Related papers: Measuring Uncertainty in Transformer Circuits with…

Recently, there have been efforts towards understanding the sampling behaviour of event-triggered control (ETC), for obtaining metrics on its sampling performance and predicting its sampling patterns. Finite-state abstractions, capturing…

Uncertainty estimation (UE) aims to detect hallucinated outputs of large language models (LLMs) to improve their reliability. However, UE metrics often exhibit unstable performance across configurations, which significantly limits their…

Large language models (LLMs) are increasingly deployed in settings where the available context is incomplete or degraded. We argue that an LLM generating answers under incomplete context can be viewed as an implicit imputer, and evaluated…

Effective Uncertainty Quantification (UQ) represents a key aspect for reliable deployment of Large Language Models (LLMs) in automated decision-making and beyond. Yet, for LLM generation with multiple choice structure, the state-of-the-art…

Explainability of black-box machine learning models is crucial, in particular when deployed in critical applications such as medicine or autonomous cars. Existing approaches produce explanations for the predictions of models, however, how…

Efficiently scaling industrial Click-Through Rate (CTR) prediction has recently attracted significant research attention. Existing approaches typically employ early aggregation of user behaviors to maintain efficiency. However, such…

Despite the rapid expansion of Large Language Models (LLMs) in healthcare, robust and explainable evaluation of their ability to assess clinical trial reporting according to CONSORT standards remains an open challenge. In particular,…

A novel iterative Equivalent Surface Current (iESC) algorithm has been developed to simulate the electromagnetic scattering of electrically large dielectric objects with relatively smooth surfaces. The iESC algorithm corrects the surface…

While Multimodal Large Language Models (MLLMs) show promising performance in automated electrocardiogram interpretation, it remains unclear whether they genuinely perform actual step-by-step reasoning or just rely on superficial visual…

In this paper, we present our system for SemEval-2026 Task 6 (CLARITY) on response clarity and evasion detection in question-answer pairs from U.S. presidential interviews, comparing fine-tuned encoders with prompt-based LLMs. Our LLM…

Large language models (LLMs) are increasingly used for high-stakes decisions, yet their susceptibility to spurious features remains poorly characterized. We introduce ICE-Guard, a framework applying intervention consistency testing to…

Uncertainty Quantification (UQ) is a promising approach to improve model reliability, yet quantifying the uncertainty of Large Language Models (LLMs) is non-trivial. In this work, we establish a connection between the uncertainty of LLMs…

Deep learning frameworks have become increasingly popular in brain computer interface (BCI) study thanks to their outstanding performance. However, in terms of the classification model alone, they are treated as black box as they do not…

In-context learning (ICL) is a central capability of Transformer models, but the structures in data that enable its emergence and govern its robustness remain poorly understood. In this work, we study how the structure of pretraining tasks…

Large language models (LLMs) have demonstrated remarkable performance, yet their diverse strengths and weaknesses prevent any single LLM from achieving dominance across all tasks. Ensembling multiple LLMs is a promising approach to generate…

Agent harnesses increasingly determine the performance of language-model systems by deciding how models call tools, receive feedback, verify intermediate states, store memory, and revise solutions. Yet current test-time scaling analyses…

We present a Transfer Causal Learning (TCL) framework when target and source domains share the same covariate/feature spaces, aiming to improve causal effect estimation accuracy in limited data. Limited data is very common in medical…

The use of emergent constraints to quantify uncertainty for key policy relevant quantities such as Equilibrium Climate Sensitivity (ECS) has become increasingly widespread in recent years. Many researchers, however, claim that emergent…

Preserving invariants while designing distributed applications under weak consistency models is difficult. The CEC (Correct Eventual Consistency Tool) is meant to aid the application designer in this task. It provides information about the…

State estimators often provide self-assessed uncertainty metrics, such as covariance matrices, whose credibility is critical for downstream tasks. However, these self-assessments can be misleading due to underlying modeling violations like…