This paper proposes DeMix, a novel framework for simultaneously diagnosing erroneous samples and their error types in machine learning models.

This paper characterizes the risk of covert influence—where a sender's hidden behavioral payload transfers to a receiver through undetectable carriers—across three common LLM interfaces, demonstrating…

The paper introduces Influence-Guided Symbolic Regression (IGSR), a novel framework that uses granular influence scores to guide LLMs in efficiently searching for and discovering complex mathematical…

This paper proposes a new framework called STRIDE for training data attribution in Large Language Models.

This study compares various authorship attribution methods on Japanese web reviews, finding that while BERT fine-tuning performs best, TF-IDF+LR offers superior stability and efficiency for large-scal…

The paper introduces a quotient-DAG view to accurately estimate unordered slate propensities for off-policy evaluation, solving the nuisance variance and computational gap inherent in standard importa…

The paper introduces a novel paradigm where a fine-tuned LLM acts as an ancillary predictor to forecast likely advertisers, significantly improving ad recommendation systems by augmenting candidate ge…

The paper introduces the Vector Network (VN), a novel recurrent architecture that replaces fixed weight matrices with reusable weight atoms, enabling superior compositional generalization by making st…

DiffuSent proposes a non-auto-regressive diffusion framework to unify Aspect-Based Sentiment Analysis (ABSA), significantly improving boundary detection for multi-word aspect and opinion terms.

The paper proposes ProRL, an effective Reinforcement Learning framework that rectifies gradient estimation deficiencies to optimize proactive recommendation paths, significantly outperforming existing…

The paper introduces a framework to quantitatively measure evolving agent behaviors (traits) by analyzing changes in their configuration text files, achieving high accuracy in classifying behavioral s…

This paper proposes a novel framework, DS-MLP, for click-through rate prediction in online advertising and recommendation systems.

SPAR introduces a novel framework that rectifies action policies by performing local fine-tuning in a residual space anchored to a pure behavior cloning policy, achieving state-of-the-art performance…

The paper introduces ARCANE, a Bayesian network framework for cross-campaign cyber attribution, finding that while aggregating telemetry improves identification, structural feature limitations prevent…

The paper demonstrates that supervised fine-tuning significantly outperforms frontier zero-shot large language models for screen-conditioned action prediction on the PiSAR benchmark, highlighting the…

The paper demonstrates that the order and content of external information (the 'feed') an LLM agent consumes before making a decision can significantly and causally steer its final choice, often overr…

The paper demonstrates that the sequence and composition of external information (the 'feed') an LLM agent consumes can significantly and causally steer its final decisions, often overriding its defau…

ShaplEIG introduces a Bayesian experimental design framework to efficiently and adaptively estimate Shapley values by minimizing the number of required costly function evaluations.

This paper addresses the lack of specialized NLP tools for detecting toxicity in real-time video game chat by creating a large, fine-grained dataset and developing a superior, domain-specific detector…

This paper compares traditional machine learning models (Random Forests, XGBoost, SVM) against a complex Unified Multi-Task Time Series Model for churn prediction, concluding that conventional methods…