# Enhancing Hallucination Detection through Perturbation-Based Synthetic Data Generation in System Responses

arXiv: https://arxiv.org/abs/2407.05474 · HTML: https://mlsanity.com/paper/2407.05474/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Self-improving MLLMs and synthetic data, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 17 of its 28 references that are in the map.
- First posted on arXiv 7 Jul 2024.

## Placed in

- Synthetic data and self-improvement for LLMs / [Self-improving MLLMs and synthetic data](https://mlsanity.com/synth/self-improving-mllms-and-synthetic-data/)

## Builds on (most cited first, 17 of 17)

- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization](https://mlsanity.com/paper/2111.09525/) (2021)
- [A Survey of Hallucination in Large Foundation Models](https://mlsanity.com/paper/2309.05922/) (2023)
- [QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization](https://mlsanity.com/paper/2112.08542/) (2021)
- [Q2: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering](https://mlsanity.com/paper/2104.08202/) (2021)
- [A Dataset for Document Grounded Conversations](https://mlsanity.com/paper/1809.07358/) (2018)
- [Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations](https://mlsanity.com/paper/2308.11995/) (2023)
- [Alleviating Hallucinations of Large Language Models through Induced Hallucinations](https://mlsanity.com/paper/2312.15710/) (2023)
- [Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark](https://mlsanity.com/paper/2105.00071/) (2021)
- [DialFact: A Benchmark for Fact-Checking in Dialogue](https://mlsanity.com/paper/2110.08222/) (2021)
- [Fighting Fire with Fire: The Dual Role of LLMs in Crafting and Detecting Elusive Disinformation](https://mlsanity.com/paper/2310.15515/) (2023)
- [Diving Deep into Modes of Fact Hallucinations in Dialogue Systems](https://mlsanity.com/paper/2301.04449/) (2023)
- [HaluEval-Wild: Evaluating Hallucinations of Language Models in the Wild](https://mlsanity.com/paper/2403.04307/) (2024)
- [Fast and Accurate Factual Inconsistency Detection Over Long Documents](https://mlsanity.com/paper/2310.13189/) (2023)

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

- [Refine Knowledge of Large Language Models via Adaptive Contrastive Learning](https://mlsanity.com/paper/2502.07184/) (2025)
- [HalluciNot: Hallucination Detection Through Context and Common Knowledge Verification](https://mlsanity.com/paper/2504.07069/) (2025)
- [Attention with Dependency Parsing Augmentation for Fine-Grained Attribution](https://mlsanity.com/paper/2412.11404/) (2024)
- [When the Wrong Key Wins: Understanding and Detecting Hallucinations in LLMs](https://mlsanity.com/paper/2609.15106/) (2026)
- [Vroom-Vroom at SHROOM-Visions: A Multi-Judge Committee for Detecting Hallucinated Spans in Vision-Language Outputs](https://mlsanity.com/paper/2609.17327/) (2026)

## Abstract (arXiv)

Detecting hallucinations in large language model (LLM) outputs is pivotal, yet traditional fine-tuning for this classification task is impeded by the expensive and quickly outdated annotation process, especially across numerous vertical domains and in the face of rapid LLM advancements. In this study, we introduce an approach that automatically generates both faithful and hallucinated outputs by rewriting system responses. Experimental findings demonstrate that a T5-base model, fine-tuned on our generated dataset, surpasses state-of-the-art zero-shot detectors and existing synthetic generation methods in both accuracy and latency, indicating efficacy of our approach.