Reinforcement Unlearning
Machine unlearning refers to the process of mitigating the influence of specific training data on machine learning models based on removal requests from data owners. However, one important area that...
View ArticleNPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models...
Complex reasoning ability is one of the most important features of current LLMs, which has also been leveraged to play an integral role in complex decision-making tasks. Therefore, the investigation...
View ArticleBeyond mirkwood: Enhancing SED Modeling with Conformal Predictions
Traditional spectral energy distribution (SED) fitting techniques face uncertainties due to assumptions in star formation histories and dust attenuation curves. We propose an advanced machine...
View ArticleFast, Scalable, Warm-Start Semidefinite Programming with Spectral Bundling...
While semidefinite programming (SDP) has traditionally been limited to moderate-sized problems, recent algorithms augmented with matrix sketching techniques have enabled solving larger SDPs. However,...
View ArticleFast sampling from constrained spaces using the Metropolis-adjusted Mirror...
We propose a new method called the Metropolis-adjusted Mirror Langevin algorithm for approximate sampling from distributions whose support is a compact and convex set. This algorithm adds an...
View ArticleFortify the Shortest Stave in Attention: Enhancing Context Awareness of Large...
In this paper, we demonstrate that an inherent waveform pattern in the attention allocation of large language models (LLMs) significantly affects their performance in tasks demanding a high degree of...
View ArticleMultiGPrompt for Multi-Task Pre-Training and Prompting on Graphs
Graphs can inherently model interconnected objects on the Web, thereby facilitating a series of Web applications, such as web analyzing and content recommendation. Recently, Graph Neural Networks...
View ArticleIs Inverse Reinforcement Learning Harder than Standard Reinforcement...
Inverse Reinforcement Learning (IRL) -- the problem of learning reward functions from demonstrations of an \emph{expert policy} -- plays a critical role in developing intelligent systems. While widely...
View ArticleDetection of developmental language disorder in Cypriot Greek children using...
Children with developmental language disorder (DLD) encounter difficulties in acquiring various language structures. Early identification and intervention are crucial to prevent negative long-term...
View ArticleUniversal Jailbreak Backdoors from Poisoned Human Feedback
Reinforcement Learning from Human Feedback (RLHF) is used to align large language models to produce helpful and harmless responses. Yet, prior work showed these models can be jailbroken by finding...
View ArticleExploring the impact of social stress on the adaptive dynamics of COVID-19:...
In the context of natural disasters, human responses inevitably intertwine with natural factors. The COVID-19 pandemic, as a significant stress factor, has brought to light profound variations among...
View ArticleDiscovering Effective Policies for Land-Use Planning
How areas of land are allocated for different uses, such as forests, urban areas, and agriculture, has a large effect on the terrestrial carbon balance, and therefore climate change. Based on available...
View ArticleOn Measuring Faithfulness or Self-consistency of Natural Language Explanations
Large language models (LLMs) can explain their predictions through post-hoc or Chain-of-Thought (CoT) explanations. But an LLM could make up reasonably sounding explanations that are unfaithful to its...
View ArticleData Contamination Quiz: A Tool to Detect and Estimate Contamination in Large...
We propose the Data Contamination Quiz (DCQ), a simple and effective approach to detect data contamination in large language models (LLMs) and estimate the amount of it. Specifically, we frame data...
View ArticleKernel-, mean- and noise-marginalised Gaussian processes for exoplanet...
Using a fully Bayesian approach, Gaussian Process regression is extended to include marginalisation over the kernel choice and kernel hyperparameters. In addition, Bayesian model comparison via the...
View ArticleGraph Neural Networks for Road Safety Modeling: Datasets and Evaluations for...
We consider the problem of traffic accident analysis on a road network based on road network connections and traffic volume. Previous works have designed various deep-learning methods using historical...
View ArticleSQLformer: Deep Auto-Regressive Query Graph Generation for Text-to-SQL...
In recent years, there has been growing interest in text-to-SQL translation, which is the task of converting natural language questions into executable SQL queries. This technology is important for its...
View ArticleDenoising Heat-inspired Diffusion with Insulators for Collision Free Motion...
Diffusion models have risen as a powerful tool in robotics due to their flexibility and multi-modality. While some of these methods effectively address complex problems, they often depend heavily on...
View ArticleLearning optimal integration of spatial and temporal information in noisy...
We investigate the boundary between chemotaxis driven by spatial estimation of gradients and chemotaxis driven by temporal estimation. While it is well known that spatial chemotaxis becomes...
View ArticleByteStack-ID: Integrated Stacked Model Leveraging Payload Byte Frequency for...
In the ever-evolving realm of network security, the swift and accurate identification of diverse attack classes within network traffic is of paramount importance. This paper introduces "ByteStack-ID,"...
View Article