# Factored Verification: Detecting and Reducing Hallucination in Summaries of Academic Papers

arXiv: https://arxiv.org/abs/2310.10627 · HTML: https://mlsanity.com/paper/2310.10627/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 26 references that are in the map.
- First posted on arXiv 16 Oct 2023.

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

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [Self-critiquing models for assisting human evaluators](https://mlsanity.com/paper/2206.05802/) (2022)
- [Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback](https://mlsanity.com/paper/2302.12813/) (2023)
- [Chain-of-Verification Reduces Hallucination in Large Language Models](https://mlsanity.com/paper/2309.11495/) (2023)
- [Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization](https://mlsanity.com/paper/2109.09784/) (2021)
- [The Factual Inconsistency Problem in Abstractive Text Summarization: A Survey](https://mlsanity.com/paper/2104.14839/) (2021)
- [Zero-shot Faithful Factual Error Correction](https://mlsanity.com/paper/2305.07982/) (2023)

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

- [FaithLens: Detecting and Explaining Faithfulness Hallucination](https://mlsanity.com/paper/2512.20182/) (2025)
- [Confabulations from ACL Publications (CAP): A Dataset for Scientific Hallucination Detection](https://mlsanity.com/paper/2510.22395/) (2025)
- [OpenFActScore: Open-Source Atomic Evaluation of Factuality in Text Generation](https://mlsanity.com/paper/2507.05965/) (2025)
- [Sharding Prevents LLM Oversight Failures and Adversarial Exploitation](https://mlsanity.com/paper/2608.06422/) (2026)

## Abstract (arXiv)

Hallucination plagues even frontier LLMs--but how bad is it really for summarizing academic papers? We evaluate Factored Verification, a simple automated method for detecting hallucinations in abstractive summaries. This method sets a new SotA on hallucination detection in the summarization task of the HaluEval benchmark, achieving 76.2% accuracy. We then use this method to estimate how often language models hallucinate when summarizing across multiple academic papers and find 0.62 hallucinations in the average ChatGPT (16k) summary, 0.84 for GPT-4, and 1.55 for Claude 2. We ask models to self-correct using Factored Critiques and find that this lowers the number of hallucinations to 0.49 for ChatGPT, 0.46 for GPT-4, and 0.95 for Claude 2. The hallucinations we find are often subtle, so we advise caution when using models to synthesize academic papers.