papers

Publications (91)

cs.DB2024

RetClean: Retrieval-Based Data Cleaning Using Foundation Models and Data Lakes

Zan Ahmad Naeem, Mohammad Shahmeer Ahmad, Mohamed Eltabakh +2

Can foundation models (such as ChatGPT) clean your data? In this proposal, we demonstrate that indeed ChatGPT can assist in data cleaning by suggesting corrections for specific cel…

cs.LG2025

ReLAM: Learning Anticipation Model for Rewarding Visual Robotic Manipulation

Nan Tang, Jing-Cheng Pang, Guanlin Li +2

Reward design remains a critical bottleneck in visual reinforcement learning (RL) for robotic manipulation. In simulated environments, rewards are conventionally designed based on…

cond-mat.str-el2026

Observation via spin Seebeck effect of macroscopic magnetic transport from emergent magnetic monopoles

Nan Tang, Stephan Glamsch, Aisha Aqeel +7

Magnetic monopoles, elusive in high-energy physics, have been realised as emergent quasiparticles in solid-state systems, where their unique properties hold promise for novel spint…

cond-mat.str-el2021

Phonon spectrum of PrZrO and PrIrO as an evidence of coupling of the lattice with electronic and magnetic degrees of freedom

Yuanyuan Xu, Huiyuan Man, Nan Tang +5

Magnetic materials with pyrochlore crystal structure form exotic magnetic states due to the high lattice frustration. In this work we follow the effects of coupling of the lattice…

cs.LG2025

SCAR: A Characterization Scheme for Multi-Modal Dataset

Ri Su, Zhao Chen, Caleb Chen Cao +2

Foundation models exhibit remarkable generalization across diverse tasks, largely driven by the characteristics of their training data. Recent data-centric methods like pruning and…

cond-mat.str-el2023

Hole doping in compositionally complex correlated oxide enables tunable exchange biasing

Alessandro R. Mazza, Elizabeth Skoropata, Jason Lapano +8

Magnetic interfaces and the phenomena arising from them drive both the design of modern spintronics and fundamental research. Recently, it was revealed that through designing magne…

cond-mat.str-el2021

Importance of dynamic lattice effects for crystal field excitations in quantum spin ice candidate PrZrO

Yuanyuan Xu, Huiyuan Man, Nan Tang +5

PrZrO is a pyrochlore quantum spin-ice candidate. Using Raman scattering spectroscopy we probe crystal electric field excitations of Pr, and demonstrate the impo…

cs.AI2026

DocSage: An Information Structuring Agent for Multi-Doc Multi-Entity Question Answering

Teng Lin, Yizhang Zhu, Zhengxuan Zhang +2

Multi-document Multi-entity Question Answering inherently demands models to track implicit logic between multiple entities across scattered documents. However, existing Large Langu…

cs.MA2025

Will LLMs be Professional at Fund Investment? DeepFund: A Live Arena Perspective

Changlun Li, Yao Shi, Yuyu Luo +1

Large Language Models (LLMs) have demonstrated impressive capabilities across various domains, but their effectiveness in financial decision-making remains inadequately evaluated.…

cond-mat.mtrl-sci2021

Magnetism in Metastable and Annealed Compositionally Complex Alloys

Nan Tang, Lizabeth Quigley, Walker L. Boldman +6

Compositionally complex materials (CCMs) present a potential paradigm shift in the design of magnetic materials. These alloys exhibit long-range structural order coupled with limit…

cs.DB2024

HAIChart: Human and AI Paired Visualization System

Yupeng Xie, Yuyu Luo, Guoliang Li +1

The growing importance of data visualization in business intelligence and data science emphasizes the need for tools that can efficiently generate meaningful visualizations from la…

cs.CL2025

AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent Framework

Meihao Fan, Ju Fan, Nan Tang +3

Answering natural language (NL) questions about tables, known as Tabular Question Answering (TQA), is crucial because it allows users to quickly and efficiently extract meaningful…

cond-mat.mtrl-sci2021

Controlling magnetic configuration in soft-hard bilayers probed by polarized neutron reflectometry

Nan Tang, Jung-Wei Liao, Siu-Tat Chui +4

Hard/soft magnetic bilayer thin films have been widely used in data storage technologies and permanent magnet applications. The magnetic configuration and response to temperatures…

cond-mat.mtrl-sci2023

Skyrmion-Excited Spin Wave Fractal Network

Nan Tang, W. L. N. C. Liyanage, Sergio A. Montoya +9

Magnetic skyrmions exhibit unique, technologically relevant pseudo-particle behaviors which arise from their topological protection, including well-defined, three-dimensional dynam…

cs.CL2024

Review-Then-Refine: A Dynamic Framework for Multi-Hop Question Answering with Temporal Adaptability

Xiangsen Chen, Xuming Hu, Nan Tang

Retrieve-augmented generation (RAG) frameworks have emerged as a promising solution to multi-hop question answering(QA) tasks since it enables large language models (LLMs) to incor…

cs.CL2022

PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-training

Zihui Gu, Ju Fan, Nan Tang +3

Fact verification has attracted a lot of research attention recently, e.g., in journalism, marketing, and policymaking, as misinformation and disinformation online can sway one's o…

cs.LG2026

A Risk Decomposition Framework for Pre-Hoc Fine-Tuning Prediction

Yuxiang Luo, Chen Wang, Nan Tang

The high cost of fine-tuning LLMs poses a significant economic barrier; pre-hoc performance prediction offers a critical solution to substantially reduce this expense. However, the…

cs.DB2015

On Summarizing Graph Streams

Nan Tang, Qing Chen, Prasenjit Mitra

Graph streams, which refer to the graph with edges being updated sequentially in a form of a stream, have wide applications such as cyber security, social networks and transportati…

cs.DB2023

ChatPipe: Orchestrating Data Preparation Program by Optimizing Human-ChatGPT Interactions

Sibei Chen, Hanbing Liu, Weiting Jin +5

Orchestrating a high-quality data preparation program is essential for successful machine learning (ML), but it is known to be time and effort consuming. Despite the impressive cap…

cs.DB2025

A Unified Model for Cardinality Estimation by Learning from Data and Queries via Sum-Product Networks

Jiawei Liu, Ju Fan, Tongyu Liu +5

Cardinality estimation is a fundamental component in database systems, crucial for generating efficient execution plans. Despite advancements in learning-based cardinality estimati…

cs.LG2025

LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning

Xiaotian Lin, Yanlin Qi, Yizhang Zhu +4

Instruction tuning has emerged as a critical paradigm for improving the capabilities and alignment of large language models (LLMs). However, existing iterative model-aware data sel…

cs.CL2024

BWArea Model: Learning World Model, Inverse Dynamics, and Policy for Controllable Language Generation

Chengxing Jia, Pengyuan Wang, Ziniu Li +4

Large language models (LLMs) have catalyzed a paradigm shift in natural language processing, yet their limited controllability poses a significant challenge for downstream applicat…

cs.LG2021

RPT: Relational Pre-trained Transformer Is Almost All You Need towards Democratizing Data Preparation

Nan Tang, Ju Fan, Fangyi Li +5

Can AI help automate human-easy but computer-hard data preparation tasks that burden data scientists, practitioners, and crowd workers? We answer this question by presenting RPT, a…

cs.CL2025

SRAG: Structured Retrieval-Augmented Generation for Multi-Entity Question Answering over Wikipedia Graph

Teng Lin, Yizhang Zhu, Yuyu Luo +1

Multi-entity question answering (MEQA) poses significant challenges for large language models (LLMs), which often struggle to consolidate scattered information across multiple docu…

cs.CL2025

InteractComp: Evaluating Search Agents With Ambiguous Queries

Mingyi Deng, Lijun Huang, Yani Fan +23

Language agents have demonstrated remarkable potential in web search and information retrieval. However, many search-agent benchmarks assume that user queries are complete and unam…

cs.DB2025

EllieSQL: Cost-Efficient Text-to-SQL with Complexity-Aware Routing

Yizhang Zhu, Runzhi Jiang, Boyan Li +2

Text-to-SQL automatically translates natural language queries to SQL, allowing non-technical users to retrieve data from databases without specialized SQL knowledge. Despite the su…

cs.CL2024

Empowering Language Models with Active Inquiry for Deeper Understanding

Jing-Cheng Pang, Heng-Bo Fan, Pengyuan Wang +6

The rise of large language models (LLMs) has revolutionized the way that we interact with artificial intelligence systems through natural language. However, LLMs often misinterpret…

cs.DB2018

Reuse and Adaptation for Entity Resolution through Transfer Learning

Saravanan Thirumuruganathan, Shameem A Puthiya Parambath, Mourad Ouzzani +2

Entity resolution (ER) is one of the fundamental problems in data integration, where machine learning (ML) based classifiers often provide the state-of-the-art results. Considerabl…

cs.DB2026

Data Agents: Levels, State of the Art, and Open Problems

Yuyu Luo, Guoliang Li, Ju Fan +1

Data agents are an emerging paradigm that leverages large language models (LLMs) and tool-using agents to automate data management, preparation, and analysis tasks. However, the te…

cs.CE2025

Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking

Changlun Li, Yao Shi, Chen Wang +7

Large Language Models (LLMs) have demonstrated notable capabilities across financial tasks, including financial report summarization, earnings call transcript analysis, and asset c…

cs.DB2024

SEED: Domain-Specific Data Curation With Large Language Models

Zui Chen, Lei Cao, Sam Madden +7

Data curation tasks that prepare data for analytics are critical for turning data into actionable insights. However, due to the diverse requirements of applications in different do…

cs.IR2026

Structural and Disentangled Adaptation of Large Vision Language Models for Multimodal Recommendation

Zhongtao Rao, Peilin Zhou, Dading Chong +3

Multimodal recommendation enhances accuracy by leveraging visual and textual signals, and its success largely depends on learning high-quality cross-modal representations. Recent a…

cs.DB2018

Unsupervised String Transformation Learning for Entity Consolidation

Dong Deng, Wenbo Tao, Ziawasch Abedjan +7

Data integration has been a long-standing challenge in data management with many applications. A key step in data integration is entity consolidation. It takes a collection of clus…

cs.AI2026

CSTrader: A Testbed for Language-Grounded Trading in a Community-Driven Virtual Asset Market

Yao Shi, Kingfung Luo, Nan Tang +1

Niche asset markets, such as Counter-Strike 2 (CS2) weapon skins, are small, volatile, and heavily driven by community discussions and platform rules. These properties make them ha…

cond-mat.mes-hall2019

Realization of Ordered Magnetic Skyrmions in Thin Films at Ambient Conditions

Ryan D. Desautels, Lisa DeBeer-Schmitt, Sergio Montoya +7

Magnetic skyrmions present interesting physics due to their topological nature and hold significant promise for future information technologies. A key barrier to realizing skyrmion…

cs.SI2019

Efficient Algorithms for Approximate Single-Source Personalized PageRank Queries

Sibo Wang, Renchi Yang, Runhui Wang +5

Given a graph , a source node and a target node , the personalized PageRank (PPR) of with respect to is the probability that a random walk starting from termi…

cs.CL2024

ChartInsights: Evaluating Multimodal Large Language Models for Low-Level Chart Question Answering

Yifan Wu, Lutao Yan, Leixian Shen +3

Chart question answering (ChartQA) tasks play a critical role in interpreting and extracting insights from visualization charts. While recent advancements in multimodal large langu…

cs.AI2025

Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting

Yifan Wu, Jingze Shi, Bingheng Wu +4

Existing chain-of-thought (CoT) distillation methods can effectively transfer reasoning abilities to base models but suffer from two major limitations: excessive verbosity of reaso…

cs.CV2024

AskChart: Universal Chart Understanding through Textual Enhancement

Xudong Yang, Yifan Wu, Yizhang Zhu +2

Chart understanding tasks such as ChartQA and Chart-to-Text involve automatically extracting and interpreting key information from charts, enabling users to query or convert visual…

cs.CL2026

LakeHopper: Cross Data Lakes Column Type Annotation through Model Adaptation

Yushi Sun, Xujia Li, Nan Tang +3

Column type annotation is vital for tasks like data cleaning, integration, and visualization. Recent solutions rely on resource-intensive language models fine-tuned on well-annotat…

cs.SI2025

Rise of the Community Champions: From Reviewer Crunch to Community Power

Changlun Li, Yao Shi, Yuyu Luo +1

Academic publishing is facing a crisis driven by exponential growth in submissions and an overwhelmed peer review system, leading to inconsistent decisions and a severe reviewer sh…

cs.DB2024

The Dawn of Natural Language to SQL: Are We Fully Ready?

Boyan Li, Yuyu Luo, Chengliang Chai +2

Translating users' natural language questions into SQL queries (i.e., NL2SQL) significantly lowers the barriers to accessing relational databases. The emergence of Large Language M…

cs.CL2024

Are Large Language Models a Good Replacement of Taxonomies?

Yushi Sun, Hao Xin, Kai Sun +5

Large language models (LLMs) demonstrate an impressive ability to internalize knowledge and answer natural language questions. Although previous studies validate that LLMs perform…

cs.DB2025

A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?

Xinyu Liu, Shuyu Shen, Boyan Li +7

Translating users' natural language queries (NL) into SQL queries (i.e., Text-to-SQL, a.k.a. NL2SQL) can significantly reduce barriers to accessing relational databases and support…

cs.DB2019

Technical Report: Optimizing Human Involvement for Entity Matching and Consolidation

Ji Sun, Dong Deng, Ihab Ilyas +5

An end-to-end data integration system requires human feedback in several phases, including collecting training data for entity matching, debugging the resulting clusters, confirmin…

cs.LG2024

Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts

Jing-Cheng Pang, Si-Hang Yang, Kaiyuan Li +4

Reinforcement learning (RL) trains agents to accomplish complex tasks through environmental interaction data, but its capacity is also limited by the scope of the available data. T…

cs.CL2025

KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering

Yushi Sun, Kai Sun, Yifan Ethan Xu +4

Retrieval-Augmented Generation (RAG) mitigates hallucination in Large Language Models (LLMs) by incorporating external data, with Knowledge Graphs (KGs) offering crucial informatio…

cs.DB2025

Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search

Boyan Li, Jiayi Zhang, Ju Fan +4

Text-to-SQL, which enables natural language interaction with databases, serves as a pivotal method across diverse industries. With new, more powerful large language models (LLMs) e…

cs.CL2023

Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generation

Zihui Gu, Ju Fan, Nan Tang +7

Zero-shot NL2SQL is crucial in achieving natural language to SQL that is adaptive to new environments (e.g., new databases, new linguistic phenomena or SQL structures) with zero an…

cs.CL2024

Are Large Language Models Good Statisticians?

Yizhang Zhu, Shiyin Du, Boyan Li +2

Large Language Models (LLMs) have demonstrated impressive capabilities across a range of scientific tasks including mathematics, physics, and chemistry. Despite their successes, th…

cond-mat.mes-hall2023

Three-Dimensional Structure of Hybrid Magnetic Skyrmions Determined by Neutron Scattering

WLNC Liyanage, Nan Tang, Lizabeth Quigley +9

Magnetic skyrmions are topologically protected chiral spin textures which present opportunities for next-generation magnetic data storage and logic information technologies. The to…

cs.AI2026

Text2GraphQuery-Bench: A Text to Graph Query Benchmark

Songlin Lyu, Lujie Ban, Zihang Wu +14

Graph models are fundamental to data analysis in domains rich with complex relationships. Unlike SQL, which benefits from a rel- atively unified standard and widespread familiarity…

cs.LG2026

TuneAhead: Predicting Fine-tuning Performance Before Full Training Begins

Yuxiang Luo, Haonan Long, Chen Wang +6

Fine-tuning large language models (LLMs) is compute-intensive and error-prone: model performance depends sensitively on data quality and hyperparameter choices, and naïve runs can…

cs.CV2025

RAMer: Reconstruction-based Adversarial Model for Multi-party Multi-modal Multi-label Emotion Recognition

Xudong Yang, Yizhang Zhu, Hanfeng Liu +3

Conventional Multi-modal multi-label emotion recognition (MMER) assumes complete access to visual, textual, and acoustic modalities. However, real-world multi-party settings often…

cs.CL2025

TransXSSM: A Hybrid Transformer State Space Model with Unified Rotary Position Embedding

Bingheng Wu, Jingze Shi, Yifan Wu +2

Transformers exhibit proficiency in capturing long-range dependencies, whereas State Space Models (SSMs) facilitate linear-time sequence modeling. Notwithstanding their synergistic…

cs.AI2026

Can Agentic Trading Systems Pay for Their Own Intelligence?

Qiqi Duan, Changlun Li, Chen Wang +10

Large language model (LLM) agents are increasingly used in trading systems, where model reasoning, tool use, and continual decisions incur costs that are expected to produce tradin…

cs.CL2025

MEBench: Benchmarking Large Language Models for Cross-Document Multi-Entity Question Answering

Teng Lin, Yuyu Luo, Honglin Zhang +4

Multi-entity question answering (MEQA) represents significant challenges for large language models (LLM) and retrieval-augmented generation (RAG) systems, which frequently struggle…

cs.AI2026

EVOQUANT: Self-Evolving Verifier-Guided Strategy Optimization for Robust Quantitative Trading

Jie Mao, Changlun Li, Xiang Li +7

EVOQUANT is a framework that uses large language models together with a verifier pipeline to automatically diagnose, edit, and improve quantitative trading strategies, achieving hi…

#quantitative trading#strategy optimization#large language models#verifier-guided editing
cs.DB2025

NL2SQL-BUGs: A Benchmark for Detecting Semantic Errors in NL2SQL Translation

Xinyu Liu, Shuyu Shen, Boyan Li +2

Natural Language to SQL (i.e., NL2SQL) translation is crucial for democratizing database access, but even state-of-the-art models frequently generate semantically incorrect SQL que…

cs.CL2024

CRAG -- Comprehensive RAG Benchmark

Xiao Yang, Kai Sun, Hao Xin +24

Retrieval-Augmented Generation (RAG) has recently emerged as a promising solution to alleviate Large Language Model (LLM)'s deficiency in lack of knowledge. Existing RAG datasets,…

cond-mat.str-el2026

Electrical observation via spin Seebeck effect of fractionalized excitations in a magnetic insulator

Nan Tang, Josef Willsher, Stephan Glamsch +9

Fractionalized excitations are among the most striking signatures of emergence in quantum matter. While widely sought in frustrated magnets, their detection and characterization re…

cs.IR2025

EXCLAIM: An Explainable Cross-Modal Agentic System for Misinformation Detection with Hierarchical Retrieval

Yin Wu, Zhengxuan Zhang, Fuling Wang +3

Misinformation continues to pose a significant challenge in today's information ecosystem, profoundly shaping public perception and behavior. Among its various manifestations, Out-…

cs.DB2019

DeepER -- Deep Entity Resolution

Muhammad Ebraheem, Saravanan Thirumuruganathan, Shafiq Joty +2

Entity resolution (ER) is a key data integration problem. Despite the efforts in 70+ years in all aspects of ER, there is still a high demand for democratizing ER - humans are heav…

cs.AI2026

DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces

Boyan Li, Zhuowen Liang, Yupeng Xie +11

Data agents enable natural-language analytics over organizational workspaces, where relevant evidence may be scattered across databases, structured files, long documents, and multi…

cs.CL2026

nvBench 2.0: Resolving Ambiguity in Text-to-Visualization through Stepwise Reasoning

Tianqi Luo, Chuhan Huang, Leixian Shen +5

Text-to-Visualization (Text2VIS) enables users to create visualizations from natural language queries, making data insights more accessible. However, Text2VIS faces challenges in i…

cs.DB2026

A Survey of Data Agents: Emerging Paradigm or Overstated Hype?

Yizhang Zhu, Liangwei Wang, Chenyu Yang +22

The rapid advancement of large language models (LLMs) has spurred the emergence of data agents, autonomous systems designed to orchestrate Data + AI ecosystems for tackling complex…

cs.DB2025

Automatic Database Configuration Debugging using Retrieval-Augmented Language Models

Sibei Chen, Ju Fan, Bin Wu +8

Database management system (DBMS) configuration debugging, e.g., diagnosing poorly configured DBMS knobs and generating troubleshooting recommendations, is crucial in optimizing DB…

cs.DB2024

A Plug-and-Play Natural Language Rewriter for Natural Language to SQL

Peixian Ma, Boyan Li, Runzhi Jiang +3

Existing Natural Language to SQL (NL2SQL) solutions have made significant advancements, yet challenges persist in interpreting and translating NL queries, primarily due to users' l…

cond-mat.str-el2024

Tensile and compressive strain tuning of a Kondo lattice

Soumendra Nath Panja, Anton Jesche, Nan Tang +1

We present electrical resistivity measurements on the prototypical heavy-fermion metal YbRhSi (YRS) under -axis tensile and compressive strain and focus on the evolu…

cs.DB2026

DTBench: A Synthetic Benchmark for Document-to-Table Extraction

Yuxiang Guo, Zhuoran Du, Nan Tang +3

Document-to-table (Doc2Table) extraction derives structured tables from unstructured documents under a target schema, enabling reliable and verifiable SQL-based data analytics. Alt…

cs.HC2025

ChartEditor: A Human-AI Paired Tool for Authoring Pictorial Charts

Siyu Yan, Tiancheng Liu, Weikai Yang +2

Pictorial charts are favored for their memorability and visual appeal, offering a more engaging alternative to basic charts. However, their creation can be complex and time-consumi…

cs.AI2026

TABQAWORLD: Optimizing Multimodal Reasoning for Multi-Turn Table Question Answering

Tung Sum Thomas Kwok, Xinyu Wang, Xiaofeng Lin +7

Multimodal reasoning has emerged as a powerful framework for enhancing reasoning capabilities of reasoning models. While multi-turn table reasoning methods have improved reasoning…

cs.CL2026

Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs

Zhuowen Liang, Xiaotian Lin, Zhengxuan Zhang +3

Large language models (LLMs) are widely applied to data analytics over documents, yet direct reasoning over long, noisy documents remains brittle and error-prone. Hence, we study d…

cs.DB2019

Data Curation with Deep Learning [Vision]

Saravanan Thirumuruganathan, Nan Tang, Mourad Ouzzani +1

Data curation - the process of discovering, integrating, and cleaning data - is one of the oldest, hardest, yet inevitable data management problems. Despite decades of efforts from…

cs.LG2026

VLGOR: Visual-Language Knowledge Guided Offline Reinforcement Learning for Generalizable Agents

Pengsen Liu, Maosen Zeng, Nan Tang +4

Combining Large Language Models (LLMs) with Reinforcement Learning (RL) enables agents to interpret language instructions more effectively for task execution. However, LLMs typical…

cs.AI2026

Monte Carlo Tree Search for Table-to-Multimodal Report Generation

Teng Lin, Zhiyang Zhang, Yuyu Luo +1

Automatically generating professional multimodal reports comprising both textual analysis and visual charts from structured tabular data is a critical challenge in data intelligenc…

cond-mat.str-el2025

Crystal-field magnetostriction of the spin ice under ultrahigh magnetic fields

Nan Tang, Masaki Gen, Martin Rotter +9

We present a comprehensive study of the magnetoelastic properties of the Ising pyrochlore oxide HoTiO, known as spin ice, by means of high-field magnetostriction…

cs.IR2026

AnnoRetrieve: Efficient Structured Retrieval for Unstructured Document Analysis

Teng Lin, Yuyu Luo, Nan Tang

Unstructured documents dominate enterprise and web data, but their lack of explicit organization hinders precise information retrieval. Current mainstream retrieval methods, especi…

cs.DB2019

Dataset-On-Demand: Automatic View Search and Presentation for Data Discovery

Raul Castro Fernandez, Nan Tang, Mourad Ouzzani +2

Many data problems are solved when the right view of a combination of datasets is identified. Finding such a view is challenging because of the many tables spread across many datab…

cs.CL2023

Cost-Effective In-Context Learning for Entity Resolution: A Design Space Exploration

Meihao Fan, Xiaoyue Han, Ju Fan +4

Entity resolution (ER) is an important data integration task with a wide spectrum of applications. The state-of-the-art solutions on ER rely on pre-trained language models (PLMs),…

cs.IR2026

Decoding Ancient Oracle Bone Script via Generative Dictionary Retrieval

Yin Wu, Gangjian Zhang, Jiayu Chen +4

Understanding humanity's earliest writing systems is crucial for reconstructing civilization's origins, yet many ancient scripts remain undeciphered. Oracle Bone Script (OBS) from…

cs.PL2020

Deductive Optimization of Relational Data Storage

John K. Feser, Samuel Madden, Nan Tang +1

Optimizing the physical data storage and retrieval of data are two key database management problems. In this paper, we propose a language that can express a wide range of physical…

cs.CL2026

Beyond Tables: Doc2DB-Bench for Relationally Faithful Document-to-Database Construction

Zhuowen Liang, Zhengxuan Zhang, Jiayang Wang +2

Practical AI systems increasingly need to turn long, heterogeneous documents into queryable relational databases, not isolated spreadsheets. In domains such as finance, healthcare,…

cs.CL2025

DataPuzzle: Breaking Free from the Hallucinated Promise of LLMs in Data Analysis

Zhengxuan Zhang, Zhuowen Liang, Yin Wu +3

Large language models (LLMs) are increasingly applied to multi-modal data analysis -- not necessarily because they offer the most precise answers, but because they provide fluent,…

cs.DB2023

VerifAI: Verified Generative AI

Nan Tang, Chenyu Yang, Ju Fan +3

Generative AI has made significant strides, yet concerns about the accuracy and reliability of its outputs continue to grow. Such inaccuracies can have serious consequences such as…

cs.CV2025

Fine-Grained Knowledge Structuring and Retrieval for Visual Question Answering

Zhengxuan Zhang, Yin Wu, Yuyu Luo +1

Visual Question Answering (VQA) focuses on providing answers to natural language questions by utilizing information from images. Although cutting-edge multimodal large language mod…

cs.IR2026

Boosting Text-to-Chart Retrieval through Training with Synthesized Semantic Insights

Yifan Wu, Lutao Yan, Yizhang Zhu +6

Text-to-chart retrieval, enabling users to find relevant charts via natural language queries, has gained significant attention. However, evaluating models in real-world business in…

cond-mat.str-el2025

Quantum Griffiths phase in the kagome Kondo lattice CeRhPdSn

Nan Tang, Rajesh Tripathi, Yasuyuki Shimura +3

CeRhSn is a valence fluctuating heavy-fermion metal with a twisted Ce-kagome lattice, displaying zero-field quantum criticality, previously associated with geometrical frustration.…

cs.CR2026

CyberThreat-Eval: Can Large Language Models Automate Real-World Threat Research?

Xiangsen Chen, Xuan Feng, Shuo Chen +5

Analyzing Open Source Intelligence (OSINT) from large volumes of data is critical for drafting and publishing comprehensive CTI reports. This process usually follows a three-stage…

cs.CL2024

SketchFill: Sketch-Guided Code Generation for Imputing Derived Missing Values

Yunfan Zhang, Changlun Li, Yuyu Luo +1

Missing value is a critical issue in data science, significantly impacting the reliability of analyses and predictions. Missing value imputation (MVI) is a longstanding problem bec…

physics.bio-ph2022

Anti-microbial properties of a multi-component alloy

Anne F. Murray, Daniel Bryan, David A. Garfinkel +8

High traffic touch surfaces such as doorknobs, countertops, and handrails can be transmission points for the spread of pathogens, emphasizing the need to develop materials that act…