Related papers: When More is Less: Understanding Chain-of-Thought …

Recent advances in reasoning with large language models (LLMs) have popularized Long Chain-of-Thought (LCoT), a strategy that encourages deliberate and step-by-step reasoning before producing a final answer. While LCoTs have enabled…

Large Language Models (LLMs) are typically trained to reflect a relatively uniform set of values, which limits their applicability to tasks that require understanding of nuanced human perspectives. Recent research has underscored the…

Large Language Models (LLMs) solve many reasoning tasks via chain-of-thought (CoT) prompting, but smaller models (about 7 to 8B parameters) still struggle with multi-step reasoning under tight compute and token budgets. Existing test time…

The table reasoning task, crucial for efficient data acquisition, aims to answer questions based on the given table. Recently, reasoning large language models (RLLMs) with Long Chain-of-Thought (Long CoT) significantly enhance reasoning…

Scaling test-time compute through extended chains of thought has become a dominant paradigm for improving large language model reasoning. However, existing research implicitly assumes that longer thinking always yields better results. This…

Test-time scaling has enabled Large Language Models (LLMs) to tackle complex reasoning, yet the limitations of current Chain-of-Thought (CoT) evaluation obscures whether performance gains stem from genuine reasoning or mere verbosity. To…

Chain-of-Though (CoT) represents a common strategy for reasoning in Large Language Models (LLMs) by decomposing complex tasks into intermediate inference steps. However, explanations generated via CoT are susceptible to content biases that…

Chain-of-Thought (CoT) significantly enhances formal reasoning capabilities in Large Language Models (LLMs) by training them to explicitly generate intermediate reasoning steps. While LLMs readily benefit from such techniques, improving…

In-Context Learning (ICL) in Large Language Models (LLM) has emerged as the dominant technique for performing natural language tasks, as it does not require updating the model parameters with gradient-based methods. ICL promises to "adapt"…

Large language models (LLMs) achieve strong performance on code generation, but the mechanisms by which Chain-of-Thought (CoT) prompting helps remain unclear. We present a systematic empirical and information-theoretic study of CoT…

Large Audio Language Models (LALMs), powered by the chain-of-thought (CoT) paradigm, have shown remarkable reasoning capabilities. Intuitively, different problems often require varying depths of reasoning. While some methods can determine…

Chain of Thought (CoT) prompting can encourage language models to engage in multi-step logical reasoning. The quality of the provided demonstrations significantly influences the success of downstream inference tasks. Current unsupervised…

Learning to reason and carefully explain arguments is central to students' cognitive, mathematical, and computational thinking development. This is particularly challenging in problems under uncertainty and in Bayesian reasoning. With the…

Reinforcement Learning (RL) has become a pivotal approach for enhancing the reasoning capabilities of Large Language Models (LLMs). However, a significant theoretical gap persists, as traditional token-level RL frameworks fail to align with…

Chain-of-Thought (CoT) and Looped Transformers have been shown to empirically improve performance on reasoning tasks and to theoretically enhance expressivity by recursively increasing the number of computational steps. However, their…

Chain of thought (CoT) is a reasoning framework that can enhance the performance of Large Language Models (LLMs) on complex inference tasks. In particular, among various studies related to CoT, multi-path inference stands out as a simple…

Chain-of-thought (CoT) reasoning improves large language model performance on complex tasks, but often produces excessively long and inefficient reasoning traces. Existing methods shorten CoTs using length penalties or global entropy…

Recent large reasoning models such as DeepSeek-R1 exhibit strong complex problems solving abilities by generating long chain-of-thought (CoT) reasoning steps. It is challenging to directly train small language models (SLMs) to emerge long…

Recent large language models achieve strong reasoning performance by generating detailed chain-of-thought traces, but this often leads to excessive token use and high inference latency. Existing efficiency approaches typically focus on…

Large language models (LLMs) excel at complex reasoning but can still exhibit harmful behaviors. Current alignment strategies typically embed safety into model weights, making these controls implicit, static, and difficult to modify. This…