Know-MRI: A Knowledge Mechanisms Revealer&Interpreter for Large Language Models

As large language models (LLMs) continue to advance, there is a growing urgency to enhance the interpretability of their internal knowledge mechanisms. Consequently, many interpretation methods have emerged, aiming to unravel the knowledge mechanisms of LLMs from various perspectives. However, current interpretation methods differ in input data formats and interpreting outputs. The tools integrating these methods are only capable of supporting tasks with specific inputs, significantly constraining their practical applications. To address these challenges, we present an open-source Knowledge Mechanisms Revealer&Interpreter (Know-MRI) designed to analyze the knowledge mechanisms within LLMs systematically. Specifically, we have developed an extensible core module that can automatically match different input data with interpretation methods and consolidate the interpreting outputs. It enables users to freely choose appropriate interpretation methods based on the inputs, making it easier to comprehensively diagnose the model's internal knowledge mechanisms from multiple perspectives. Our code is available at https://github.com/nlpkeg/Know-MRI. We also provide a demonstration video on https://youtu.be/NVWZABJ43Bs.

Spurious Privacy Leakage in Neural Networks

Neural networks are vulnerable to privacy attacks aimed at stealing sensitive data. The risks can be amplified in a real-world scenario, particularly when models are trained on limited and biased data. In this work, we investigate the impact of spurious correlation bias on privacy vulnerability. We introduce \emph{spurious privacy leakage}, a phenomenon where spurious groups are significantly more vulnerable to privacy attacks than non-spurious groups. We further show that group privacy disparity increases in tasks with simpler objectives (e.g. fewer classes) due to the persistence of spurious features. Surprisingly, we find that reducing spurious correlation using spurious robust methods does not mitigate spurious privacy leakage. This leads us to introduce a perspective on privacy disparity based on memorization, where mitigating spurious correlation does not mitigate the memorization of spurious data, and therefore, neither the privacy level. Lastly, we compare the privacy of different model architectures trained with spurious data, demonstrating that, contrary to prior works, architectural choice can affect privacy outcomes.

NeuroTrails: Training with Dynamic Sparse Heads as the Key to Effective Ensembling

Model ensembles have long been a cornerstone for improving generalization and robustness in deep learning. However, their effectiveness often comes at the cost of substantial computational overhead. To address this issue, state-of-the-art methods aim to replicate ensemble-class performance without requiring multiple independently trained networks. Unfortunately, these algorithms often still demand considerable compute at inference. In response to these limitations, we introduce $\textbf{NeuroTrails}$, a sparse multi-head architecture with dynamically evolving topology. This unexplored model-agnostic training paradigm improves ensemble performance while reducing the required resources. We analyze the underlying reason for its effectiveness and observe that the various neural trails induced by dynamic sparsity attain a $\textit{Goldilocks zone}$ of prediction diversity. NeuroTrails displays efficacy with convolutional and transformer-based architectures on computer vision and language tasks. Experiments on ResNet-50/ImageNet, LLaMA-350M/C4, among many others, demonstrate increased accuracy and stronger robustness in zero-shot generalization, while requiring significantly fewer parameters.

Beyond Instruction Following: Evaluating Rule Following of Large Language Models

Although Large Language Models (LLMs) have demonstrated strong instruction-following ability to be helpful, they are further supposed to be controlled and guided by rules in real-world scenarios to be safe, and accurate in responses. This demands the possession of rule-following capability of LLMs. However, few works have made a clear evaluation of the rule-following capability of LLMs. Previous studies that try to evaluate the rule-following capability of LLMs fail to distinguish the rule-following scenarios from the instruction-following scenarios. Therefore, this paper first makes a clarification of the concept of rule-following, and curates a comprehensive benchmark, RuleBench, to evaluate a diversified range of rule-following abilities. Our experimental results on a variety of LLMs show that they are still limited in following rules. Our further analysis provides insights into the improvements for LLMs toward a better rule-following intelligent agent. The data and code can be found at: https://anonymous.4open.science/r/llm-rule-following-B3E3/

Training, Architecture, and Prior for Deterministic Uncertainty Methods

Accurate and efficient uncertainty estimation is crucial to build reliable Machine Learning (ML) models capable to provide calibrated uncertainty estimates, generalize and detect Out-Of-Distribution (OOD) datasets. To this end, Deterministic Uncertainty Methods (DUMs) is a promising model family capable to perform uncertainty estimation in a single forward pass. This work investigates important design choices in DUMs: (1) we show that training schemes decoupling the core architecture and the uncertainty head schemes can significantly improve uncertainty performances. (2) we demonstrate that the core architecture expressiveness is crucial for uncertainty performance and that additional architecture constraints to avoid feature collapse can deteriorate the trade-off between OOD generalization and detection. (3) Contrary to other Bayesian models, we show that the prior defined by DUMs do not have a strong effect on the final performances.