6 papers
StateFlow: Dual-State Recurrent Modeling for Long-Horizon Time Series Forecasting
Haroon Gharwi, Yue Dai, Kai Shu
Long-horizon multivariate time series forecasting (LTSF) remains challenging due to non-stationarity, regime shifts, and error accumulation. The Variability-Aware Recursive Neural…
Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction
Shanglin Wu, Lihui Liu, Jinho D. Choi +1
Large Language Models (LLMs) often struggle with producing factually consistent answers due to limitations in their parametric memory. Retrieval-Augmented Generation (RAG) paradigm…
Prompt-Induced Linguistic Fingerprints for LLM-Generated Fake News Detection
Chi Wang, Min Gao, Zongwei Wang +3
With the rapid development of large language models, the generation of fake news has become increasingly effortless, posing a growing societal threat and underscoring the urgent ne…
Measuring Sycophancy of Language Models in Multi-turn Dialogues
Jiseung Hong, Grace Byun, Seungone Kim +2
Large Language Models (LLMs) are expected to provide helpful and harmless responses, yet they often exhibit sycophancy--conforming to user beliefs regardless of factual accuracy or…
Variability Aware Recursive Neural Network (VARNN): A Residual-Memory Model for Capturing Temporal Deviation in Sequence Regression Modeling
Haroon Gharwi, Kai Shu
Real-world time series data exhibit non-stationary behavior, regime shifts, and temporally varying noise (heteroscedastic) that degrade the robustness of standard regression models…
TransNet: Transfer Knowledge for Few-shot Knowledge Graph Completion
Lihui Liu, Zihao Wang, Dawei Zhou +6
Knowledge graphs (KGs) are ubiquitous and widely used in various applications. However, most real-world knowledge graphs are incomplete, which significantly degrades their performa…