相关论文: InterPol: De-anonymizing LM Arena via Interpolated…

Standard tabular benchmarks mainly focus on the evaluation of a model's capability to interpolate values inside a data manifold, where models good at performing local statistical smoothing are rewarded. However, there exists a very large…

Membership Inference Attack (MIA) aims to determine whether a specific data sample was included in the training dataset of a target model. Traditional MIA approaches rely on shadow models to mimic target model behavior, but their…

It is commonplace to produce application-specific models by fine-tuning large pre-trained models using a small bespoke dataset. The widespread availability of foundation model checkpoints on the web poses considerable risks, including the…

Standard interpolation techniques are implicitly based on the assumption that the signal lies on a single homogeneous domain. In contrast, many naturally occurring signals lie on an inhomogeneous domain, such as brain activity associated to…

Abstraction is a successful technique in software verification, and interpolation on infeasible error paths is a successful approach to automatically detect the right level of abstraction in counterexample-guided abstraction refinement.…

Semi-supervised learning (SSL) has long been proved to be an effective technique to construct powerful models with limited labels. In the existing literature, consistency regularization-based methods, which force the perturbed samples to…

Measuring progress is fundamental to the advancement of any scientific field. As benchmarks play an increasingly central role, they also grow more susceptible to distortion. Chatbot Arena has emerged as the go-to leaderboard for ranking the…

Preference learning is critical for aligning large language models (LLMs) with human values, with the quality of preference datasets playing a crucial role in this process. While existing metrics primarily assess data quality based on…

We investigate the expressive power of deep residual neural networks idealized as continuous dynamical systems through control theory. Specifically, we consider two properties that arise from supervised learning, namely universal…

Privacy and transparency are two key foundations of trustworthy machine learning. Model explanations offer insights into a model's decisions on input data, whereas privacy is primarily concerned with protecting information about the…

Anonymization is widely treated as a practical safeguard because re-identifying anonymous records was historically costly, requiring domain expertise, tailored algorithms, and manual corroboration. We study a growing privacy risk that may…

Preference learning extends the performance of Code LLMs beyond traditional supervised fine-tuning by leveraging relative quality comparisons. In existing approaches, a set of n candidate solutions is evaluated based on test case success…

Aligning Large Language Models (LLMs) with human preferences is crucial, but standard methods like Reinforcement Learning from Human Feedback (RLHF) are often complex and unstable. In this work, we propose a new, simpler approach that…

Artificial intelligence systems are prevalent in everyday life, with use cases in retail, manufacturing, health, and many other fields. With the rise in AI adoption, associated risks have been identified, including privacy risks to the…

Imitation learning has shown success in many tasks by learning from expert demonstrations. However, most existing work relies on large-scale demonstrations from technical professionals and close monitoring of the training process. These are…

Multi-modal retrieval-augmented generation (MRAG) systems retrieve visual evidence from large image corpora to ground the responses of large multi-modal models, yet the retrieved images frequently contain human faces whose identities…

Pre-trained language models (PLMs) have demonstrated significant proficiency in solving a wide range of general natural language processing (NLP) tasks. Researchers have observed a direct correlation between the performance of these models…

Modern machine learning systems based on neural networks have shown great success in learning complex data patterns while being able to make good predictions on unseen data points. However, the limited interpretability of these systems…

As we rely on machine learning (ML) models to make more consequential decisions, the issue of ML models perpetuating or even exacerbating undesirable historical biases (e.g., gender and racial biases) has come to the fore of the public's…

As learning-to-rank models are increasingly deployed for decision-making in areas with profound life implications, the FairML community has been developing fair learning-to-rank (LTR) models. These models rely on the availability of…