Related papers: LECTOR: Joint Optimization of Scientific Reasoning…
Visual instructions for long-horizon tasks are crucial as they intuitively clarify complex concepts and enhance retention across extended steps. Directly generating a series of images using text-to-image models without considering the…
Undergraduate students of artificial intelligence often struggle with representing knowledge as logical sentences. This is a skill that seems to require extensive practice to obtain, suggesting a teaching strategy that involves the…
Semantic parsing is the task of producing structured meaning representations for natural language sentences. Recent research has pointed out that the commonly-used sequence-to-sequence (seq2seq) semantic parsers struggle to generalize…
Intuitive learning is crucial for developing deep conceptual understanding, especially in STEM education, where students often struggle with abstract and interconnected concepts. Automatic question generation has become an effective…
Scientific paper generation requires document-level planning and factual grounding, but current large language models, despite their strong local fluency, often fail in global structure, input coverage, and citation consistency. We present…
Retrieval-Augmented Generation (RAG) has emerged as a dominant paradigm for mitigating hallucinations in Large Language Models (LLMs) by incorporating external knowledge. Nevertheless, effectively integrating and interpreting key evidence…
The proliferation of scientific literature presents an increasingly significant challenge for researchers. While Large Language Models (LLMs) offer promise, existing tools often provide verbose summaries that risk replacing, rather than…
The increasing amount of published scholarly articles, exceeding 2.5 million yearly, raises the challenge for researchers in following scientific progress. Integrating the contributions from scholarly articles into a novel type of cognitive…
Chain-of-thought (CoT) reasoning boosts large language models' (LLMs) performance on complex tasks but faces two key limitations: a lack of reliability when solely relying on LLM-generated reasoning chains and lower reasoning performance…
The powerful reasoning capabilities of Large Language Models (LLMs) in mathematics and coding, combined with their ability to automate complex tasks through agentic frameworks, present unprecedented opportunities for accelerating scientific…
Large language models (LLMs) are increasingly used in scientific writing but struggle with book-length tasks, often producing inconsistent structure and unreliable citations. We introduce CoAuthorAI, a human-in-the-loop writing system that…
Autoregressive Language Models instantiate a factorized likelihood over token sequences, yet their strictly sequential decoding process imposes an intrinsic lower bound on inference latency. This bottleneck has emerged as a central obstacle…
Research question answering requires accurate retrieval and contextual understanding of scientific literature. However, current Retrieval-Augmented Generation (RAG) methods often struggle to balance complex document relationships with…
We present components of an AI-assisted academic writing system including citation recommendation and introduction writing. The system recommends citations by considering the user's current document context to provide relevant suggestions.…
Citation text plays a pivotal role in elucidating the connection between scientific documents, demanding an in-depth comprehension of the cited paper. Constructing citations is often time-consuming, requiring researchers to delve into…
With the rapid advancement of artificial intelligence technology, AI students are confronted with a significant "information-to-innovation" gap: they must navigate through the rapidly expanding body of literature, trace the development of a…
Large Language Models (LLMs) can perform chart question-answering tasks but often generate unverified hallucinated responses. Existing answer attribution methods struggle to ground responses in source charts due to limited visual-semantic…
Large Language Models (LLMs) are being integrated into professional domains, yet their limitations in such high-stakes fields as law remain poorly understood. In response, this paper introduces examples of critical challenges to the…
Retrieval-augmented generation (RAG) is a key means to effectively enhance large language models (LLMs) in many knowledge-based tasks. However, existing RAG methods struggle with knowledge-intensive reasoning tasks, because useful…
The sheer volume of scientific experimental results and complex technical statements, often presented in tabular formats, presents a formidable barrier to individuals acquiring preferred information. The realms of scientific reasoning and…