FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance [PDF]
There is a rapidly growing number of large language models (LLMs) that users can query for a fee. We review the cost associated with querying popular LLM APIs, e.g.
Lingjiao Chen, M. Zaharia, James Y. Zou
semanticscholar +1 more source
Dissecting Recall of Factual Associations in Auto-Regressive Language Models [PDF]
Transformer-based language models (LMs) are known to capture factual knowledge in their parameters. While previous work looked into where factual associations are stored, only little is known about how they are retrieved internally during inference.
Mor Geva+3 more
semanticscholar +1 more source
Code Generation for Efficient Query Processing in Managed Runtimes [PDF]
In this paper we examine opportunities arising from the conver-gence of two trends in data management: in-memory database sys-tems (IMDBs), which have received renewed attention following the availability of affordable, very large main memory systems ...
Bierman, Gavin M.+2 more
core +1 more source
RESEARCH ON EXTENSION OF SPARQL ONTOLOGY QUERY LANGUAGE CONSIDERING THE COMPUTATION OF INDOOR SPATIAL RELATIONS [PDF]
A method suitable for indoor complex semantic query considering the computation of indoor spatial relations is provided According to the characteristics of indoor space. This paper designs ontology model describing the space related information of humans,
C. Li, X. Zhu, W. Guo, Y. Liu, H. Huang
doaj +1 more source
Detecting Language Model Attacks with Perplexity [PDF]
A novel hack involving Large Language Models (LLMs) has emerged, leveraging adversarial suffixes to trick models into generating perilous responses. This method has garnered considerable attention from reputable media outlets such as the New York Times ...
Gabriel Alon, Michael Kamfonas
semanticscholar +1 more source
Query recovery of short user queries: on query expansion with stopwords [PDF]
User queries to search engines are observed to predominantly contain inflected content words but lack stopwords and capitalization. Thus, they often resemble natural language queries after case folding and stopword removal.
Jones, Gareth J.F., Leveling, Johannes
core +2 more sources
An Approach of Automatic SPARQL Generation for BIM Data Extraction
Generally, building information modelling (BIM) models contain multiple dimensions of building information, including building design data, construction information, and maintenance-related contents, which are related with different engineering ...
Dongming Guo+2 more
doaj +1 more source
Semantic Protocol and Resource Description Framework Query Language: A Comprehensive Review
This review presents various perspectives on converting user keywords into a formal query. Without understanding the dataset’s underlying structure, how can a user input a text-based query and then convert this text into semantic protocol and resource ...
Essam H. Houssein+3 more
doaj +1 more source
Proposal-free Temporal Moment Localization of a Natural-Language Query in Video using Guided Attention [PDF]
This paper studies the problem of temporal moment localization in a long untrimmed video using natural language as the query. Given an untrimmed video and a query sentence, the goal is to determine the start and end of the relevant visual moment in the ...
Cristian Rodriguez-Opazo+4 more
semanticscholar +1 more source
Pathfinder: XQuery - The Relational Way [PDF]
Relational query processors are probably the best understood (as well as the best engineered) query engines available today. Although carefully tuned to process instances of the relational model (tables of tuples), these processors can also provide a ...
Boncz, Peter+5 more
core +5 more sources