arXiv AI
Alleviating Hallucination in Reasoning Tasks with Training-Free Uncertainty-Guided Steering
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jul 27
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 Machine Learning
Jul 14
The Cost of Reasoning: Chain-of-Thought Induces Overconfidence in Vision-Language Models
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.
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.
arXiv Machine Learning
Jul 14
Hallucination Detection in Large Language Models Using Diversion Decoding
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 AI
Jul 9
HIVE: Understanding Post-Hallucination Reasoning in Vision Language Models
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 Machine Learning
Jun 10
Predicting Future Behaviors in Reasoning Models Enables Better Steering
arXiv:2606. 11172v1 Announce Type: new Abstract: Deployed large reasoning models (LRMs) often behave unexpectedly.