Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models
arXiv:2607. 22098v1 Announce Type: cross Abstract: Large reasoning models (LRMs) generate long reasoning traces before producing final answers.
arXiv:2607. 22098v1 Announce Type: cross Abstract: Large reasoning models (LRMs) generate long reasoning traces before producing final answers.
arXiv:2603. 16728v2 Announce Type: replace Abstract: Vision-language models (VLMs) are increasingly deployed in high-stakes settings where reliable uncertainty quantification (UQ) is as important as predictive accuracy.
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.
arXiv:2607. 10476v1 Announce Type: cross Abstract: Large language models (LLMs) have emerged as a powerful tool for retrieving knowledge through seamless, human-like interactions.
arXiv:2607. 07507v1 Announce Type: cross Abstract: Hallucinations in vision language models (VLMs) are commonly treated as semantic errors, yet they often arise from partial or ambiguous visual evidence.
arXiv:2606. 11172v1 Announce Type: new Abstract: Deployed large reasoning models (LRMs) often behave unexpectedly.
ConfRAG introduces a confidence-guided approach to reduce hallucinations in large language models and selectively trigger Retrieval-Augmented Generation (RAG) only when the model is uncertain. The ConfQA fine‑tuning strategy trains the model to answer correctly or respond with "I am unsure," achieving a drop in hallucination rates from 20‑40% to below 5% across factuality benchmarks. Building on ConfQA, ConfRAG limits external retrievals by more than 30% while maintaining over 95% accuracy in ideal scenarios.
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.
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:2606. 03628v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable progress in open-ended text generation, yet they remain prone to hallucinating incorrect or unsupported content, which undermines their reliability.
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.
RL-ARC is a calibration‑aware training framework that jointly uses reasoning confidence and answer confidence to improve the calibration of large reasoning models. It applies reasoning‑guided regularization for correct predictions and an overconfidence penalty for incorrect ones. Experiments on in‑distribution and out‑of‑distribution data show that RL‑ARC enhances calibration while preserving reasoning performance.