arXiv:2509. 24770v2 Announce Type: replace Abstract: Large Language Models (LLMs) often generate incorrect or unsupported content, known as hallucinations.
arXiv:2604. 10697v2 Announce Type: replace-cross Abstract: Large language models frequently exhibit hallucinations: fluent and confident outputs that are factually incorrect or unsupported by the input context.
arXiv:2606. 19351v1 Announce Type: cross Abstract: Knowledge graph (KG) reasoning infers new knowledge from existing facts and is widely applied in question answering, recommendation, and decision support.
arXiv:2606. 31166v1 Announce Type: cross Abstract: Text-attributed graphs (TAGs), where each node carries a natural language description, require models to jointly reason over text and graph topology.
arXiv:2604. 07492v2 Announce Type: replace-cross Abstract: Message Passing Neural Networks have recently become the most popular approach to graph machine learning tasks; however, their receptive field is limited by the number of message passing layers.
The paper reinterprets graph neural networks (GNNs) as retrieval-augmented models, where each layer uses an MLP on a node representation and a permutation‑invariant summary of retrieved graph context instead of traditional message passing. It introduces RTA, a lightweight MLP‑based framework that replaces structural message passing with label‑aware retrieval and propagation, and provides theoretical links to softmax‑attention message passing and robustness to mis‑retrieved outliers. Experiments on text‑attributed graph benchmarks demonstrate that RTA matches or surpasses strong GNN and graph LLM baselines while improving efficiency and robustness.
The paper investigates how the topology of attention graphs can differentiate hallucinated from non-hallucinated responses in large language models. By analyzing Forman-Ricci curvature, the authors identify structural bottlenecks and develop a method that captures both semi-local and global information-flow characteristics of attention heads associated with hallucinations. Extensive evaluation across multiple LLMs and benchmarks shows that this single-pass approach consistently outperforms existing attention-based and multi-response baselines, while also revealing that impaired context sharing—such as over-reliance on self-attention and information over-squashing—correlates strongly with hallucination occurrences.
arXiv:2608. 10835v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) achieve impressive visual reasoning and dialogue capabilities, yet frequently hallucinate content unsupported by the visual input.
arXiv:2606. 27679v1 Announce Type: cross Abstract: Probe-based uncertainty estimation (UE) has emerged as a prominent approach to detect hallucinations in Large Language Models (LLMs) by learning uncertainty from internal model signals.
The paper proposes a hidden‑state probing method for detecting hallucinations at the span level in large language model outputs, moving beyond token‑wise binary classification. By examining layer‑wise activation patterns, the approach identifies the exact onset and continuation tokens of hallucinations, achieving higher precision‑recall AUC than random baselines despite class imbalance. Additionally, the authors introduce a cross‑model detection framework where one model observes another’s internal representations, showing that an external observer can match or surpass the generator’s own self‑detection of hallucination onsets, even when the observer is smaller.
arXiv:2608. 16353v1 Announce Type: cross Abstract: Even well-aligned large language models confidently generate factually incorrect text, making hallucination a persistent reliability risk in high-stakes deployments.
arXiv:2607. 22098v1 Announce Type: cross Abstract: Large reasoning models (LRMs) generate long reasoning traces before producing final answers.
arXiv:2609.14448v1 Announce Type: cross Abstract: Hallucination in large language models reduces their reliability and slows adoption. Various white-box studies have used internal representations to...