Optimization methods for personalizing large language models through retrieval augmentation
This paper studies retrieval-augmented approaches for personalizing large language
models (LLMs), which potentially have a substantial impact on various applications and …
models (LLMs), which potentially have a substantial impact on various applications and …
Multi-armed bandits for adjudicating documents in pooling-based evaluation of information retrieval systems
Abstract Evaluating Information Retrieval systems is crucial to making progress in search
technologies. Evaluation is often based on assembling reference collections consisting of …
technologies. Evaluation is often based on assembling reference collections consisting of …
An adaptive social network-aware collaborative filtering algorithm for improved rating prediction accuracy
When information from traditional recommender systems is augmented with information
about user relationships that social networks store, more successful recommendations can …
about user relationships that social networks store, more successful recommendations can …
Maximal fusion of facts on the web with credibility guarantee
The Web became the central medium for valuable sources of information fusion
applications. However, such user-generated resources are often plagued by inaccuracies …
applications. However, such user-generated resources are often plagued by inaccuracies …
Using score distributions to compare statistical significance tests for information retrieval evaluation
Statistical significance tests can provide evidence that the observed difference in
performance between 2 methods is not due to chance. In information retrieval (IR), some …
performance between 2 methods is not due to chance. In information retrieval (IR), some …
Reliable Information Retrieval Systems Performance Evaluation: A Review
With the progressive and availability of various search tools, interest in the evaluation of
information retrieval based on user perspective has grown tremendously among …
information retrieval based on user perspective has grown tremendously among …
Robustness of rank aggregation methods for malicious disturbance
Rank aggregation has widespread applications in social choice, information retrieval, and
bioinformatics. Given the enormous social and economic implications of these applications …
bioinformatics. Given the enormous social and economic implications of these applications …
Beyond kemeny rank aggregation: A parameterizable-penalty framework for robust ranking aggregation with ties
Rank Aggregation has ubiquitous applications in operations research, artificial intelligence,
computational social choice, and various other fields. Interest in this problem has increased …
computational social choice, and various other fields. Interest in this problem has increased …
An axiomatic distance methodology for aggregating multimodal evaluations
This work introduces a multimodal data aggregation methodology featuring optimization
models and algorithms for jointly aggregating heterogeneous ordinal and cardinal …
models and algorithms for jointly aggregating heterogeneous ordinal and cardinal …
Enriched Construction Regulation Inquiry Responses: A Hybrid Search Approach for Large Language Models
The applicability of existing automated compliance check tools in construction is limited, as
they are insufficient to provide end-to-end responses given the fragmented and unstructured …
they are insufficient to provide end-to-end responses given the fragmented and unstructured …