相关论文: Understanding Transformer Memorization Recall Thro…

Recent developments in Language Models (LMs) have shown their effectiveness in NLP tasks, particularly in knowledge-intensive tasks. However, the mechanisms underlying knowledge storage and memory access within their parameters remain…

Recent research suggests that the feed-forward module within Transformers can be viewed as a collection of key-value memories, where the keys learn to capture specific patterns from the input based on the training examples. The values then…

Transformer-based Neural Language Models achieve state-of-the-art performance on various natural language processing tasks. However, an open question is the extent to which these models rely on word-order/syntactic or word…

Idioms present a unique challenge for language models due to their non-compositional figurative interpretations, which often strongly diverge from the idiom's literal interpretation. In this paper, we employ causal tracing to systematically…

Pretrained language models (PLMs) are today the primary model for natural language processing. Despite their impressive downstream performance, it can be difficult to apply PLMs to new languages, a barrier to making their capabilities…

Large Language Models (LLMs), characterized by being trained on broad amounts of data in a self-supervised manner, have shown impressive performance across a wide range of tasks. Indeed, their generative abilities have aroused interest on…

Understanding what knowledge is implicitly encoded in deep learning models is essential for improving the interpretability of AI systems. This paper examines common methods to explain the knowledge encoded in word embeddings, which are core…

In parallel to their overwhelming success across NLP tasks, language ability of deep Transformer networks, pretrained via language modeling (LM) objectives has undergone extensive scrutiny. While probing revealed that these models encode a…

With the recent success and popularity of pre-trained language models (LMs) in natural language processing, there has been a rise in efforts to understand their inner workings. In line with such interest, we propose a novel method that…

Can we localize the weights and mechanisms used by a language model to memorize and recite entire paragraphs of its training data? In this paper, we show that while memorization is spread across multiple layers and model components,…

Large language models (LLMs) achieve strong performance across a wide range of tasks, but remain frozen after pretraining until subsequent updates. Many real-world applications require timely, domain-specific information, motivating the…

Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Large Language Models (LLMs) struggle to perform such reasoning consistently. Here we propose an approach to pinpoint and rectify…

The remarkable success of large language models (LLMs) stems from their ability to consolidate vast amounts of knowledge into the memory during pre-training and to retrieve it from the memory during inference, enabling advanced capabilities…

We study how large language models (LLMs) reason about memorized knowledge through simple binary relations such as equality ($=$), inequality ($<$), and inclusion ($\subset$). Unlike in-context reasoning, the axioms (e.g., $a < b, b < c$)…

Pretrained language models (PLMs) have produced substantial improvements in discourse-aware neural machine translation (NMT), for example, improved coherence in spoken language translation. However, the underlying reasons for their strong…

Prior research has explored the ability of computational models to predict a word semantic fit with a given predicate. While much work has been devoted to modeling the typicality relation between verbs and arguments in isolation, in this…

Large language models (LLMs) often benefit from intermediate steps of reasoning to generate answers to complex problems. When these intermediate steps of reasoning are used to monitor the activity of the model, it is essential that this…

Phrases play an important role in natural language understanding and machine translation (Sag et al., 2002; Villavicencio et al., 2005). However, it is difficult to integrate them into current neural machine translation (NMT) which reads…

Pretrained transformer-based Language Models (LMs) are well-known for their ability to achieve significant improvement on NLP tasks, but their black-box nature, which leads to a lack of interpretability, has been a major concern. My…

Memory is the process of encoding, storing, and retrieving information, allowing humans to retain experiences, knowledge, skills, and facts over time, and serving as the foundation for growth and effective interaction with the world. It…