相关论文: Linear Correlation in LM's Compositional Generaliz…

Recently, there has been an explosion of large language models created through fine-tuning with data from larger models. These small models able to produce outputs that appear qualitatively similar to significantly larger models. However,…

Hallucination is a central failure mode in large language models (LLMs). We focus on hallucinations of answers to questions like: "Which instrument did Glenn Gould play?", but we ask these questions for synthetic entities that are unknown…

Pre-trained language models (LMs) store knowledge in their parameters and can generate informative responses when used in conversational systems. However, LMs suffer from the problem of "hallucination:" they may generate plausible-looking…

Recent advancements in large language models (LLMs) have enhanced natural-language reasoning. However, their limited parametric memory and susceptibility to hallucination present persistent challenges for tasks requiring accurate,…

Compositional generalization is the ability of a model to generalize to complex, previously unseen types of combinations of entities from just having seen the primitives. This type of generalization is particularly relevant to the semantic…

In the age of misinformation, hallucination - the tendency of Large Language Models (LLMs) to generate non-factual or unfaithful responses - represents the main risk for their global utility. Despite LLMs becoming increasingly multilingual,…

Large Language Models have rapidly advanced in their ability to interpret and generate natural language. In enterprise settings, they are frequently augmented with closed-source domain knowledge to deliver more contextually informed…

Rote learning is a memorization technique based on repetition. Many researchers argue that rote learning hinders generalization because it encourages verbatim memorization rather than deeper understanding. This concern extends even to…

Neural network models often generalize poorly to mismatched domains or distributions. In NLP, this issue arises in particular when models are expected to generalize compositionally, that is, to novel combinations of familiar words and…

Despite their impressive capabilities, large language models (LLMs) are prone to hallucinations, i.e., generating content that deviates from facts seen during pretraining. We propose a simple decoding strategy for reducing hallucinations…

The emergence of large language models (LLMs) has marked a significant breakthrough in natural language processing (NLP), fueling a paradigm shift in information acquisition. Nevertheless, LLMs are prone to hallucination, generating…

Large Language Models (LLMs) have made significant advances in natural language processing, but their underlying mechanisms are often misunderstood. Despite exhibiting coherent answers and apparent reasoning behaviors, LLMs rely on…

Multilingual large language models (LLMs) seem to generalize somewhat across languages. We hypothesize this is a result of implicit vector space alignment. Evaluating such alignment, we see that larger models exhibit very high-quality…

Large language models (LLMs) have demonstrated remarkable performance, particularly in multilingual contexts. While recent studies suggest that LLMs can transfer skills learned in one language to others, the internal mechanisms behind this…

Scaling large language models (LLMs) leads to an emergent capacity to learn in-context from example demonstrations. Despite progress, theoretical understanding of this phenomenon remains limited. We argue that in-context learning relies on…

Metacognition--the capacity to monitor and evaluate one's own knowledge and performance--is foundational to human decision-making, learning, and communication. As large language models (LLMs) become increasingly embedded in both high-stakes…

Grounded language models use external sources of information, such as knowledge graphs, to meet some of the general challenges associated with pre-training. By extending previous work on compositional generalization in semantic parsing, we…

Large Language Models (LLMs) are capable of displaying a wide range of abilities that are not directly connected with the task for which they are trained: predicting the next words of human-written texts. In this article, I review recent…

Recent advances in Large Language Models (LLMs) have demonstrated strong capabilities in tasks such as code and mathematics. However, their potential to internalize structured spatial knowledge remains underexplored. This study investigates…

What is the interplay between semantic representations learned by language models (LM) from surface form alone to those learned from more grounded evidence? We study this question for a scenario where part of the input comes from a…