# Quantifying Genuine Awareness in Hallucination Prediction Beyond Question-Side Shortcuts

arXiv: https://arxiv.org/abs/2509.15339 · HTML: https://mlsanity.com/paper/2509.15339/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 36 references that are in the map.
- First posted on arXiv 18 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)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [ELI5: Long Form Question Answering](https://mlsanity.com/paper/1907.09190/) (2019)
- [Measuring and Improving Consistency in Pretrained Language Models](https://mlsanity.com/paper/2102.01017/) (2021)
- [INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection](https://mlsanity.com/paper/2402.03744/) (2024)
- [Out-of-Distribution Detection and Selective Generation for Conditional Language Models](https://mlsanity.com/paper/2209.15558/) (2022)
- [Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering](https://mlsanity.com/paper/2210.01613/) (2022)
- [On Early Detection of Hallucinations in Factual Question Answering](https://mlsanity.com/paper/2312.14183/) (2023)
- [Shapley values for feature selection: The good, the bad, and the axioms](https://mlsanity.com/paper/2102.10936/) (2021)
- [Simple Question Answering by Attentive Convolutional Neural Network](https://mlsanity.com/paper/1606.03391/) (2016)

## Built on by (most cited first, 3 of 3)

- [A decodability criterion predicts when hidden-state selection beats majority voting in large language models](https://mlsanity.com/paper/2608.17124/) (2026)
- [AI Consciousness and Existential Risk](https://mlsanity.com/paper/2511.19115/) (2025)
- [Cross-Model In-Context Neurofeedback Reveals (Limited) Activation Control in LLMs](https://mlsanity.com/paper/2610.20179/) (2026)

## Abstract (arXiv)

Many works have proposed methodologies for language model (LM) hallucination detection and reported seemingly strong performance. However, we argue that the reported performance to date reflects not only a model's genuine awareness of its internal information, but also awareness derived purely from question-side information (e.g., benchmark hacking). While benchmark hacking can be effective for boosting hallucination detection score on existing benchmarks, it does not generalize to out-of-domain settings and practical usage. Nevertheless, disentangling how much of a model's hallucination detection performance arises from question-side awareness is non-trivial. To address this, we propose a methodology for measuring this effect without requiring human labor, Approximate Question-side Effect (AQE). Our analysis using AQE reveals that existing hallucination detection methods rely heavily on benchmark hacking.