Search Results for author:
Found 34 papers, 15 papers with code
DataMosaic: Explainable and Verifiable Multi-Modal Data Analytics through Extract-Reason-Verify
Large Language Models (LLMs) are transforming data analytics, but their widespread adoption is hindered by two critical limitations: they are not explainable (opaque reasoning processes) and not verifiable (prone to hallucinations and unchecked errors).
EllieSQL: Cost-Efficient Text-to-SQL with Complexity-Aware Routing
Text-to-SQL automatically translates natural language queries to SQL, allowing non-technical users to retrieve data from databases without specialized SQL knowledge.
DeepFund: Will LLM be Professional at Fund Investment? A Live Arena Perspective
Large Language Models (LLMs) have demonstrated impressive capabilities across various domains, but their effectiveness in financial decision making, particularly in fund investment, remains inadequately evaluated.
nvBench 2.0: A Benchmark for Natural Language to Visualization under Ambiguity
Natural Language to Visualization (NL2VIS) enables users to create visualizations from natural language queries, making data insights more accessible.
SRAG: Structured Retrieval-Augmented Generation for Multi-Entity Question Answering over Wikipedia Graph
The effectiveness of current retrieval-augmented generation (RAG) methods is limited by the LLMs' capacity to aggregate insights from numerous pages.
Fine-Grained Retrieval-Augmented Generation for Visual Question Answering
Visual Question Answering (VQA) focuses on providing answers to natural language questions by utilizing information from images.
RAMer: Reconstruction-based Adversarial Model for Multi-party Multi-modal Multi-label Emotion Recognition
Conventional multi-modal multi-label emotion recognition (MMER) from videos typically assumes full availability of visual, textual, and acoustic modalities.
SketchFill: Sketch-Guided Code Generation for Imputing Derived Missing Values
This gap underscores the need for further advancements in LLM methodologies to enhance their reasoning capabilities for more reliable imputation outcomes.
AskChart: Universal Chart Understanding through Textual Enhancement
To effectively train AskChart, we design a three-stage training strategy to align visual and textual modalities for learning robust visual-textual representations and optimizing the learning of the MoE layer.
Review-Then-Refine: A Dynamic Framework for Multi-Hop Question Answering with Temporal Adaptability
Despite this progress, existing RAG frameworks, which usually follows the retrieve-then-read paradigm, often struggle with multi-hop QA with temporal information since it has difficulty retrieving and synthesizing accurate time-related information.
AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent Framework
Many of these tables are derived from web sources or real-world scenarios, which require meticulous data preparation (or data prep) to ensure accurate responses.
A Survey of NL2SQL with Large Language Models: Where are we, and where are we going?
Translating users' natural language queries (NL) into SQL queries (i. e., NL2SQL, a. k. a., Text-to-SQL) can significantly reduce barriers to accessing relational databases and support various commercial applications.
Are Large Language Models a Good Replacement of Taxonomies?
Unfortunately, there lacks a comprehensive benchmark that evaluates the LLMs over a wide range of taxonomies from common to specialized domains and at levels from root to leaf so that we can draw a confident conclusion.
HAIChart: Human and AI Paired Visualization System
The growing importance of data visualization in business intelligence and data science emphasizes the need for tools that can efficiently generate meaningful visualizations from large datasets.
Are Large Language Models Good Statisticians?
Large Language Models (LLMs) have demonstrated impressive capabilities across a range of scientific tasks including mathematics, physics, and chemistry.
CRAG -- Comprehensive RAG Benchmark
To bridge this gap, we introduce the Comprehensive RAG Benchmark (CRAG), a factual question answering benchmark of 4, 409 question-answer pairs and mock APIs to simulate web and Knowledge Graph (KG) search.
BWArea Model: Learning World Model, Inverse Dynamics, and Policy for Controllable Language Generation
In a similar vein, our proposed system, the BWArea model, conceptualizes language generation as a decision-making task.
ChartInsights: Evaluating Multimodal Large Language Models for Low-Level Chart Question Answering
To further explore the limitations of MLLMs in low-level ChartQA, we conduct experiments that alter visual elements of charts (e. g., changing color schemes, adding image noise) to assess their impact on the task effectiveness.
Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts
Furthermore, KALM effectively enables the LLM to comprehend environmental dynamics, resulting in the generation of meaningful imaginary rollouts that reflect novel skills and demonstrate the seamless integration of large language models and reinforcement learning.
Empowering Language Models with Active Inquiry for Deeper Understanding
The rise of large language models (LLMs) has revolutionized the way that we interact with artificial intelligence systems through natural language.
Cost-Effective In-Context Learning for Entity Resolution: A Design Space Exploration
However, existing ICL approaches to ER typically necessitate providing a task description and a set of demonstrations for each entity pair and thus have limitations on the monetary cost of interfacing LLMs.
SEED: Domain-Specific Data Curation With Large Language Models
As a result, data scientists often have to develop domain-specific solutions tailored to both the dataset and the task, e. g. writing domain-specific code or training machine learning models on a sufficient number of annotated examples.
VerifAI: Verified Generative AI
We propose that verifying the outputs of generative AI from a data management perspective is an emerging issue for generative AI.
Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generation
PLMs can perform well in schema alignment but struggle to achieve complex reasoning, while LLMs is superior in complex reasoning tasks but cannot achieve precise schema alignment.
Unicorn: A Unified Multi-tasking Model for Supporting Matching Tasks in Data Integration
The widely used practice is to build task-specific or even dataset-specific solutions, which are hard to generalize and disable the opportunities of knowledge sharing that can be learned from different datasets and multiple tasks.
ChatPipe: Orchestrating Data Preparation Program by Optimizing Human-ChatGPT Interactions
Orchestrating a high-quality data preparation program is essential for successful machine learning (ML), but it is known to be time and effort consuming.
RetClean: Retrieval-Based Data Cleaning Using Foundation Models and Data Lakes
To assist with this scenario, we developed a custom RoBERTa-based foundation model that can be locally deployed.
PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-training
In particular, on the complex set of TabFact, which contains multiple operations, PASTA largely outperforms the previous state of the art by 4. 7 points (85. 6% vs. 80. 9%), and the gap between PASTA and human performance on the small TabFact test set is narrowed to just 1. 5 points (90. 6% vs. 92. 1%).
Ranked #3 on
Table-based Fact Verification
on TabFact
Domain Adaptation for Deep Entity Resolution: A Design Space Exploration
Entity resolution (ER) is a core problem of data integration.
Ranked #2 on
Entity Resolution
on WDC Watches-small
Deep learning for blocking in entity matching: a design space exploration
In this paper, we develop the DeepBlocker framework that significantly advances the state of the art in applying DL to blocking for EM.
Ranked #5 on
Blocking
on Abt-Buy
Deductive Optimization of Relational Data Storage
Optimizing the physical data storage and retrieval of data are two key database management problems.
Programming Languages Databases
Reuse and Adaptation for Entity Resolution through Transfer Learning
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.
DeepER -- Deep Entity Resolution
word embeddings), we present a novel ER system, called DeepER, that achieves good accuracy, high efficiency, as well as ease-of-use (i. e., much less human efforts).
Databases
