Related papers: The Ramon Llull's Thinking Machine for Automated I…
Reasoning is a fundamental aspect of human intelligence that plays a crucial role in activities such as problem solving, decision making, and critical thinking. In recent years, large language models (LLMs) have made significant progress in…
Reasoning about failures is crucial for building reliable and trustworthy robotic systems. Prior approaches either treat failure reasoning as a closed-set classification problem or assume access to ample human annotations. Failures in the…
In recent years, large language models (LLMs) and generative AI have revolutionized natural language processing (NLP), offering unprecedented capabilities in education. This chapter explores the transformative potential of LLMs in automated…
LLM-based agents offer new potential to accelerate science and reshape research work. However, the quality of researcher contributions can vary significantly depending on human ability to steer agent behaviors. How can we best use these…
The scientific research paradigm is undergoing a profound transformation owing to the development of Artificial Intelligence (AI). Recent works demonstrate that various AI-assisted research methods can largely improve research efficiency by…
The Retrieval-Augmented Language Model (RALM) has shown remarkable performance on knowledge-intensive tasks by incorporating external knowledge during inference, which mitigates the factual hallucinations inherited in large language models…
Despite their linguistic competence, Large Language Models (LLMs) often struggle to reason reliably and flexibly. To identify these shortcomings, we introduce the Non-Linear Reasoning (NLR) dataset, a collection of 55 unique, hand-designed…
Retrieval-Augmented Generation (RAG) effectively enhances Large Language Models (LLMs) by incorporating retrieved external knowledge into the generation process. Reasoning models improve LLM performance in multi-hop QA tasks, which require…
Thanks to their generative capabilities, large language models (LLMs) have become an invaluable tool for creative processes. These models have the capacity to produce hundreds and thousands of visual and textual outputs, offering abundant…
Large language models (LLMs) excel in complex tasks through advanced prompting techniques like Chain-of-Thought (CoT) and Tree-of-Thought (ToT), but their reliance on manually crafted, task-specific prompts limits adaptability and…
The Abstraction Reasoning Corpus (ARC) is a visual analogical reasoning test designed for humans and machines (Chollet, 2019). We compared human and large language model (LLM) performance on a new child-friendly set of ARC items. Results…
Large language models (LLMs) have demonstrated strong performance in a wide-range of language tasks without requiring task-specific fine-tuning. However, they remain prone to hallucinations and inconsistencies, and often struggle with…
In AI-assisted decision-making, humans often passively review AI's suggestion and decide whether to accept or reject it as a whole. In such a paradigm, humans are found to rarely trigger analytical thinking and face difficulties in…
Multimodal large language models (MLLMs) have achieved impressive progress on vision language benchmarks, yet their capacity for visual cognitive and visuospatial reasoning remains less understood. We introduce "Mind's Eye", a…
Retrieval-Augmented Generation (RAG) has emerged as a powerful framework to overcome the knowledge limitations of Large Language Models (LLMs) by integrating external retrieval with language generation. While early RAG systems based on…
Computational argumentation has become an essential tool in various domains, including law, public policy, and artificial intelligence. It is an emerging research field in natural language processing that attracts increasing attention.…
Large language models' reasoning abilities benefit from methods that organize their thought processes, such as chain-of-thought prompting, which employs a sequential structure to guide the reasoning process step-by-step. However, existing…
For human cognitive process, spatial reasoning and perception are closely entangled, yet the nature of this interplay remains underexplored in the evaluation of multimodal large language models (MLLMs). While recent MLLM advancements show…
Large Language Models (LLMs) have demonstrated impressive real-world utility, exemplifying artificial useful intelligence (AUI). However, their ability to reason adaptively and robustly -- the hallmarks of artificial general intelligence…
The Abstraction and Reasoning Corpus (ARC) evaluates general reasoning capabilities that are difficult for both machine learning models and combinatorial search methods. We propose a neuro-symbolic approach that combines a transformer for…