keepitsimple at SemEval-2025 Task 3: LLM-Uncertainty based Approach for Multilingual Hallucination Span Detection

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Vemula, Saketh Reddy, Krishnamurthy, Parameswari
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913855052972032
author Vemula, Saketh Reddy
Krishnamurthy, Parameswari
author_facet Vemula, Saketh Reddy
Krishnamurthy, Parameswari
contents Identification of hallucination spans in black-box language model generated text is essential for applications in the real world. A recent attempt at this direction is SemEval-2025 Task 3, Mu-SHROOM-a Multilingual Shared Task on Hallucinations and Related Observable Over-generation Errors. In this work, we present our solution to this problem, which capitalizes on the variability of stochastically-sampled responses in order to identify hallucinated spans. Our hypothesis is that if a language model is certain of a fact, its sampled responses will be uniform, while hallucinated facts will yield different and conflicting results. We measure this divergence through entropy-based analysis, allowing for accurate identification of hallucinated segments. Our method is not dependent on additional training and hence is cost-effective and adaptable. In addition, we conduct extensive hyperparameter tuning and perform error analysis, giving us crucial insights into model behavior.
format Preprint
id arxiv_https___arxiv_org_abs_2505_17485
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle keepitsimple at SemEval-2025 Task 3: LLM-Uncertainty based Approach for Multilingual Hallucination Span Detection
Vemula, Saketh Reddy
Krishnamurthy, Parameswari
Computation and Language
Artificial Intelligence
Identification of hallucination spans in black-box language model generated text is essential for applications in the real world. A recent attempt at this direction is SemEval-2025 Task 3, Mu-SHROOM-a Multilingual Shared Task on Hallucinations and Related Observable Over-generation Errors. In this work, we present our solution to this problem, which capitalizes on the variability of stochastically-sampled responses in order to identify hallucinated spans. Our hypothesis is that if a language model is certain of a fact, its sampled responses will be uniform, while hallucinated facts will yield different and conflicting results. We measure this divergence through entropy-based analysis, allowing for accurate identification of hallucinated segments. Our method is not dependent on additional training and hence is cost-effective and adaptable. In addition, we conduct extensive hyperparameter tuning and perform error analysis, giving us crucial insights into model behavior.
title keepitsimple at SemEval-2025 Task 3: LLM-Uncertainty based Approach for Multilingual Hallucination Span Detection
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2505.17485