Related papers: Finite Sentence-Interface Control for Learning Bou…

Self-supervised model pre-training has recently garnered significant interest, but relatively few efforts have explored using additional resources in fine-tuning these models. We demonstrate how universal phoneset acoustic models can…

While large models achieve impressive results, their learning dynamics are far from understood. Many domains of interest, such as natural language syntax, coding languages, arithmetic problems, are captured by context-free grammars (CFGs).…

Simultaneous neural machine translation(SNMT) models start emitting the target sequence before they have processed the source sequence. The recent adaptive policies for SNMT use monotonic attention to perform read/write decisions based on…

We introduce a novel model-theoretic framework inspired from graph modification and based on the interplay between model theory and algorithmic graph minors. The core of our framework is a new compound logic operating with two types of…

The problem of identifying a probabilistic context free grammar has two aspects: the first is determining the grammar's topology (the rules of the grammar) and the second is estimating probabilistic weights for each rule. Given the hardness…

Fine-tuning-based unlearning methods prevail for preventing targeted harmful, sensitive, or copyrighted information within large language models while preserving overall capabilities. However, the true effectiveness of these methods is…

Zero-shot intent classification is a vital and challenging task in dialogue systems, which aims to deal with numerous fast-emerging unacquainted intents without annotated training data. To obtain more satisfactory performance, the crucial…

Prompt learning has become the most effective paradigm for adapting large pre-trained vision-language models (VLMs) to downstream tasks. Recently, unsupervised prompt tuning methods, such as UPL and POUF, directly leverage pseudo-labels as…

Embeddings play an important role in end-to-end solutions for multi-modal language processing problems. Although there has been some effort to understand the properties of single-modality embedding spaces, particularly that of text, their…

Counterfactual explanations for machine learning models are used to find minimal interventions to the feature values such that the model changes the prediction to a different output or a target output. A valid counterfactual explanation…

Language models often generate reasoning before giving a final answer, but the visible answer does not reveal when the model's answer preference became stable. We study this question through a narrow computable object: \emph{finite-answer…

As a step toward better document-level understanding, we explore classification of a sequence of sentences into their corresponding categories, a task that requires understanding sentences in context of the document. Recent successful…

We present a trainable model for identifying sentence boundaries in raw text. Given a corpus annotated with sentence boundaries, our model learns to classify each occurrence of ., ?, and ! as either a valid or invalid sentence boundary. The…

Large language models (LLMs) are powerful tools that have found applications beyond human-machine interfaces and chatbots. In particular, their ability to generate reasoning traces motivated their use in many prediction tasks like math…

Interpreting the learned features of vision models has posed a longstanding challenge in the field of machine learning. To address this issue, we propose a novel method that leverages the capabilities of language models to interpret the…

Existing approaches to lifelong language learning rely on plenty of labeled data for learning a new task, which is hard to obtain in most real scenarios. Considering that humans can continually learn new tasks from a handful of examples, we…

Grounded text generation, encompassing tasks such as long-form question-answering and summarization, necessitates both content selection and content consolidation. Current end-to-end methods are difficult to control and interpret due to…

Through prompting, large-scale pre-trained models have become more expressive and powerful, gaining significant attention in recent years. Though these big models have zero-shot capabilities, in general, labeled data are still required to…

A neural population responding to multiple appearances of a single object defines a manifold in the neural response space. The ability to classify such manifolds is of interest, as object recognition and other computational tasks require a…

Fine-grained entity typing is the task of assigning fine-grained semantic types to entity mentions. We propose a neural architecture which learns a distributional semantic representation that leverages a greater amount of semantic context…