# Semantic Reformulation Entropy for Robust Hallucination Detection in QA Tasks

arXiv: https://arxiv.org/abs/2509.17445 · HTML: https://mlsanity.com/paper/2509.17445/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 20 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Builds on (most cited first, 19 of 19)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs](https://mlsanity.com/paper/2406.15927/) (2024)
- [On Wasserstein Two Sample Testing and Related Families of Nonparametric Tests](https://mlsanity.com/paper/1509.02237/) (2015)
- [Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering](https://mlsanity.com/paper/2307.16877/) (2023)
- [A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation](https://mlsanity.com/paper/2104.08704/) (2021)
- [To Believe or Not to Believe Your LLM](https://mlsanity.com/paper/2406.02543/) (2024)
- [Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus](https://mlsanity.com/paper/2311.13230/) (2023)
- [Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunities](https://mlsanity.com/paper/2405.10825/) (2024)
- [VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation](https://mlsanity.com/paper/2411.11919/) (2024)
- [Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family](https://mlsanity.com/paper/2303.07992/) (2023)
- [Improving Uncertainty Quantification in Large Language Models via Semantic Embeddings](https://mlsanity.com/paper/2410.22685/) (2024)
- [Semantic Energy: Detecting LLM Hallucination Beyond Entropy](https://mlsanity.com/paper/2508.14496/) (2025)
- [Semantic Sensitivities and Inconsistent Predictions: Measuring the Fragility of NLI Models](https://mlsanity.com/paper/2401.14440/) (2024)

## Built on by (most cited first, 4 of 4)

- [FaithSCAN: Model-Driven Single-Pass Hallucination Detection for Faithful Visual Question Answering](https://mlsanity.com/paper/2601.00269/) (2026)
- [Lowest Span Confidence: Zero-Shot Hallucination Detection from a Single LLM Response](https://mlsanity.com/paper/2601.19918/) (2026)
- [Knowledge Dependency Estimation for Reliable Question Answering](https://mlsanity.com/paper/2605.28047/) (2026)
- [Diversity-Oriented Fine-Tuning for Uncertainty-Based Hallucination Detection](https://mlsanity.com/paper/2607.16643/) (2026)

## Abstract (arXiv)

Reliable question answering with large language models (LLMs) is challenged by hallucinations, fluent but factually incorrect outputs arising from epistemic uncertainty. Existing entropy-based semantic-level uncertainty estimation methods are limited by sampling noise and unstable clustering of variable-length answers. We propose Semantic Reformulation Entropy (SRE), which improves uncertainty estimation in two ways. First, input-side semantic reformulations produce faithful paraphrases, expand the estimation space, and reduce biases from superficial decoder tendencies. Second, progressive, energy-based hybrid clustering stabilizes semantic grouping. Experiments on SQuAD and TriviaQA show that SRE outperforms strong baselines, providing more robust and generalizable hallucination detection. These results demonstrate that combining input diversification with multi-signal clustering substantially enhances semantic-level uncertainty estimation.