Enregistré dans:
Détails bibliographiques
Auteurs principaux: Shin, Hagyeong, Dalal, Binoy Robin, Bialynicka-Birula, Iwona, Matharu, Navjot, Muir, Ryan, Yang, Xingwei, Wong, Samuel W. K.
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2508.00889
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908476554346496
author Shin, Hagyeong
Dalal, Binoy Robin
Bialynicka-Birula, Iwona
Matharu, Navjot
Muir, Ryan
Yang, Xingwei
Wong, Samuel W. K.
author_facet Shin, Hagyeong
Dalal, Binoy Robin
Bialynicka-Birula, Iwona
Matharu, Navjot
Muir, Ryan
Yang, Xingwei
Wong, Samuel W. K.
contents Large language models (LLMs) are known to hallucinate, producing natural language outputs that are not grounded in the input, reference materials, or real-world knowledge. In enterprise applications where AI features support business decisions, such hallucinations can be particularly detrimental. LLMs that analyze and summarize contact center conversations introduce a unique set of challenges for factuality evaluation, because ground-truth labels often do not exist for analytical interpretations about sentiments captured in the conversation and root causes of the business problems. To remedy this, we first introduce a \textbf{3D} -- \textbf{Decompose, Decouple, Detach} -- paradigm in the human annotation guideline and the LLM-judges' prompt to ground the factuality labels in linguistically-informed evaluation criteria. We then introduce \textbf{FECT}, a novel benchmark dataset for \textbf{F}actuality \textbf{E}valuation of Interpretive AI-Generated \textbf{C}laims in Contact Center Conversation \textbf{T}ranscripts, labeled under our 3D paradigm. Lastly, we report our findings from aligning LLM-judges on the 3D paradigm. Overall, our findings contribute a new approach for automatically evaluating the factuality of outputs generated by an AI system for analyzing contact center conversations.
format Preprint
id arxiv_https___arxiv_org_abs_2508_00889
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FECT: Factuality Evaluation of Interpretive AI-Generated Claims in Contact Center Conversation Transcripts
Shin, Hagyeong
Dalal, Binoy Robin
Bialynicka-Birula, Iwona
Matharu, Navjot
Muir, Ryan
Yang, Xingwei
Wong, Samuel W. K.
Computation and Language
Artificial Intelligence
Machine Learning
Large language models (LLMs) are known to hallucinate, producing natural language outputs that are not grounded in the input, reference materials, or real-world knowledge. In enterprise applications where AI features support business decisions, such hallucinations can be particularly detrimental. LLMs that analyze and summarize contact center conversations introduce a unique set of challenges for factuality evaluation, because ground-truth labels often do not exist for analytical interpretations about sentiments captured in the conversation and root causes of the business problems. To remedy this, we first introduce a \textbf{3D} -- \textbf{Decompose, Decouple, Detach} -- paradigm in the human annotation guideline and the LLM-judges' prompt to ground the factuality labels in linguistically-informed evaluation criteria. We then introduce \textbf{FECT}, a novel benchmark dataset for \textbf{F}actuality \textbf{E}valuation of Interpretive AI-Generated \textbf{C}laims in Contact Center Conversation \textbf{T}ranscripts, labeled under our 3D paradigm. Lastly, we report our findings from aligning LLM-judges on the 3D paradigm. Overall, our findings contribute a new approach for automatically evaluating the factuality of outputs generated by an AI system for analyzing contact center conversations.
title FECT: Factuality Evaluation of Interpretive AI-Generated Claims in Contact Center Conversation Transcripts
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2508.00889