# Investigating Symbolic Triggers of Hallucination in Gemma Models Across HaluEval and TruthfulQA

arXiv: https://arxiv.org/abs/2509.09715 · HTML: https://mlsanity.com/paper/2509.09715/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 21 references that are in the map.
- First posted on arXiv 9 Sep 2025.

## Builds on (most cited first, 18 of 18)

- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models](https://mlsanity.com/paper/2309.01219/) (2023)
- [Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks](https://mlsanity.com/paper/1502.05698/) (2015)
- [FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization](https://mlsanity.com/paper/2005.03754/) (2020)
- [AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders](https://mlsanity.com/paper/2501.17148/) (2025)
- [LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples](https://mlsanity.com/paper/2310.01469/) (2023)
- [Evaluating Open-Domain Question Answering in the Era of Large Language Models](https://mlsanity.com/paper/2305.06984/) (2023)
- [Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey](https://mlsanity.com/paper/2503.22458/) (2025)
- [Benchmarking Hallucination in Large Language Models based on Unanswerable Math Word Problem](https://mlsanity.com/paper/2403.03558/) (2024)
- [Towards Robust Evaluation of Unlearning in LLMs via Data Transformations](https://mlsanity.com/paper/2411.15477/) (2024)
- [Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negation](https://mlsanity.com/paper/2406.05494/) (2024)
- [Question-Analysis Prompting Improves LLM Performance in Reasoning Tasks](https://mlsanity.com/paper/2407.03624/) (2024)
- [A Survey on Symbolic Knowledge Distillation of Large Language Models](https://mlsanity.com/paper/2408.10210/) (2024)
- [Strong hallucinations from negation and how to fix them](https://mlsanity.com/paper/2402.10543/) (2024)
- [COBIAS: Assessing the Contextual Reliability of Bias Benchmarks for Language Models](https://mlsanity.com/paper/2402.14889/) (2024)

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

- [Probabilities Are All You Need: A Probability-Only Approach to Uncertainty Estimation in Large Language Models](https://mlsanity.com/paper/2511.07694/) (2025)
- [SymLoc: Symbolic Localization of Hallucination across HaluEval and TruthfulQA](https://mlsanity.com/paper/2511.14172/) (2025)
- [Hallucinations in LLMs: A Lifecycle-Based Survey of Causes, Detection, Mitigation, and Prevention](https://mlsanity.com/paper/2608.26168/) (2026)

## Abstract (arXiv)

Hallucination in Large Language Models (LLMs) is a well studied problem. However, the properties that make LLM intrinsically vulnerable to hallucinations have not been identified and studied. This research identifies and characterizes the key properties, allowing us to pinpoint vulnerabilities within the model's internal mechanisms. To solidify on these properties, we utilized two established datasets, HaluEval and TruthfulQA and convert their existing format of question answering into various other formats to narrow down these properties as the reason for the hallucinations. Our findings reveal that hallucination percentages across symbolic properties are notably high for Gemma-2-2B, averaging 79.0% across tasks and datasets. With increased model scale, hallucination drops to 73.6% for Gemma-2-9B and 63.9% for Gemma-2-27B, reflecting a 15 percentage point reduction overall. Although the hallucination rate decreases as the model size increases, a substantial amount of hallucination caused by symbolic properties still persists. This is especially evident for modifiers (ranging from 84.76% to 94.98%) and named entities (ranging from 83.87% to 93.96%) across all Gemma models and both datasets. These findings indicate that symbolic elements continue to confuse the models, pointing to a fundamental weakness in how these LLMs process such inputs--regardless of their scale.