With new large language models (LLMs) emerging frequently, it is important to consider the potential value of model-agnostic approaches that can provide interpretability across a variety of architectures.While recent advances in LLM interpretability show promise, many rely on complex, model-specific methods with high computational costs.To address these limitations, we propose Nor-mXLogit, a novel technique for assessing the significance of individual input tokens.This method operates based on the input and output representations associated with each token.First, we demonstrate that the norm of word embeddings can be utilized as a measure of token importance.Second, we reveal a significant relationship between a token's importance and how predictive its representation is of the model's final output.Extensive analyses indicate that our approach outperforms existing gradient-based methods in terms of faithfulness and offers competitive performance compared to leading architecture-specific techniques.

Advances in dataset analysis techniques have enabled more sophisticated approaches to analyzing and characterizing training data instances, often categorizing data based on attributes such as "difficulty".In this work, we introduce RepMatch, a novel method that characterizes data through the lens of similarity.RepMatch quantifies the similarity between subsets of training instances by comparing the knowledge encoded in models trained on them, overcoming the limitations of existing analysis methods that focus solely on individual instances and are restricted to within-dataset analysis.Our framework allows for a broader evaluation, enabling similarity comparisons across arbitrary subsets of instances, supporting both dataset-to-dataset and instance-to-dataset analyses.We validate the effectiveness of Rep-Match across multiple NLP tasks, datasets, and models.Through extensive experimentation, we demonstrate that RepMatch can effectively compare datasets, identify more representative subsets of a dataset (that lead to better performance than randomly selected subsets of equivalent size), and uncover heuristics underlying the construction of some challenge datasets.

Faster-than-Nyquist (FTN) signaling is a candidate non-orthonormal transmission technique to improve the spectral efficiency (SE) of future communication systems. However, such improvements of the SE are at the cost of additional computational complexity to remove the intentionally introduced intersymbol interference. In this paper, we investigate the use of deep learning (DL) to reduce the detection complexity of FTN signaling. To eliminate the need of having a noise whitening filter at the receiver, we first present an equivalent FTN signaling model based on using a set of orthonormal basis functions and identify its operation region. Second, we propose a DL-based list sphere decoding (DL-LSD) algorithm that selects and updates the initial radius of the original LSD to guarantee a pre-defined number NLof lattice points inside the hypersphere. This is achieved by training a neural network to output an approximate initial radius that includes NLlattice points. At the testing phase, if the hypersphere has more than NLlattice points, we keep the NLclosest points to the point corresponding to the received FTN signal; however, if the hypersphere has less than NLpoints, we increase the approximate initial radius by a value that depends on the standard deviation of the distribution of the output radii from the training phase. Then, the approximate value of the log-likelihood ratio (LLR) is calculated based on the obtained NLpoints. Simulation results show that the computational complexity of the proposed DL-LSD is lower than its counterpart of the original LSD by orders of magnitude.