相关论文: Optimizing Spectral Learning for Parsing

Latent variable models are an elegant framework for capturing rich probabilistic dependencies in many applications. However, current approaches typically parametrize these models using conditional probability tables, and learning relies…

In order to find hyperparameters for a machine learning model, algorithms such as grid search or random search are used over the space of possible values of the models hyperparameters. These search algorithms opt the solution that minimizes…

We analyse preference inference, through consistency, for general preference languages based on lexicographic models. We identify a property, which we call strong compositionality, that applies for many natural kinds of preference…

Hyperparameter optimization is a crucial problem in Evolutionary Computation. In fact, the values of the hyperparameters directly impact the trajectory taken by the optimization process, and their choice requires extensive reasoning by…

Advancements in Large Language Models (LLMs) have significantly enhanced instruction-following capabilities. However, most Instruction Fine-Tuning (IFT) datasets are predominantly in English, limiting model performance in other languages.…

We propose a large margin criterion for training neural language models. Conventionally, neural language models are trained by minimizing perplexity (PPL) on grammatical sentences. However, we demonstrate that PPL may not be the best metric…

Detecting fine-grained differences in content conveyed in different languages matters for cross-lingual NLP and multilingual corpora analysis, but it is a challenging machine learning problem since annotation is expensive and hard to scale.…

While Retrieval-Augmented Generation (RAG) systems enhance Large Language Models (LLMs) by incorporating external knowledge, they still face persistent challenges in retrieval inefficiency and the inability of LLMs to filter out irrelevant…

Fine-tuning large language models (LLMs) for downstream tasks has become increasingly crucial due to their widespread use and the growing availability of open-source models. However, the high memory costs associated with fine-tuning remain…

Spectral Graph Neural Networks (SGNNs) have achieved remarkable performance in tasks such as node classification due to their ability to learn flexible filters. Typically, these filters are learned under the supervision of downstream tasks,…

Aligning Large Language Models (LLMs) with general human preferences has been proved crucial in improving the interaction quality between LLMs and human. However, human values are inherently diverse among different individuals, making it…

Collaborative learning through latent shared feature representations enables heterogeneous clients to train personalized models with improved performance and reduced sample complexity. Despite empirical success and extensive study, the…

We investigate an advantage for information processing of ordering a set of states over making a global quantum processing with a fixed number of copies of coherent states. Suppose Alice has $N$ copies of one of two quantum states…

Supervised fine-tuning (SFT) is crucial for adapting Large Language Models (LLMs) to specific tasks. In this work, we demonstrate that the order of training data can lead to significant training imbalances, potentially resulting in…

Despite recent advances in Language Reasoning Models (LRMs), most research focuses solely on English, even though many models are pretrained on multilingual data. In this work, we investigate: Is English the most token-efficient language…

This work presents a systematic theoretical and empirical comparison of the major algorithms that have been proposed for learning Harmonic and Optimality Theory grammars (HG and OT, respectively). By comparing learning algorithms, we are…

Large language models (LLMs) have revolutionized various domains but still struggle with non-Latin scripts and low-resource languages. This paper addresses the critical challenge of improving multilingual performance without extensive…

We present Neural Spectral Methods, a technique to solve parametric Partial Differential Equations (PDEs), grounded in classical spectral methods. Our method uses orthogonal bases to learn PDE solutions as mappings between spectral…

In many jurisdictions, the excessive workload of courts leads to high delays. Suitable predictive AI models can assist legal professionals in their work, and thus enhance and speed up the process. So far, Legal Judgment Prediction (LJP)…

This paper deals the combination of nonlinear predictive models with classical LPCC parameterization for speaker recognition. It is shown that the combination of both a measure defined over LPCC coefficients and a measure defined over…