Related papers: Where Does Authorship Signal Emerge in Encoder-Bas…

To learn semantic attributes, existing methods typically train one discriminative model for each word in a vocabulary of nameable properties. However, this "one model per word" assumption is problematic: while a word might have a precise…

In recent years, neural networks have demonstrated their remarkable ability to discern intricate patterns and relationships from raw data. However, understanding the inner workings of these black box models remains challenging, yet crucial…

Large language models (LLMs) can convincingly imitate human writing styles, yet it remains unclear how much stylistic information is encoded in embeddings from any language model and retained after LLM rewriting. We investigate these…

Sparse coding in learned dictionaries has been established as a successful approach for signal denoising, source separation and solving inverse problems in general. A dictionary learning method adapts an initial dictionary to a particular…

Faithful evaluation of language model capabilities is crucial for deriving actionable insights that can inform model development. However, rigorous causal evaluations in this domain face significant methodological challenges, including…

Despite their strong performance on many tasks, pre-trained language models have been shown to struggle on out-of-distribution compositional generalization. Meanwhile, recent work has shown considerable improvements on many NLP tasks from…

Machine learning and deep learning models are pivotal in educational contexts, particularly in predicting student success. Despite their widespread application, a significant gap persists in comprehending the factors influencing these…

Recent advancements in Large Speech-Language Models have significantly bridged the gap between acoustic signals and linguistic understanding. However, a persistent performance disparity remains in speech-based input tasks compared to direct…

The rapid developments of various machine learning models and their deployments in several applications has led to discussions around the importance of looking beyond the accuracies of these models. Fairness of such models is one such…

While most successful approaches for machine reading comprehension rely on single training objective, it is assumed that the encoder layer can learn great representation through the loss function we define in the predict layer, which is…

Diffusion models do not recover semantic structure uniformly over time. Instead, samples transition from semantic ambiguity to class commitment within a narrow regime. Recent theoretical work attributes this transition to dynamical…

In this paper we propose a general framework for learning distributed representations of attributes: characteristics of text whose representations can be jointly learned with word embeddings. Attributes can correspond to document indicators…

Predicting a label correctly does not necessarily require representing the operation that produces it. Transformer representations are known to carry label-level information, but whether they encode semantic operations producing those…

We study the problem of entropy calibration, which asks whether a language model's entropy over generations matches its log loss on human text. Past work found that models are miscalibrated, with entropy per step increasing as generations…

We analyze reasoning in language models during task-specific fine-tuning and draws parallel between reasoning tokens--intermediate steps generated while solving problem and the human working memory. Drawing from cognitive science, we align…

Abstractive neural summarization models have seen great improvements in recent years, as shown by ROUGE scores of the generated summaries. But despite these improved metrics, there is limited understanding of the strategies different models…

Automated grading systems can efficiently score short-answer responses, yet they often fail to indicate when a grading decision is uncertain or potentially contentious. We introduce semantic entropy, a measure of variability across multiple…

Well-established automatic analyses of texts mainly consider frequencies of linguistic units, e.g. letters, words and bigrams, while methods based on co-occurrence networks consider the structure of texts regardless of the nodes label (i.e.…

Concepts and methods of complex networks can be used to analyse texts at their different complexity levels. Examples of natural language processing (NLP) tasks studied via topological analysis of networks are keyword identification,…

Model interpretability methods are often used to explain NLP model decisions on tasks such as text classification, where the output space is relatively small. However, when applied to language generation, where the output space often…