# On Early Detection of Hallucinations in Factual Question Answering

arXiv: https://arxiv.org/abs/2312.14183 · HTML: https://mlsanity.com/paper/2312.14183/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 44 references that are in the map.
- First posted on arXiv 19 Dec 2023.

## Builds on (most cited first, 21 of 21)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (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)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [Explaining Explanations: An Overview of Interpretability of Machine Learning](https://mlsanity.com/paper/1806.00069/) (2018)
- [Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics](https://mlsanity.com/paper/2104.13346/) (2021)
- [Unsupervised Quality Estimation for Neural Machine Translation](https://mlsanity.com/paper/2005.10608/) (2020)
- [Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering](https://mlsanity.com/paper/2307.16877/) (2023)
- [Detecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even Better](https://mlsanity.com/paper/2212.08597/) (2022)
- [Analyzing the Source and Target Contributions to Predictions in Neural Machine Translation](https://mlsanity.com/paper/2010.10907/) (2020)
- [Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation](https://mlsanity.com/paper/2208.05309/) (2022)
- [Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer](https://mlsanity.com/paper/2205.11631/) (2022)

## Built on by (most cited first, 30 of 56)

- [LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations](https://mlsanity.com/paper/2410.02707/) (2024)
- [LLM Internal States Reveal Hallucination Risk Faced With a Query](https://mlsanity.com/paper/2407.03282/) (2024)
- [Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification](https://mlsanity.com/paper/2502.01839/) (2025)
- [LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions](https://mlsanity.com/paper/2509.18970/) (2025)
- [Large Language Models Hallucination: A Comprehensive Survey](https://mlsanity.com/paper/2510.06265/) (2025)
- [Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations](https://mlsanity.com/paper/2503.14477/) (2025)
- [Estimating Knowledge in Large Language Models Without Generating a Single Token](https://mlsanity.com/paper/2406.12673/) (2024)
- [No Answer Needed: Predicting LLM Answer Accuracy from Question-Only Linear Probes](https://mlsanity.com/paper/2509.10625/) (2025)
- [Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models](https://mlsanity.com/paper/2407.08039/) (2024)
- [ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models](https://mlsanity.com/paper/2412.07012/) (2024)
- [Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)](https://mlsanity.com/paper/2407.12858/) (2024)
- [Robust Hallucination Detection in LLMs via Adaptive Token Selection](https://mlsanity.com/paper/2504.07863/) (2025)
- [Correctness Assessment of Code Generated by Large Language Models Using Internal Representations](https://mlsanity.com/paper/2501.12934/) (2025)
- [Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT](https://mlsanity.com/paper/2510.00296/) (2025)
- [From Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty](https://mlsanity.com/paper/2407.06071/) (2024)
- [Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions](https://mlsanity.com/paper/2503.14043/) (2025)
- [Can LLMs Explain Themselves Counterfactually?](https://mlsanity.com/paper/2502.18156/) (2025)
- [Zero-resource Hallucination Detection for Text Generation via Graph-based Contextual Knowledge Triples Modeling](https://mlsanity.com/paper/2409.11283/) (2024)
- [Fake Artificial Intelligence Generated Contents (FAIGC): A Survey of Theories, Detection Methods, and Opportunities](https://mlsanity.com/paper/2405.00711/) (2024)
- [Towards Reliable Latent Knowledge Estimation in LLMs: Zero-Prompt Many-Shot Based Factual Knowledge Extraction](https://mlsanity.com/paper/2404.12957/) (2024)
- [GORAG: Graph-based Online Retrieval Augmented Generation for Dynamic Few-shot Social Media Text Classification](https://mlsanity.com/paper/2501.02844/) (2025)
- [DioR: Adaptive Cognitive Detection and Contextual Retrieval Optimization for Dynamic Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.10198/) (2025)
- [AGRAG: Advanced Graph-based Retrieval-Augmented Generation for LLMs](https://mlsanity.com/paper/2511.05549/) (2025)
- [To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Calling](https://mlsanity.com/paper/2605.00737/) (2026)
- [Is There No Such Thing as a Bad Question? H4R: HalluciBot For Ratiocination, Rewriting, Ranking, and Routing](https://mlsanity.com/paper/2404.12535/) (2024)
- [CARROT: A Learned Cost-Constrained Retrieval Optimization System for RAG](https://mlsanity.com/paper/2411.00744/) (2024)
- [AI Agent Behavioral Science](https://mlsanity.com/paper/2506.06366/) (2025)
- [Neural Message-Passing on Attention Graphs for Hallucination Detection](https://mlsanity.com/paper/2509.24770/) (2025)
- [Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs](https://mlsanity.com/paper/2507.21914/) (2025)
- [Gradient-Stable Attention Heads Signal LLM Correctness](https://mlsanity.com/paper/2602.13699/) (2026)

## Abstract (arXiv)

While large language models (LLMs) have taken great strides towards helping humans with a plethora of tasks, hallucinations remain a major impediment towards gaining user trust. The fluency and coherence of model generations even when hallucinating makes detection a difficult task. In this work, we explore if the artifacts associated with the model generations can provide hints that the generation will contain hallucinations. Specifically, we probe LLMs at 1) the inputs via Integrated Gradients based token attribution, 2) the outputs via the Softmax probabilities, and 3) the internal state via self-attention and fully-connected layer activations for signs of hallucinations on open-ended question answering tasks. Our results show that the distributions of these artifacts tend to differ between hallucinated and non-hallucinated generations. Building on this insight, we train binary classifiers that use these artifacts as input features to classify model generations into hallucinations and non-hallucinations. These hallucination classifiers achieve up to 0.80 AUROC. We also show that tokens preceding a hallucination can already predict the subsequent hallucination even before it occurs.