From the 1 of 7 linked papers with an AI index.
7 papers
Critic Experience Bank: Self-Evolving Step-Level Confidence Estimation for LLM Agents
Yaopei Zeng, Congchao Wang, JianHang Chen +3
The paper proposes the Critic Experience Bank, a training-free framework that lets large language model agents estimate confidence for each action by storing and retrieving past st…
Forced Deferral: Manipulating Routing Decisions in Multimodal LLM Cascades
Zhongye Liu, Yaopei Zeng, Yurui Chang +1
While multimodal large language models (MLLMs) have shown strong visual reasoning abilities, serving a large model for every query is computationally expensive. MLLM cascades mitig…
Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks
Bohan Wang, Zewen Liu, Lu Lin +4
Interpretable time series deep learning systems are often assessed by checking temporal consistency on explanations, implicitly treating this as evidence of robustness. We show tha…
ForecastCompass: Guiding Agentic Forecasting with Adaptive Factor Memory
Yurui Chang, Yongkang Du, Yuanpu Cao +2
Agentic forecasting is important for decision-making in dynamic environments, but it remains challenging because agents must reason from incomplete, time-limited evidence and produ…
Score-based Conditional Out-of-Distribution Augmentation for Graph Covariate Shift
Bohan Wang, Yurui Chang, Wei Jin +1
Distribution shifts between training and testing datasets significantly impair the model performance on graph learning. A commonly-taken causal view in graph invariant learning sug…
Monitoring Decoding: Mitigating Hallucination via Evaluating the Factuality of Partial Response during Generation
Yurui Chang, Bochuan Cao, Lu Lin
While large language models have demonstrated exceptional performance across a wide range of tasks, they remain susceptible to hallucinations -- generating plausible yet factually…