Related papers: Designing and Interpreting Probes with Control Tas…

Word embeddings are trained to predict word cooccurrence statistics, which leads them to possess different lexical properties (syntactic, semantic, etc.) depending on the notion of context defined at training time. These properties manifest…

Contextual word representations derived from large-scale neural language models are successful across a diverse set of NLP tasks, suggesting that they encode useful and transferable features of language. To shed light on the linguistic…

Pre-training a language model and then fine-tuning it for downstream tasks has demonstrated state-of-the-art results for various NLP tasks. Pre-training is usually independent of the downstream task, and previous works have shown that this…

Understanding how linguistic structures are encoded in contextualized embedding could help explain their impressive performance across NLP@. Existing approaches for probing them usually call for training classifiers and use the accuracy,…

Recent work has shown that language models (LMs) have strong multi-step (i.e., procedural) reasoning capabilities. However, it is unclear whether LMs perform these tasks by cheating with answers memorized from pretraining corpus, or, via a…

With the rapid advancement of large language models (LLMs) for handling complex language tasks, an increasing number of studies are employing LLMs as agents to emulate the sequential decision-making processes of humans often represented as…

Pre-trained language models have achieved huge improvement on many NLP tasks. However, these methods are usually designed for written text, so they do not consider the properties of spoken language. Therefore, this paper aims at…

Many efforts have been made to facilitate natural language processing tasks with pre-trained language models (LMs), and brought significant improvements to various applications. To fully leverage the nearly unlimited corpora and capture…

Distributed representations of words have been shown to capture lexical semantics, as demonstrated by their effectiveness in word similarity and analogical relation tasks. But, these tasks only evaluate lexical semantics indirectly. In this…

Probes are small networks that predict properties of underlying data from embeddings, and they provide a targeted, effective way to illuminate the information contained in embeddings. While analysis through the use of probes has become…

Language models trained on large text corpora encode rich distributional information about real-world environments and action sequences. This information plays a crucial role in current approaches to language processing tasks like question…

Language models (LLMs) offer potential as a source of knowledge for agents that need to acquire new task competencies within a performance environment. We describe efforts toward a novel agent capability that can construct cues (or…

To measure how well pretrained representations encode some linguistic property, it is common to use accuracy of a probe, i.e. a classifier trained to predict the property from the representations. Despite widespread adoption of probes,…

Many self-supervised speech models (S3Ms) have been introduced over the last few years, improving performance and data efficiency on various speech tasks. However, these empirical successes alone do not give a complete picture of what is…

Despite widespread success in language understanding and generation, large language models (LLMs) exhibit unclear and often inconsistent behavior when faced with tasks that require probabilistic reasoning. In this work, we present the first…

Linguistic information is encoded at varying timescales (subwords, phrases, etc.) and communicative levels, such as syntax and semantics. Contextualized embeddings have analogously been found to capture these phenomena at distinctive layers…

Fine-tuning pre-trained contextualized embedding models has become an integral part of the NLP pipeline. At the same time, probing has emerged as a way to investigate the linguistic knowledge captured by pre-trained models. Very little is,…

The ability to identify and control different kinds of linguistic information encoded in vector representations of words has many use cases, especially for explainability and bias removal. This is usually done via a set of simple…

The success of pre-trained contextualized representations has prompted researchers to analyze them for the presence of linguistic information. Indeed, it is natural to assume that these pre-trained representations do encode some level of…

We investigate the performance of large language models on repetitive deterministic prediction tasks and study how the sequence accuracy rate scales with output length. Each such task involves repeating the same operation n times. Examples…