Related papers: Open-Domain Safety Policy Construction
Large Language Models (LLMs) are increasingly deployed to curate and rank human-created content, yet the nature and structure of their biases in these tasks remains poorly understood: which biases are robust across providers and platforms,…
Multiple-Criteria Decision Making (MCDM) is a sub-discipline of Operations Research that helps decision-makers in choosing, ranking, or sorting alternatives based on conflicting criteria. Over time, its application has been expanded into…
In Wireless Networked Control Systems (WNCSs), control and communication systems must be co-designed due to their strong interdependence. This paper presents a novel optimization theory-based safe deep reinforcement learning (DRL) framework…
Deep reinforcement learning (DRL) finds extensive application in autonomous drone navigation within complex, high-risk environments. However, its practical deployment faces a safety-exploration dilemma: soft penalty mechanisms encourage…
Prompt privacy is crucial, especially when using online large language models (LLMs), due to the sensitive information often contained within prompts. While LLMs can enhance prompt privacy through text rewriting, existing methods primarily…
The remarkable proliferation of deep learning across various industries has underscored the importance of data privacy and security in AI pipelines. As the evolution of sophisticated Membership Inference Attacks (MIAs) threatens the secrecy…
With the emergence of smart cities, Internet of Things (IoT) devices as well as deep learning technologies have witnessed an increasing adoption. To support the requirements of such paradigm in terms of memory and computation, joint and…
This paper applies deep reinforcement learning (DRL) to optimize liquidity provisioning in Uniswap v3, a decentralized finance (DeFi) protocol implementing an automated market maker (AMM) model with concentrated liquidity. We model the…
Multi-domain sentiment classification aims to mitigate poor performance models due to the scarcity of labeled data in a single domain, by utilizing data labeled from various domains. A series of models that jointly train domain classifiers…
Online discourse takes place in corporate-controlled spaces thought by users to be public realms. These platforms in name enable free speech but in practice implement varying degrees of censorship either by government edict or by uneven and…
In the mobile Internet era, the recommender system has become an irreplaceable tool to help users discover useful items, and thus alleviating the information overload problem. Recent deep neural network (DNN)-based recommender system…
The growing prospect of deep reinforcement learning (DRL) being used in cyber-physical systems has raised concerns around safety and robustness of autonomous agents. Recent work on generating adversarial attacks have shown that it is…
Privacy-preserving distributed processing has recently attracted considerable attention. It aims to design solutions for conducting signal processing tasks over networks in a decentralized fashion without violating privacy. Many algorithms…
Neural retrieval models excel in Web search, but their training requires substantial amounts of labeled query-document pairs, which are costly to obtain. With the widespread availability of Web document collections like ClueWeb22, synthetic…
Policy optimization (PO) is a cornerstone of modern reinforcement learning (RL), with diverse applications spanning robotics, healthcare, and large language model training. The increasing deployment of PO in sensitive domains, however,…
A recommender system generates personalized recommendations for a user by computing the preference score of items, sorting the items according to the score, and filtering top-K items with high scores. While sorting and ranking items are…
Large Reasoning Models (LRMs) and Multi-Agent Systems (MAS) in high-stakes domains demand reliable verification, yet centralized approaches suffer four limitations: (1) Robustness, with single points of failure vulnerable to attacks and…
Machine learning based classifiers that take a privacy policy as the input and predict relevant concepts are useful in different applications such as (semi-)automated compliance analysis against requirements of the EU GDPR. In all past…
This paper introduces a novel Deep Researcher architecture designed to generate detailed research reports on complex PhD level topics by addressing the inherent limitations of the Parallel Scaling paradigm. Our system utilizes two key…
Knowledge-based AI typically depends on a knowledge engineer to construct a formal model of domain knowledge -- but what if domain experts could do this themselves? This paper describes an extension to the Decision Model and Notation (DMN)…