相关论文: Partial-input baselines show that NLI models can i…

Compositional Natural Language Inference has been explored to assess the true abilities of neural models to perform NLI. Yet, current evaluations assume models to have full access to all primitive inferences in advance, in contrast to…

Pretrained language models have achieved a new state of the art on many NLP tasks, but there are still many open questions about how and why they work so well. We investigate the contextualization of words in BERT. We quantify the amount of…

Language models can achieve high accuracy on natural language tasks such as NLI, but performance suffers on manually created adversarial examples. We investigate the performance of a language model trained on the Stanford Natural Language…

This open access book provides a comprehensive overview of the state of the art in research and applications of Foundation Models and is intended for readers familiar with basic Natural Language Processing (NLP) concepts. Over the recent…

Large language models (LLMs) trained on huge corpora of text datasets demonstrate intriguing capabilities, achieving state-of-the-art performance on tasks they were not explicitly trained for. The precise nature of LLM capabilities is often…

Natural Language Processing systems are heavily dependent on the availability of annotated data to train practical models. Primarily, models are trained on English datasets. In recent times, significant advances have been made in…

In this paper, we study the response of large models from the BERT family to incoherent inputs that should confuse any model that claims to understand natural language. We define simple heuristics to construct such examples. Our experiments…

Anomaly detection aims to identify observations that deviate from expected behavior. Because anomalous events are inherently sparse, most frameworks are trained exclusively on normal data to learn a single reference model of normality. This…

Large language models (LMs) are able to in-context learn -- perform a new task via inference alone by conditioning on a few input-label pairs (demonstrations) and making predictions for new inputs. However, there has been little…

Though state-of-the-art sentence representation models can perform tasks requiring significant knowledge of grammar, it is an open question how best to evaluate their grammatical knowledge. We explore five experimental methods inspired by…

Incremental processing allows interactive systems to respond based on partial inputs, which is a desirable property e.g. in dialogue agents. The currently popular Transformer architecture inherently processes sequences as a whole,…

In-context learning (ICL) derives its power from enabling Large Language Models to adapt to new tasks via prompt-based reasoning alone, entirely bypassing the need for parameter updates. Existing theories primarily study ICL in single-task…

Many NLP models gain performance by having access to a knowledge base. A lot of research has been devoted to devising and improving the way the knowledge base is accessed and incorporated into the model, resulting in a number of mechanisms…

Natural language inference (NLI) is critical for complex decision-making in biomedical domain. One key question, for example, is whether a given biomedical mechanism is supported by experimental evidence. This can be seen as an NLI problem…

In-context learning, where pre-trained language models learn to perform tasks from task examples and instructions in their contexts, has attracted much attention in the NLP community. However, the ability of in-context learning is not fully…

Transformers have emerged as the dominant architecture in the field of deep learning, with a broad range of applications and remarkable in-context learning (ICL) capabilities. While not yet fully understood, ICL has already proved to be an…

Language Models (LMs) can perform new tasks by adapting to a few in-context examples. For humans, explanations that connect examples to task principles can improve learning. We therefore investigate whether explanations of few-shot examples…

We propose a principle for exploring context in machine learning models. Starting with a simple assumption that each observation may or may not depend on its context, a conditional probability distribution is decomposed into two parts:…

Standard imitation learning can fail when the expert demonstrators have different sensory inputs than the imitating agent. This is because partial observability gives rise to hidden confounders in the causal graph. In previous work, to work…

Adapting to latent confounded shift remains a core challenge in modern AI. This setting is driven by hidden variables that induce spurious correlations between inputs and outputs during training, leading models to rely on non-causal…