# Span-Level Hallucination Detection for LLM-Generated Answers

arXiv: https://arxiv.org/abs/2504.18639 · HTML: https://mlsanity.com/paper/2504.18639/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 21 references that are in the map.
- First posted on arXiv 25 Apr 2025.

## Builds on (most cited first, 11 of 11)

- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning](https://mlsanity.com/paper/2306.14565/) (2023)
- [Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity](https://mlsanity.com/paper/2310.07521/) (2023)
- [Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification](https://mlsanity.com/paper/2403.04696/) (2024)
- [Simple BERT Models for Relation Extraction and Semantic Role Labeling](https://mlsanity.com/paper/1904.05255/) (2019)
- [A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation](https://mlsanity.com/paper/2104.08704/) (2021)
- [SciFact-Open: Towards open-domain scientific claim verification](https://mlsanity.com/paper/2210.13777/) (2022)
- [Detecting and Mitigating Hallucinations in Multilingual Summarisation](https://mlsanity.com/paper/2305.13632/) (2023)
- [Detecting Hallucinations in Large Language Model Generation: A Token Probability Approach](https://mlsanity.com/paper/2405.19648/) (2024)
- [The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders](https://mlsanity.com/paper/2109.06939/) (2021)
- [Hallucination Detection and Hallucination Mitigation: An Investigation](https://mlsanity.com/paper/2401.08358/) (2024)

## Built on by (most cited first, 5 of 5)

- [From RAG to Agentic RAG for Faithful Islamic Question Answering](https://mlsanity.com/paper/2601.07528/) (2026)
- [Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders](https://mlsanity.com/paper/2512.08892/) (2025)
- [HalluTruthQA: A Fine-Grained Benchmark for Hallucination Detection, Localization, and Explanation in Arabic Question Answering](https://mlsanity.com/paper/2607.20219/) (2026)
- [HalluTruthQA-4K: A Fine-Grained Corpus and Annotation Process for Arabic Hallucination Detection and Truth Verification](https://mlsanity.com/paper/2608.03966/) (2026)
- [Hallucination Span Detection with Input-Side Evidence Alignment](https://mlsanity.com/paper/2608.15804/) (2026)

## Abstract (arXiv)

Detecting spans of hallucination in LLM-generated answers is crucial for improving factual consistency. This paper presents a span-level hallucination detection framework for the SemEval-2025 Shared Task, focusing on English and Arabic texts. Our approach integrates Semantic Role Labeling (SRL) to decompose the answer into atomic roles, which are then compared with a retrieved reference context obtained via question-based LLM prompting. Using a DeBERTa-based textual entailment model, we evaluate each role semantic alignment with the retrieved context. The entailment scores are further refined through token-level confidence measures derived from output logits, and the combined scores are used to detect hallucinated spans. Experiments on the Mu-SHROOM dataset demonstrate competitive performance. Additionally, hallucinated spans have been verified through fact-checking by prompting GPT-4 and LLaMA. Our findings contribute to improving hallucination detection in LLM-generated responses.