Salvato in:
Dettagli Bibliografici
Autori principali: Bang, Geonwoo, Kim, Dongho, Min, Moohong
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2601.05267
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911362123300864
author Bang, Geonwoo
Kim, Dongho
Min, Moohong
author_facet Bang, Geonwoo
Kim, Dongho
Min, Moohong
contents Evaluating complex texts across domains requires converting user defined criteria into quantitative, explainable indicators, which is a persistent challenge in search and recommendation systems. Single prompt LLM evaluations suffer from complexity and latency issues, while criterion specific decomposition approaches rely on naive averaging or opaque black-box aggregation methods. We present an interpretable aggregation framework combining LLM scoring with the Analytic Hierarchy Process. Our method generates criterion specific scores via LLM as judge, measures discriminative power using Jensen Shannon distance, and derives statistically grounded weights through AHP pairwise comparison matrices. Experiments on Amazon review quality assessment and depression related text scoring demonstrate that our approach achieves high explainability and operational efficiency while maintaining comparable predictive power, making it suitable for real time latency sensitive web services.
format Preprint
id arxiv_https___arxiv_org_abs_2601_05267
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Transforming User Defined Criteria into Explainable Indicators with an Integrated LLM AHP System
Bang, Geonwoo
Kim, Dongho
Min, Moohong
Information Retrieval
Computation and Language
Machine Learning
Evaluating complex texts across domains requires converting user defined criteria into quantitative, explainable indicators, which is a persistent challenge in search and recommendation systems. Single prompt LLM evaluations suffer from complexity and latency issues, while criterion specific decomposition approaches rely on naive averaging or opaque black-box aggregation methods. We present an interpretable aggregation framework combining LLM scoring with the Analytic Hierarchy Process. Our method generates criterion specific scores via LLM as judge, measures discriminative power using Jensen Shannon distance, and derives statistically grounded weights through AHP pairwise comparison matrices. Experiments on Amazon review quality assessment and depression related text scoring demonstrate that our approach achieves high explainability and operational efficiency while maintaining comparable predictive power, making it suitable for real time latency sensitive web services.
title Transforming User Defined Criteria into Explainable Indicators with an Integrated LLM AHP System
topic Information Retrieval
Computation and Language
Machine Learning
url https://arxiv.org/abs/2601.05267