相关论文: Generating Informative and Diverse Conversational …

Conversational AI is rapidly becoming a primary interface for information seeking and decision making, yet most systems still assume idealized users. In practice, human reasoning is bounded by limited attention, uneven knowledge, and…

The feedback data of recommender systems are often subject to what was exposed to the users; however, most learning and evaluation methods do not account for the underlying exposure mechanism. We first show in theory that applying…

Standard accuracy metrics indicate that modern reading comprehension systems have achieved strong performance in many question answering datasets. However, the extent these systems truly understand language remains unknown, and existing…

The rapid spread of misinformation on digital platforms threatens public discourse, emotional stability, and decision-making. While prior work has explored various adversarial attacks in misinformation detection, the specific…

Adversarial training is an approach of increasing the robustness of models to adversarial attacks by including adversarial examples in the training set. One major challenge of producing adversarial examples is to contain sufficient…

Despite deep learning's broad success, its abstract-reasoning bottleneck persists. We tackle Raven's Progressive Matrices (RPM), the benchmark for pattern, reasoning and problem-solving intelligence. We model the full causal chain image…

This paper introduces DebateBrawl, an innovative AI-powered debate platform that integrates Large Language Models (LLMs), Genetic Algorithms (GA), and Adversarial Search (AS) to create an adaptive and engaging debating experience.…

Large language models have many beneficial applications, but can they also be used to attack content-filtering algorithms in social media platforms? We investigate the challenge of generating adversarial examples to test the robustness of…

Adversarial training is a technique for training robust machine learning models. To encourage robustness, it iteratively computes adversarial examples for the model, and then re-trains on these examples via some update rule. This work…

Adversarial machine learning concerns situations in which learners face attacks from active adversaries. Such scenarios arise in applications such as spam email filtering, malware detection and fake image generation, where security methods…

Large language models memorize parts of their training data. Memorizing short snippets and facts is required to answer questions about the world and to be fluent in any language. But models have also been shown to reproduce long verbatim…

Model-based curiosity combines active learning approaches to optimal sampling with the information gain based incentives for exploration presented in the curiosity literature. Existing model-based curiosity methods look to approximate…

This paper presents a system for diversity-aware autonomous conversation leveraging the capabilities of large language models (LLMs). The system adapts to diverse populations and individuals, considering factors like background,…

Generating qualitative responses has always been a challenge for human-computer dialogue systems. Existing dialogue systems generally derive from either retrieval-based or generative-based approaches, both of which have their own pros and…

Adversarial learning has emerged as one of the successful techniques to circumvent the susceptibility of existing methods against adversarial perturbations. However, the majority of existing defense methods are tailored to defend against a…

Counterfactual explanations offer actionable insights by illustrating how changes to inputs can lead to different outcomes. However, these explanations often suffer from ambiguity and impracticality, limiting their utility for non-expert…

It has been observed that deep learning architectures tend to make erroneous decisions with high reliability for particularly designed adversarial instances. In this work, we show that the perturbation analysis of these architectures…

We investigate the problem of reliable communication in the presence of active adversaries that can tamper with the transmitted data. We consider a legitimate transmitter-receiver pair connected over multiple communication paths (routes).…

Adversarial attack is commonly regarded as a huge threat to neural networks because of misleading behavior. This paper presents an opposite perspective: adversarial attacks can be harnessed to improve neural models if amended correctly.…

Lip reading has received an increasing research interest in recent years due to the rapid development of deep learning and its widespread potential applications. One key point to obtain good performance for the lip reading task depends…