2 citations · 6 across the 14 of their papers we have counts for
17 papers
CRAFT: An Agentic Spreadsheet Form Filling System with Template Awareness
Leyao Gu, Yingjie Xiong, Zirui Tang +5
Spreadsheet form filling requires agents to consolidate external evidence, ground values to precise cells, and preserve irregular template structure. Errors in early edits can over…
Suppressing Pressure, Amplifying Evidence: Self-Guided Attention Steering to Mitigate Sycophancy and Stubbornness
Yinghao He, Mengyu Xu, Haixiang Sun +8
Reliable language models should resist unsupported user pressure while effectively using objective contextual information. However, models may exhibit sycophancy by yielding to uns…
Guarded Commits: Transactional Human Approvals for LLM Workflows
Laurent Bindschaedler, Ferdi Kossmann, Chunwei Liu +1
LLM workflows often require human approval before an irreversible external action. Most systems keep that approval outside the workflow, as an interface click or an audit entry. Th…
SemJoin: Semantic Join Optimization
Christopher Gou, Aditya Banerjee, Jiaxuan Wang +1
Integrating unstructured data into relational database systems is increasingly important as demand grows for natural language querying and analysis. A semantic join, joining two ta…
TabClean: Reusable LLM-Synthesized Programs for Tabular Data Cleaning
Yibo Wang, Riteng Zhang, Yinghao He +3
Reliable analytics and machine-learning pipelines depend on clean tabular data, yet production tables often contain missing values, typographical errors, inconsistent formats, viol…
The Table Says Otherwise: Testing LLMs with Counterfactual Relational Data
Xinzhi Wang, Chunwei Liu
Large language models (LLMs) are increasingly used to answer natural-language questions over structured data. However, when a table contains familiar real-world facts, it is unclea…
Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies
Zirui Tang, Xuanhe Zhou, Yumou Liu +19
Workspace learning requires AI agents to identify, reason over, exploit, and update explicit and implicit dependencies among heterogeneous files in a worker's workspace, enabling t…
SAGE: Selective Attention-Guided Extraction for Token-Efficient Document Indexing
Xinzhi Wang, Peter Baile Chen, Gerardo Vitagliano +5
Large language models with long context windows can answer complex questions directly from full-length academic, technical, and policy documents, but passing entire documents is of…
iPDB -- Optimizing Semantic SQL Queries
Udesh Kumarasinghe, Tyler Liu, Ahmed R. Mahmood +2
Structured Query Language (SQL) has remained the standard query language for databases. SQL is highly optimized for processing structured data laid out in relations. Meanwhile, in…
LLM/Agent-as-Data-Analyst: A Survey
Zirui Tang, Weizheng Wang, Zihang Zhou +16
Large language models (LLMs) and agent techniques have brought a fundamental shift in the functionality and development paradigm of data analysis tasks (a.k.a LLM/Agent-as-Data-Ana…
PBench: Workload Synthesizer with Real Statistics for Cloud Analytics Benchmarking
Yan Zhou, Chunwei Liu, Bhuvan Urgaonkar +11
Cloud service providers commonly use standard benchmarks like TPC-H and TPC-DS to evaluate and optimize cloud data analytics systems. However, these benchmarks rely on fixed query…
Abacus: A Cost-Based Optimizer for Semantic Operator Systems
Matthew Russo, Chunwei Liu, Sivaprasad Sudhir +4
LLMs enable an exciting new class of data processing applications over large collections of unstructured documents. Several new programming frameworks have enabled developers to bu…
PalimpChat: Declarative and Interactive AI analytics
Chunwei Liu, Gerardo Vitagliano, Brandon Rose +3
Thanks to the advances in generative architectures and large language models, data scientists can now code pipelines of machine-learning operations to process large collections of…
Improving DBMS Scheduling Decisions with Fine-grained Performance Prediction on Concurrent Queries -- Extended
Ziniu Wu, Markos Markakis, Chunwei Liu +4
Query scheduling is a critical task that directly impacts query performance in database management systems (DBMS). Deeply integrated schedulers, which require changes to DBMS inter…
Variable Extraction for Model Recovery in Scientific Literature
Chunwei Liu, Enrique Noriega-Atala, Adarsh Pyarelal +2
The global output of academic publications exceeds 5 million articles per year, making it difficult for humans to keep up with even a tiny fraction of scientific output. We need me…
Don't Stop Me Now: Embedding Based Scheduling for LLMs
Rana Shahout, Eran Malach, Chunwei Liu +3
Efficient scheduling is crucial for interactive Large Language Model (LLM) applications, where low request completion time directly impacts user engagement. Size-based scheduling a…
MDCR: A Dataset for Multi-Document Conditional Reasoning
Peter Baile Chen, Yi Zhang, Chunwei Liu +3
The same real-life questions posed to different individuals may lead to different answers based on their unique situations. For instance, whether a student is eligible for a schola…