Peter Baile Chen
YOU?
Author Swipe
View article: EnrichIndex: Using LLMs to Enrich Retrieval Indices Offline
EnrichIndex: Using LLMs to Enrich Retrieval Indices Offline Open
Existing information retrieval systems excel in cases where the language of target documents closely matches that of the user query. However, real-world retrieval systems are often required to implicitly reason whether a document is releva…
View article: Can we Retrieve Everything All at Once? ARM: An Alignment-Oriented LLM-based Retrieval Method
Can we Retrieve Everything All at Once? ARM: An Alignment-Oriented LLM-based Retrieval Method Open
Real-world open-domain questions can be complicated, particularly when answering them involves information from multiple information sources. LLMs have demonstrated impressive performance in decomposing complex tasks into simpler steps, an…
View article: Improving DBMS Scheduling Decisions with Fine-grained Performance Prediction on Concurrent Queries -- Extended
Improving DBMS Scheduling Decisions with Fine-grained Performance Prediction on Concurrent Queries -- Extended Open
Query scheduling is a critical task that directly impacts query performance in database management systems (DBMS). Deeply integrated schedulers, which require changes to DBMS internals, are usually customized for a specific engine and can …
View article: BEAVER: An Enterprise Benchmark for Text-to-SQL
BEAVER: An Enterprise Benchmark for Text-to-SQL Open
Existing text-to-SQL benchmarks have largely been constructed from web tables with human-generated question-SQL pairs. LLMs typically show strong results on these benchmarks, leading to a belief that LLMs are effective at text-to-SQL tasks…
View article: MDCR: A Dataset for Multi-Document Conditional Reasoning
MDCR: A Dataset for Multi-Document Conditional Reasoning Open
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 scholarship depends on eligibility conditions, such as major or d…
View article: Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrieval
Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrieval Open
Retrieving relevant tables containing the necessary information to accurately answer a given question over tables is critical to open-domain question-answering (QA) systems. Previous methods assume the answer to such a question can be foun…
View article: Fault-tolerant and Transactional Stateful Serverless Workflows (extended version)
Fault-tolerant and Transactional Stateful Serverless Workflows (extended version) Open
This paper introduces Beldi, a library and runtime system for writing and composing fault-tolerant and transactional stateful serverless functions. Beldi runs on existing providers and lets developers write complex stateful applications th…