6 papers
SPECTRA: State-Space Exogenous Context and Temporal-Frequency Resolution Architecture for Probabilistic Energy Forecasting
Hang Ye, Xinyan Jiang, Yuedong Shi +5
Modern power systems increasingly require probabilistic forecasts amid interacting uncertainties from renewable intermittency, flexible demand, market volatility, and weather-depen…
Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability
Xinyan Jiang, Ninghao Liu, Di Wang +1
Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning. We introduce TRACED, a framework that assesses reasoning quality th…
In-Context Learning Operates as Concept Subspace Learning
Wei Tang, Xinyan Jiang, Fakhri Karray +1
Regression and Bayesian accounts of in-context learning (ICL) explain how demonstrations can induce predictors, while mechanistic analyses often identify compact activation directi…
Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models
Chengsheng Zhang, Chenghao Sun, Xinyan Jiang +2
Large Vision-Language Models (LVLMs) have achieved remarkable progress in visual-textual understanding, yet their reliability is critically undermined by hallucinations, i.e., the…
Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency
Xinyan Jiang, Wenjing Yu, Di Wang +1
Activation engineering enables precise control over Large Language Models (LLMs) without the computational cost of fine-tuning. However, existing methods deriving vectors from stat…
HICD: Hallucination-Inducing via Attention Dispersion for Contrastive Decoding to Mitigate Hallucinations in Large Language Models
Xinyan Jiang, Hang Ye, Yongxin Zhu +3
Large Language Models (LLMs) often generate hallucinations, producing outputs that are contextually inaccurate or factually incorrect. We introduce HICD, a novel method designed to…