The paper introduces LOTUS, a low‑rank multilinear decomposition method for detecting hallucinations in large language models. LOTUS compresses variable‑length token representations into compact features using statistical descriptors of peak activations, distributions, and cross‑layer changes, then applies low‑rank decomposition to capture the underlying structure of hidden states. Experiments on several LLMs and QA benchmarks show that LOTUS outperforms recent state‑of‑the‑art hallucination detectors while requiring less labeled data.
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.
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.
The paper introduces SHAM-Bench, a unified benchmark for detecting span-level hallucinations across six natural language generation tasks, compiled from 6,461 human-annotated examples under a common schema. It evaluates existing detection methods, finding that fine‑tuned detectors perform well in‑domain but falter under distribution shift, while prompt‑based methods with reasoning show greater robustness. The study also highlights challenges such as subtle unsupported content, ambiguous span boundaries, and noisy labels, and releases the dataset, evaluation code, and a public leaderboard for future research.
arXiv:2605. 26366v3 Announce Type: replace Abstract: Recent studies on hallucination detection have shown that hallucination-related signals are more strongly encoded in intermediate layers than in the final layer of large language models (LLMs).
arXiv:2607. 22661v1 Announce Type: new Abstract: Diffusion large language models (D-LLMs) have recently gained increasing attention, yet their reliability is significantly hindered by the hallucination problem.
arXiv:2610.33442v1 Announce Type: new Abstract: Large language models (LLMs) are reported to be susceptible to reliability issues including hallucinations and reasoning errors. Existing quality detec...
arXiv:2608. 14632v1 Announce Type: cross Abstract: Diffusion large language models (D-LLMs) have emerged as a promising paradigm for text generation.
arXiv:2606. 00819v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved strong performance across diverse natural language tasks, yet their outputs often suffer from hallucinations -- content that is misaligned with factual information.
Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse tasks, yet they remain prone to generating hallucinations. Detecting these hallucinations is critical for deploying LLMs reliably in high-stakes applications.
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. 07528v1 Announce Type: cross Abstract: Hallucination in large language models (LLMs), defined as the generation of factually incorrect or unsupported content, remains a critical barrier to reliable deployment.
arXiv:2602. 07253v3 Announce Type: replace Abstract: Detecting hallucinations in large language models is a critical open problem with significant implications for safety and reliability.