Generative AI (GenAI) represents a shift from AI's ability to “recognize” to its ability to
“generate” solutions for a wide range of tasks. As generated solutions and applications grow …

Previous language model pre-training methods have uniformly applied a next-token
prediction loss to all training tokens. Challenging this norm, we posit that''Not all tokens in a …

Previous language model pre-training methods have uniformly applied a next-token
prediction loss to all training tokens. Challenging this norm, we posit that" 9l training". Our …

As Large Language Models (LLMs) are integrated into critical real-world applications, their
strategic and logical reasoning abilities are increasingly crucial. This paper evaluates LLMs' …

This study introduces a hypothesis-testing framework to assess whether large language
models (LLMs) possess genuine reasoning abilities or primarily depend on token bias. We …

Large language models (LLM) have demonstrated emergent abilities in text generation,
question answering, and reasoning, facilitating various tasks and domains. Despite their …

Do current large language models (LLMs) better solve graph reasoning and generation
tasks with parameter updates? In this paper, we propose InstructGraph, a framework that …

Code executability plays a vital role in software debugging and testing (eg, detecting runtime
exceptions or assertion violations). However, code execution, especially partial or arbitrary …

Against the backdrop of enthusiasm for large language models (LLMs), there is an urgent
need to scientifically assess their capabilities and shortcomings. This is nontrivial in part …

As open-weight large language models (LLMs) achieve ever more impressive performances
across a wide range of tasks in English, practitioners aim to adapt these models to different …