Related papers: Under the Hood: Using Diagnostic Classifiers to In…

Neural networks for computer vision extract uninterpretable features despite achieving high accuracy on benchmarks. In contrast, humans can explain their predictions using succinct and intuitive descriptions. To incorporate explainability…

Label noise will degenerate the performance of deep learning algorithms because deep neural networks easily overfit label errors. Let X and Y denote the instance and clean label, respectively. When Y is a cause of X, according to which many…

We address the problem of inferring a speaker's level of certainty based on prosodic information in the speech signal, which has application in speech-based dialogue systems. We show that using phrase-level prosodic features centered around…

Autoregressive language models achieve remarkable performance, yet a unified theory explaining their internal mechanisms, how training shapes representations, and why these representations support complex behavior remains incomplete. We…

Neural language models learn word representations, or embeddings, that capture rich linguistic and conceptual information. Here we investigate the embeddings learned by neural machine translation models, a recently-developed class of neural…

Large Language Models (LLMs) increasingly produce natural language explanations alongside their predictions, yet it remains unclear whether these explanations reference predictive cues present in the input text. In this work, we present an…

We find that the way we choose to represent data labels can have a profound effect on the quality of trained models. For example, training an image classifier to regress audio labels rather than traditional categorical probabilities…

We analyze the ability of pre-trained language models to transfer knowledge among datasets annotated with different type systems and to generalize beyond the domain and dataset they were trained on. We create a meta task, over multiple…

Extensive research has recently shown that recurrent neural language models are able to process a wide range of grammatical phenomena. How these models are able to perform these remarkable feats so well, however, is still an open question.…

Numeracy is the ability to understand and work with numbers. It is a necessary skill for composing and understanding documents in clinical, scientific, and other technical domains. In this paper, we explore different strategies for…

The use of neural language models to model human behavior has met with mixed success. While some work has found that the surprisal estimates from these models can be used to predict a wide range of human neural and behavioral responses,…

The rapid development of deep natural language processing (NLP) models for text classification has led to an urgent need for a unified understanding of these models proposed individually. Existing methods cannot meet the need for…

Deep learning sequence models have led to a marked increase in performance for a range of Natural Language Processing tasks, but it remains an open question whether they are able to induce proper hierarchical generalizations for…

Overfitting is a phenomenon that occurs when a machine learning model is trained for too long and focused too much on the exact fitness of the training samples to the provided training labels and cannot keep track of the predictive rules…

Despite the increasing prevalence of large language models (LLMs), we still have a limited understanding of how their representational spaces are structured. This limits our ability to interpret how and what they learn or relate them to…

While Large Language Models (LLMs) are increasingly deployed for table-related tasks, the internal mechanisms enabling them to process linearized two-dimensional structured tables remain opaque. In this work, we investigate the process of…

Representational spaces learned via language modeling are fundamental to Natural Language Processing (NLP), however there has been limited understanding regarding how and when during training various types of linguistic information emerge…

The adoption of machine learning in high-stakes applications such as healthcare and law has lagged in part because predictions are not accompanied by explanations comprehensible to the domain user, who often holds the ultimate…

Language confusion -- where large language models (LLMs) generate unintended languages against the user's need -- remains a critical challenge, especially for English-centric models. We present the first mechanistic interpretability (MI)…

Despite alarm over the reliance of machine learning systems on so-called spurious patterns, the term lacks coherent meaning in standard statistical frameworks. However, the language of causality offers clarity: spurious associations are due…