arXiv:2606. 01033v1 Announce Type: new Abstract: When a language model hallucinates, the final answer is wrong, but the mistake is not necessarily invisible inside the model.
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.
Despite recent advances in large vision-language models (LVLMs), object hallucination remains a major barrier to their reliable deployment. Existing detection methods often characterize visual groundi...
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:2602. 02888v2 Announce Type: replace-cross Abstract: Hallucinations remain a major obstacle for large language models (LLMs), especially in safety-critical domains.
The paper introduces CADMP, a lightweight framework for detecting object hallucinations in large vision‑language models. CADMP measures cross‑modal attention drift between adjacent layers and verifies predictions by masking visually relevant regions, combining these signals to identify hallucinated outputs. Experiments on multiple benchmarks show that CADMP achieves competitive detection performance, and ablation studies confirm the complementary roles of attention drift and mask‑based verification.
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. 07302v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) often suffer from object hallucination, generating objects that are absent from the image.
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).
The paper introduces Prediction of Prediction (PoP), a method that fuses intermediate hidden representations across transformer layers during a single forward pass to detect hallucinations in large language models. PoP leverages internal hidden‑state transition dynamics to signal factual errors without extra decoding steps, achieving a 75.5% AUROC on the TruthfulQA benchmark with less than 1.2% added latency.
arXiv:2603. 21607v2 Announce Type: replace Abstract: While retrieval-augmented generation (RAG) significantly improves the factual reliability of LLMs, it does not eliminate hallucinations, so robust uncertainty quantification (UQ) remains essential.
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.
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.