HalluCounter: Reference-free LLM Hallucination Detection in the Wild!

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Urlana, Ashok, Kanumolu, Gopichand, Kumar, Charaka Vinayak, Garlapati, Bala Mallikarjunarao, Mishra, Rahul
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908381085696000
author Urlana, Ashok
Kanumolu, Gopichand
Kumar, Charaka Vinayak
Garlapati, Bala Mallikarjunarao
Mishra, Rahul
author_facet Urlana, Ashok
Kanumolu, Gopichand
Kumar, Charaka Vinayak
Garlapati, Bala Mallikarjunarao
Mishra, Rahul
contents Response consistency-based, reference-free hallucination detection (RFHD) methods do not depend on internal model states, such as generation probabilities or gradients, which Grey-box models typically rely on but are inaccessible in closed-source LLMs. However, their inability to capture query-response alignment patterns often results in lower detection accuracy. Additionally, the lack of large-scale benchmark datasets spanning diverse domains remains a challenge, as most existing datasets are limited in size and scope. To this end, we propose HalluCounter, a novel reference-free hallucination detection method that utilizes both response-response and query-response consistency and alignment patterns. This enables the training of a classifier that detects hallucinations and provides a confidence score and an optimal response for user queries. Furthermore, we introduce HalluCounterEval, a benchmark dataset comprising both synthetically generated and human-curated samples across multiple domains. Our method outperforms state-of-the-art approaches by a significant margin, achieving over 90\% average confidence in hallucination detection across datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2503_04615
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HalluCounter: Reference-free LLM Hallucination Detection in the Wild!
Urlana, Ashok
Kanumolu, Gopichand
Kumar, Charaka Vinayak
Garlapati, Bala Mallikarjunarao
Mishra, Rahul
Computation and Language
Response consistency-based, reference-free hallucination detection (RFHD) methods do not depend on internal model states, such as generation probabilities or gradients, which Grey-box models typically rely on but are inaccessible in closed-source LLMs. However, their inability to capture query-response alignment patterns often results in lower detection accuracy. Additionally, the lack of large-scale benchmark datasets spanning diverse domains remains a challenge, as most existing datasets are limited in size and scope. To this end, we propose HalluCounter, a novel reference-free hallucination detection method that utilizes both response-response and query-response consistency and alignment patterns. This enables the training of a classifier that detects hallucinations and provides a confidence score and an optimal response for user queries. Furthermore, we introduce HalluCounterEval, a benchmark dataset comprising both synthetically generated and human-curated samples across multiple domains. Our method outperforms state-of-the-art approaches by a significant margin, achieving over 90\% average confidence in hallucination detection across datasets.
title HalluCounter: Reference-free LLM Hallucination Detection in the Wild!
topic Computation and Language
url https://arxiv.org/abs/2503.04615