arXiv Computation and Language October 5, 2026 By Yangfan Hu, Xuhan Tong, Haoyue Bai, Xi Ding, Shashank Muralidhar Bharadwaj, Siyang Cao, Robert Nowak, Jiawei Zhang

Understanding Why Language Models Hallucinate: Testing Reasoning Against Priors

Read the original on arXiv Computation and Language →

The paper investigates why large language models hallucinate by proposing that failures often stem from inference misalignment rather than missing knowledge. It introduces a latent key-task model that shows pretraining-frequency imbalance can cause shortcut inference paths to dominate, leading to hallucinations. The authors create TrapQA, a diagnostic testbed with ScientistQA and Real-Life Constrained QA, to demonstrate two failure modes—task-retrieval bias and key-selection bias—where biased latent inference produces hallucinated answers.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv Computation and Language

Sep 15

When the Wrong Key Wins: Understanding and Detecting Hallucinations in LLMs

arXiv:2609.15106v1 Announce Type: new Abstract: Large language models can hallucinate even when the knowledge required for a correct answer is already available. We study this failure through a laten...

By Xuhan Tong, Jiawei Zhang

llms benchmarks safety

arXiv AI

Jul 24

Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers

arXiv:2603. 01437v2 Announce Type: replace Abstract: As chain of thought (CoT) has become central to scaling reasoning capabilities in large language models (LLMs), it has also emerged as a promising tool for interpretability, suggesting the opportunity to understand model decisions through verbalized reasoning.

By Kyle Cox, Darius Kianersi, Adri\`a Garriga-Alonso

llms safety

arXiv AI

Sep 10

Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented Generation

The paper introduces Evidence-Aligned Entity Verification (EAEV), a method for detecting entity-level hallucinations in retrieval-augmented generation (RAG). EAEV aligns generated entities with retrieved evidence across three dimensions and uses counterfactual stability analysis to maintain robust alignments when evidence changes. Experiments on multiple RAG benchmarks show that EAEV consistently outperforms existing hallucination detection methods and generalizes well.

By Runsong Jia, Zhen Fang, Mengjia Wu, Jie Lu, Yi Zhang

llms rag benchmarks safety

arXiv Machine Learning

Sep 17

Attention Dispersion as a Diagnostic Signal for Hallucination in Large Language Models

The paper proposes using the temporal volatility of internal attention mechanisms—measured by an unsupervised attention dispersion metric—as a diagnostic signal for hallucinations in large language models. It demonstrates that spikes in attention entropy within intermediate layers correlate with reasoning breakdowns, and shows statistically significant AUC improvements of up to +0.076 over output-based baselines on GSM8K and MATH-500 benchmarks using the Qwen2.5 model family.

By Shardul P. More, Tanuja S. Pawar

llms benchmarks safety

arXiv Computation and Language

22h ago

The Labeling Problem in Hallucination Detection Benchmarks: An Empirical Evaluation

arXiv:2610.08026v1 Announce Type: new Abstract: In recent years, several methods for detecting when large language models (LLMs) hallucinate have been developed. These methods are often benchmarked w...

By Jorma Valjakka, Juhani Kivim\"aki, Juha Myll\"ari, Jukka K. Nurminen

llms nlp benchmarks safety

arXiv AI

Sep 1

Small Updates, Big Doubts: Does Parameter-Efficient Fine-tuning Enhance Hallucination Detection ?

arXiv:2602.11166v2 Announce Type: replace-cross Abstract: Parameter-efficient fine-tuning (PEFT) methods are widely used to adapt large language models (LLMs) to downstream tasks and are often assume...

By Xu Hu, Yifan Zhang, Songtao Wei, Chen Zhao, Qiannan Li, Bingzhe Li, Feng Chen

llms fine-tuning benchmarks safety

One email a morning, machine-written

Related stories

When the Wrong Key Wins: Understanding and Detecting Hallucinations in LLMs

Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers

Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented Generation

Attention Dispersion as a Diagnostic Signal for Hallucination in Large Language Models

The Labeling Problem in Hallucination Detection Benchmarks: An Empirical Evaluation

Small Updates, Big Doubts: Does Parameter-Efficient Fine-tuning Enhance Hallucination Detection ?