Related papers: How Do Language Models Compose Functions?
Large language models (LLMs) have emerged as powerful tools for many AI problems and exhibit remarkable in-context learning (ICL) capabilities. Compositional ability, solving unseen complex tasks that combine two or more simple tasks, is an…
Does RL teach LLMs genuinely new skills, or does it merely activate existing ones? This question lies at the core of ongoing debates about the role of RL in LLM post-training. On one side, strong empirical results can be achieved with RL…
Human cognition exhibits systematic compositionality, the algebraic ability to generate infinite novel combinations from finite learned components, which is the key to understanding and reasoning about complex logic. In this work, we…
Large language models (LLMs) are very performant connectionist systems, but do they exhibit more compositionality? More importantly, is that part of why they perform so well? We present empirical analyses across four LLM families (12…
Humans can reason compositionally when presented with new tasks. Previous research shows that appropriate prompting techniques enable large language models (LLMs) to solve artificial compositional generalization tasks such as SCAN. In this…
Large Language Models (LLMs) store and retrieve vast amounts of factual knowledge acquired during pre-training. Prior research has localized and identified mechanisms behind knowledge recall; however, it has only focused on English…
Large Language Models (LLMs) are becoming very popular and are used for many different purposes, including creative tasks in the arts. However, these models sometimes have trouble with specific reasoning tasks, especially those that involve…
Large language models (LLMs) have shown an impressive ability to perform tasks believed to require thought processes. When the model does not document an explicit thought process, it becomes difficult to understand the processes occurring…
Transformer large language models (LLMs) have sparked admiration for their exceptional performance on tasks that demand intricate multi-step reasoning. Yet, these models simultaneously show failures on surprisingly trivial problems. This…
Skill composition is the ability to combine previously learned skills to solve new tasks. As neural networks acquire increasingly complex skills during their pretraining, it is not clear how successfully they can compose them. In this…
Compositionality is considered central to language abilities. As performant language systems, how do large language models (LLMs) do on compositional tasks? We evaluate adjective-noun compositionality in LLMs using two complementary setups:…
We investigate the ability of language models to perform compositional reasoning tasks where the overall solution depends on correctly composing the answers to sub-problems. We measure how often models can correctly answer all sub-problems…
Transformer-based language models are effective but complex, and understanding their inner workings and reasoning mechanisms is a significant challenge. Previous research has primarily explored how these models handle simple tasks like name…
Large Pre-trained Language Models (PLM) have become the most desirable starting point in the field of NLP, as they have become remarkably good at solving many individual tasks. Despite such success, in this paper, we argue that current…
To achieve generalized and robust natural-to-formal language conversion (N2F), large language models (LLMs) need to have strong capabilities of decomposition and composition in N2F when faced with an unfamiliar formal language and be able…
How do transformer-based large language models (LLMs) store and retrieve knowledge? We focus on the most basic form of this task -- factual recall, where the model is tasked with explicitly surfacing stored facts in prompts of form `Fact:…
Service composition remains a central challenge in building adaptive and intelligent software systems, often constrained by limited reasoning capabilities or brittle execution mechanisms. This paper explores the integration of two emerging…
Foundational models with billions of parameters which have been trained on large corpora of data have demonstrated non-trivial skills in a variety of domains. However, due to their monolithic structure, it is challenging and expensive to…
Across languages, numeral systems vary widely in how they construct and combine numbers. While humans consistently learn to navigate this diversity, large language models (LLMs) struggle with linguistic-mathematical puzzles involving…
Transformers trained on huge text corpora exhibit a remarkable set of capabilities, e.g., performing basic arithmetic. Given the inherent compositional nature of language, one can expect the model to learn to compose these capabilities,…