相关论文: Evaluating Stability of Unreflective Alignment

Federated Learning (FL), while a breakthrough in decentralized machine learning, contends with significant challenges such as limited data availability and the variability of computational resources, which can stifle the performance and…

Large language models (LLMs) increasingly serve as automated evaluators, yet they suffer from "self-preference bias": a tendency to favor their own outputs over those of other models. This bias undermines fairness and reliability in…

Counterfactual learning to rank (CLTR) has attracted extensive attention in the IR community for its ability to leverage massive logged user interaction data to train ranking models. While the CLTR models can be theoretically unbiased when…

Delays are inherent to most dynamical systems. Besides shifting the process in time, they can significantly affect their performance. For this reason, it is usually valuable to study the delay and account for it. Because they are dynamical…

Model predictive control (MPC) is a powerful control method that allows to directly include state and input constraints into the controller design. However, errors in the model, e.g., caused by unknown disturbances, can lead to constraint…

The growing scale and complexity of safety-critical control systems underscore the need to evolve current control architectures aiming for the unparalleled performances achievable through state-of-the-art optimization and machine learning…

A major concern amongst AI safety practitioners is the possibility of loss of control, whereby humans lose the ability to exert control over increasingly advanced AI systems. The range of concerns is wide, spanning current day risks to…

Human cognition, driven by complex neurochemical processes, oscillates between imagination and reality and learns to self-correct whenever such subtle drifts lead to hallucinations or unsafe associations. In recent years, LLMs have…

This paper proposes a novel method for determining the number of factors in linear factor models under stability considerations. An instability measure is proposed based on the principal angle between the estimated loading spaces obtained…

An LLM is stable if it reaches the same conclusion when asked the identical question multiple times. We find leading LLMs like gpt-4o, claude-3.5, and gemini-1.5 are unstable when providing answers to hard legal questions, even when made as…

Large language models (LLMs) demonstrate remarkable reasoning capabilities, yet their performance often deteriorates sharply in long-horizon tasks, exhibiting systematic breakdown beyond certain scales. Conventional explanations primarily…

The solution of linear inverse problems arising, for example, in signal and image processing is a challenging problem since the ill-conditioning amplifies, in the solution, the noise present in the data. Recently introduced algorithms based…

The rise of Large Language Models (LLMs) has driven progress in reasoning tasks -- from program synthesis to scientific hypothesis generation -- yet their ability to handle ranked preferences and structured algorithms in combinatorial…

AI alignment research aims to develop techniques to ensure that AI systems do not cause harm. However, every alignment technique has failure modes, which are conditions in which there is a non-negligible chance that the technique fails to…

Calibration is crucial in deep learning applications, especially in fields like healthcare and autonomous driving, where accurate confidence estimates are vital for decision-making. However, deep neural networks often suffer from…

%!TEX root = LCSS_main_max.tex The widespread adoption of nonlinear Receding Horizon Control (RHC) strategies by industry has led to more than 30 years of intense research efforts to provide stability guarantees for these methods. However,…

Randomized coordinate descent (RCD) is a popular optimization algorithm with wide applications in solving various machine learning problems, which motivates a lot of theoretical analysis on its convergence behavior. As a comparison, there…

With the rapid advancement of large language models (LLMs), the safety of LLMs has become a critical concern. Despite significant efforts in safety alignment, current LLMs remain vulnerable to jailbreaking attacks. However, the root causes…

Large language models (LLMs) are increasingly used in human-AI interaction research and practice, yet existing capability and safety benchmarks reveal little about the value priorities these systems express or how those priorities…

Computing the receding horizon optimal control of nonlinear hybrid systems is typically prohibitively slow, limiting real-time implementation. To address this challenge, we propose a layered Model Predictive Control (MPC) architecture for…