Russia''), corpus-based set expansion is to induce an extensive set of entities which share the same semantic class (Country in…
Towards Disentangling Relevance and Bias in Unbiased Learning to Rank
Yunan Zhang, Le Yan, Zhen Qin +5
Unbiased learning to rank (ULTR) studies the problem of mitigating various biases from implicit user feedback data such as clicks, and has been receiving considerable attention rec…
Empower Entity Set Expansion via Language Model Probing
Yunyi Zhang, Jiaming Shen, Jingbo Shang +1
Entity set expansion, aiming at expanding a small seed entity set with new entities belonging to the same semantic class, is a critical task that benefits many downstream NLP and I…
Training ELECTRA Augmented with Multi-word Selection
Jiaming Shen, Jialu Liu, Tianqi Liu +2
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 ty…
HeMeNet: Heterogeneous Multichannel Equivariant Network for Protein Multitask Learning
Rong Han, Wenbing Huang, Lingxiao Luo +5
Understanding and leveraging the 3D structures of proteins is central to a variety of biological and drug discovery tasks. While deep learning has been applied successfully for str…
Discovering Hypernymy in Text-Rich Heterogeneous Information Network by Exploiting Context Granularity
Yu Shi, Jiaming Shen, Yuchen Li +7
Text-rich heterogeneous information networks (text-rich HINs) are ubiquitous in real-world applications. Hypernymy, also known as is-a relation or subclass-of relation, lays in the…
Cold-Start Data Selection for Few-shot Language Model Fine-tuning: A Prompt-Based Uncertainty Propagation Approach
Yue Yu, Rongzhi Zhang, Ran Xu +3
Large Language Models have demonstrated remarkable few-shot performance, but the performance can be sensitive to the selection of few-shot instances. We propose PATRON, a new metho…
LAMPO: Large Language Models as Preference Machines for Few-shot Ordinal Classification
Zhen Qin, Junru Wu, Jiaming Shen +2
We introduce LAMPO, a novel paradigm that leverages Large Language Models (LLMs) for solving few-shot multi-class ordinal classification tasks. Unlike conventional methods, which c…
Entity Set Search of Scientific Literature: An Unsupervised Ranking Approach
Jiaming Shen, Jinfeng Xiao, Xinwei He +3
Literature search is critical for any scientific research. Different from Web or general domain search, a large portion of queries in scientific literature search are entity-set qu…
Explanation-aware Soft Ensemble Empowers Large Language Model In-context Learning
Yue Yu, Jiaming Shen, Tianqi Liu +5
Large language models (LLMs) have shown remarkable capabilities in various natural language understanding tasks. With only a few demonstration examples, these LLMs can quickly adap…
SynSetExpan: An Iterative Framework for Joint Entity Set Expansion and Synonym Discovery
Jiaming Shen, Wenda Qiu, Jingbo Shang +3
Entity set expansion and synonym discovery are two critical NLP tasks. Previous studies accomplish them separately, without exploring their interdependencies. In this work, we hypo…
Boosting Reward Model with Preference-Conditional Multi-Aspect Synthetic Data Generation
Jiaming Shen, Ran Xu, Yennie Jun +6
Reward models (RMs) are crucial for aligning large language models (LLMs) with human preferences. They are trained using preference datasets where each example consists of one inpu…
RRM: Robust Reward Model Training Mitigates Reward Hacking
Tianqi Liu, Wei Xiong, Jie Ren +15
Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human preferences. However, traditional RM training, which relies on response pairs tied to sp…
IC-Cache: Efficient Large Language Model Serving via In-context Caching
Yifan Yu, Yu Gan, Nikhil Sarda +7
Large language models (LLMs) have excelled in various applications, yet serving them at scale is challenging due to their substantial resource demands and high latency. Our real-wo…
Eliciting Knowledge from Experts:Automatic Transcript Parsing for Cognitive Task Analysis
Junyi Du, He Jiang, Jiaming Shen +1
Cognitive task analysis (CTA) is a type of analysis in applied psychology aimed at eliciting and representing the knowledge and thought processes of domain experts. In CTA, often h…
RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation
Pengcheng Jiang, Lang Cao, Ruike Zhu +5
Large language models (LLMs) have achieved impressive performance on knowledge-intensive tasks, yet they often struggle with multi-step reasoning due to the unstructured nature of…
Integrating Planning into Single-Turn Long-Form Text Generation
Yi Liang, You Wu, Honglei Zhuang +8
Generating high-quality, in-depth textual documents, such as academic papers, news articles, Wikipedia entries, and books, remains a significant challenge for Large Language Models…
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…
Do Not Blindly Imitate the Teacher: Using Perturbed Loss for Knowledge Distillation
Rongzhi Zhang, Jiaming Shen, Tianqi Liu +4
Knowledge distillation is a popular technique to transfer knowledge from large teacher models to a small student model. Typically, the student learns to imitate the teacher by mini…
Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting
Zhen Qin, Rolf Jagerman, Kai Hui +9
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, researc…
Who Should Go First? A Self-Supervised Concept Sorting Model for Improving Taxonomy Expansion
Xiangchen Song, Jiaming Shen, Jieyu Zhang +1
Taxonomies have been widely used in various machine learning and text mining systems to organize knowledge and facilitate downstream tasks. One critical challenge is that, as data…
TELEClass: Taxonomy Enrichment and LLM-Enhanced Hierarchical Text Classification with Minimal Supervision
Yunyi Zhang, Ruozhen Yang, Xueqiang Xu +4
Hierarchical text classification aims to categorize each document into a set of classes in a label taxonomy, which is a fundamental web text mining task with broad applications suc…
TaxoGen: Unsupervised Topic Taxonomy Construction by Adaptive Term Embedding and Clustering
Chao Zhang, Fangbo Tao, Xiusi Chen +5
Taxonomy construction is not only a fundamental task for semantic analysis of text corpora, but also an important step for applications such as information filtering, recommendatio…
Multi-Task Learning for Email Search Ranking with Auxiliary Query Clustering
Jiaming Shen, Maryam Karimzadehgan, Michael Bendersky +2
User information needs vary significantly across different tasks, and therefore their queries will also differ considerably in their expressiveness and semantics. Many studies have…
Query-Specific Knowledge Summarization with Entity Evolutionary Networks
Carl Yang, Lingrui Gan, Zongyi Wang +3
Given a query, unlike traditional IR that finds relevant documents or entities, in this work, we focus on retrieving both entities and their connections for insightful knowledge su…
LiPO: Listwise Preference Optimization through Learning-to-Rank
Tianqi Liu, Zhen Qin, Junru Wu +9
Aligning language models (LMs) with curated human feedback is critical to control their behaviors in real-world applications. Several recent policy optimization methods, such as DP…
Mining Entity Synonyms with Efficient Neural Set Generation
Jiaming Shen, Ruiliang Lyu, Xiang Ren +3
Mining entity synonym sets (i.e., sets of terms referring to the same entity) is an important task for many entity-leveraging applications. Previous work either rank terms based on…
OmniNeRF: Hybriding Omnidirectional Distance and Radiance fields for Neural Surface Reconstruction
Jiaming Shen, Bolin Song, Zirui Wu +1
3D reconstruction from images has wide applications in Virtual Reality and Automatic Driving, where the precision requirement is very high. Ground-breaking research in the neural r…
PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs
Rongzhi Zhang, Jiaming Shen, Tianqi Liu +7
Large Language Models (LLMs) have exhibited impressive capabilities in various tasks, yet their vast parameter sizes restrict their applicability in resource-constrained settings.…
Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters
Boshi Wang, Sewon Min, Xiang Deng +4
Chain-of-Thought (CoT) prompting can dramatically improve the multi-step reasoning abilities of large language models (LLMs). CoT explicitly encourages the LLM to generate intermed…
Local Boosting for Weakly-Supervised Learning
Rongzhi Zhang, Yue Yu, Jiaming Shen +2
Boosting is a commonly used technique to enhance the performance of a set of base models by combining them into a strong ensemble model. Though widely adopted, boosting is typicall…
Weakly-Supervised Neural Text Classification
Yu Meng, Jiaming Shen, Chao Zhang +1
Deep neural networks are gaining increasing popularity for the classic text classification task, due to their strong expressive power and less requirement for feature engineering.…
Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusion
Yiqing Xie, Jiaming Shen, Sha Li +2
Document-level relation extraction (DocRE) aims to extract semantic relations among entity pairs in a document. Typical DocRE methods blindly take the full document as input, while…
HiExpan: Task-Guided Taxonomy Construction by Hierarchical Tree Expansion
Jiaming Shen, Zeqiu Wu, Dongming Lei +5
Taxonomies are of great value to many knowledge-rich applications. As the manual taxonomy curation costs enormous human effects, automatic taxonomy construction is in great demand.…
Predicting Text Preference Via Structured Comparative Reasoning
Jing Nathan Yan, Tianqi Liu, Justin T Chiu +9
Comparative reasoning plays a crucial role in text preference prediction; however, large language models (LLMs) often demonstrate inconsistencies in their reasoning. While approach…
ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval
Yue Yu, Yuchen Zhuang, Rongzhi Zhang +3
With the development of large language models (LLMs), zero-shot learning has attracted much attention for various NLP tasks. Different from prior works that generate training data…
STEAM: Self-Supervised Taxonomy Expansion with Mini-Paths
Yue Yu, Yinghao Li, Jiaming Shen +3
Taxonomies are important knowledge ontologies that underpin numerous applications on a daily basis, but many taxonomies used in practice suffer from the low coverage issue. We stud…