相关论文: Can LLMs Learn from Previous Mistakes? Investigati…

Pre-trained language models (LMs) have shown remarkable reasoning performance using explanations or chain-of-thoughts (CoT)) for in-context learning. On the other hand, these reasoning tasks are usually presumed to be more approachable for…

We propose novel evaluations for mathematical reasoning capabilities of Large Language Models (LLMs) based on mathematical misconceptions. Our primary approach is to simulate LLMs as a novice learner and an expert tutor, aiming to identify…

Large Language Models (LLMs) have shown impressive performance in complex reasoning tasks through the use of Chain-of-Thought (CoT) reasoning, allowing models to break down problems into manageable sub-tasks. However, existing CoT…

Large language models (LLMs) are increasingly embedded in AI-based tutoring systems. Can they faithfully model novice reasoning and metacognitive judgments? Existing evaluations emphasize problem-solving accuracy, overlooking the fragmented…

A common approach for teaching large language models (LLMs) to reason is to train on chain-of-thought (CoT) traces of in-distribution reasoning problems, but such annotated data is costly to obtain for every problem of interest. We want…

Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps, limiting the gains from additional test-time compute. Improving reasoning quality directly would require process reward models,…

With the release of R1, a publicly available large reasoning model (LRM), researchers commonly train new LRMs by training language models on R1's long chain-of-thought (CoT) inferences. While prior works show that LRMs' capabilities can be…

The cognitive mechanism by which Large Language Models (LLMs) solve mathematical problems remains a widely debated and unresolved issue. Currently, there is little interpretable experimental evidence that connects LLMs' problem-solving with…

Deep iterative chain-of-thought (CoT) reasoning enables LLMs to tackle complex tasks by progressively activating relevant pre-trained knowledge. However, it faces challenges in ensuring continual improvement and determining a stopping…

Large language models (LLMs) excel at complex tasks thanks to advances in their reasoning abilities. However, existing methods overlook the trade-off between reasoning effectiveness and efficiency, often encouraging unnecessarily long…

Chain-of-Thought (CoT) reasoning has emerged as a powerful tool for enhancing the problem-solving capabilities of large language models (LLMs). However, the theoretical foundations of learning from CoT data remain underdeveloped, and…

This paper investigates the capabilities of large language models (LLMs) in formulating and solving decision-making problems using mathematical programming. We first conduct a systematic review and meta-analysis of recent literature to…

Compressing long chain-of-thought (CoT) from large language models (LLMs) is an emerging strategy to improve the reasoning efficiency of LLMs. Despite its promising benefits, existing studies equally compress all thoughts within a long CoT,…

Large language models (LLMs) demonstrate their promise in tackling complicated practical challenges by combining action-based policies with chain of thought (CoT) reasoning. Having high-quality prompts on hand, however, is vital to the…

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…

Chain-of-Thought (CoT) monitoring has emerged as a compelling method for detecting harmful behaviors such as reward hacking for reasoning models, under the assumption that models' reasoning processes are informative of such behaviors. In…

Mathematical reasoning has long represented one of the most fundamental and challenging frontiers in artificial intelligence research. In recent years, large language models (LLMs) have achieved significant advances in this area. This…

Chain of thought (CoT) fine-tuning aims to endow large language models (LLMs) with reasoning capabilities by training them on curated reasoning traces. It leverages both supervised and reinforced fine-tuning to cultivate human-like…

Large Reasoning Models (LRMs) have achieved remarkable success on reasoning-intensive tasks such as mathematics and programming. However, their enhanced reasoning capabilities do not necessarily translate to improved safety performance-and…

We present the surprising finding that a language model's reasoning capabilities can be improved by training on synthetic datasets of chain-of-thought (CoT) traces from more capable models, even when all of those traces lead to an incorrect…