7 citations · 31 across the 11 of their papers we have counts for
12 papers
RUBEN: Rule-Based Explanations for Retrieval-Augmented LLM Systems
Joel Rorseth, Parke Godfrey, Lukasz Golab +2
This paper demonstrates RUBEN, an interactive tool for discovering minimal rules to explain the outputs of retrieval-augmented large language models (LLMs) in data-driven applicati…
Rule-Based Explanations for Retrieval-Augmented LLM Systems
Joel Rorseth, Parke Godfrey, Lukasz Golab +2
If-then rules are widely used to explain machine learning models; e.g., "if employed = no, then loan application = rejected." We present the first proposal to apply rules to explai…
Explaining Expert Search and Team Formation Systems with ExES
Kiarash Golzadeh, Lukasz Golab, Jaroslaw Szlichta
Expert search and team formation systems operate on collaboration networks, with nodes representing individuals, labeled with their skills, and edges denoting collaboration relatio…
RAGE Against the Machine: Retrieval-Augmented LLM Explanations
Joel Rorseth, Parke Godfrey, Lukasz Golab +2
This paper demonstrates RAGE, an interactive tool for explaining Large Language Models (LLMs) augmented with retrieval capabilities; i.e., able to query external sources and pull r…
CREDENCE: Counterfactual Explanations for Document Ranking
Joel Rorseth, Parke Godfrey, Lukasz Golab +3
Towards better explainability in the field of information retrieval, we present CREDENCE, an interactive tool capable of generating counterfactual explanations for document rankers…
Discovery and Contextual Data Cleaning with Ontology Functional Dependencies
Zheng Zheng, Longtao Zheng, Morteza Alipour Langouri +3
Functional Dependencies (FDs) define attribute relationships based on syntactic equality, and, when usedin data cleaning, they erroneously label syntactically different but semanti…
Efficient Discovery of Approximate Order Dependencies
Reza Karegar, Parke Godfrey, Lukasz Golab +3
Order dependencies (ODs) capture relationships between ordered domains of attributes. Approximate ODs (AODs) capture such relationships even when there exist exceptions in the data…
Discovering Domain Orders through Order Dependencies
Reza Karegar, Melicaalsadat Mirsafian, Parke Godfrey +4
Much real-world data come with explicitly defined domain orders; e.g., lexicographic order for strings, numeric for integers, and chronological for time. Our goal is to discover im…
Errata Note: Discovering Order Dependencies through Order Compatibility
Parke Godfrey, Lukasz Golab, Mehdi Kargar +2
A number of extensions to the classical notion of functional dependencies have been proposed to express and enforce application semantics. One of these extensions is that of order…
Authority-based Team Discovery in Social Networks
Morteza Zihayat, Aijun An, Lukasz Golab +2
Given a social network of experts, we address the problem of discovering a team of experts that collectively holds a set of skills required to complete a given project. Most prior…
Effective and Complete Discovery of Order Dependencies via Set-based Axiomatization
Jaroslaw Szlichta, Parke Godfrey, Lukasz Golab +2
Integrity constraints (ICs) provide a valuable tool for expressing and enforcing application semantics. However, formulating constraints manually requires domain expertise, is pron…
Effective Keyword Search in Graphs
Mehdi Kargar, Lukasz Golab, Jaroslaw Szlichta
In a node-labeled graph, keyword search finds subtrees of the graph whose nodes contain all of the query keywords. This provides a way to query graph databases that neither require…