Saved in:
Bibliographic Details
Main Authors: Dang, Nhi, Le, Tung, Nguyen, Huy Tien
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.10570
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915853801357312
author Dang, Nhi
Le, Tung
Nguyen, Huy Tien
author_facet Dang, Nhi
Le, Tung
Nguyen, Huy Tien
contents Large language models (LLMs) combined with retrieval augmented generation have enabled the deployment of domain-specific chatbots, but these systems remain prone to generating unsupported or incorrect answers. Reliable evaluation is therefore critical, yet manual review is costly and existing frameworks often depend on curated test sets and static metrics, limiting scalability. We propose an end-to-end automatic evaluator designed to substantially reduce human effort. Our system generates Q\&A pairs directly from the underlying knowledge base, uses LLMs to judge chatbot responses against reference answers, and applies confidence-based filtering to highlight uncertain cases. Applied to a Vietnamese news dataset, the evaluator achieves high agreement with human judgments while significantly lowering review overhead. The framework is modular and language-agnostic, making it readily adaptable to diverse domains. This work introduces a practical, scalable solution for evaluating chatbots with minimal reliance on manual intervention.
format Preprint
id arxiv_https___arxiv_org_abs_2603_10570
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle End-to-End Chatbot Evaluation with Adaptive Reasoning and Uncertainty Filtering
Dang, Nhi
Le, Tung
Nguyen, Huy Tien
Computation and Language
Large language models (LLMs) combined with retrieval augmented generation have enabled the deployment of domain-specific chatbots, but these systems remain prone to generating unsupported or incorrect answers. Reliable evaluation is therefore critical, yet manual review is costly and existing frameworks often depend on curated test sets and static metrics, limiting scalability. We propose an end-to-end automatic evaluator designed to substantially reduce human effort. Our system generates Q\&A pairs directly from the underlying knowledge base, uses LLMs to judge chatbot responses against reference answers, and applies confidence-based filtering to highlight uncertain cases. Applied to a Vietnamese news dataset, the evaluator achieves high agreement with human judgments while significantly lowering review overhead. The framework is modular and language-agnostic, making it readily adaptable to diverse domains. This work introduces a practical, scalable solution for evaluating chatbots with minimal reliance on manual intervention.
title End-to-End Chatbot Evaluation with Adaptive Reasoning and Uncertainty Filtering
topic Computation and Language
url https://arxiv.org/abs/2603.10570