Related papers: STaR: Bootstrapping Reasoning With Reasoning

Large Language Models exhibit impressive reasoning capabilities across diverse tasks, motivating efforts to distill these capabilities into smaller models through generated reasoning data. However, direct training on such synthesized…

Recent advancements in large language models (LLMs), such as DeepSeek-R1 and OpenAI-o1, have demonstrated the significant effectiveness of test-time scaling, achieving substantial performance gains across various benchmarks. These advanced…

Multi-hop retrieval-augmented generation (RAG) is a promising strategy for complex reasoning, yet existing iterative prompting approaches remain inefficient. They often regenerate predictable token sequences at every step and rely on…

The prevailing approach to distilling reasoning from Large Language Models (LLMs)-behavioral cloning from textual rationales-is fundamentally limited. It teaches Small Language Models (SLMs) to mimic surface-level patterns rather than the…

Large language models (LLMs) can perform complex reasoning by generating intermediate thoughts under zero-shot or few-shot settings. However, zero-shot prompting always encounters low performance, and the superior performance of few-shot…

Research on reasoning in language models (LMs) predominantly focuses on improving the correctness of their outputs. But some important applications require modeling reasoning patterns that are incorrect. For example, automated systems that…

Although large language models demonstrate emergent abilities in solving math word problems, there is a challenging task in complex multi-step mathematical reasoning tasks. To improve model performance on mathematical reasoning tasks,…

General Question Answering (QA) systems over texts require the multi-hop reasoning capability, i.e. the ability to reason with information collected from multiple passages to derive the answer. In this paper we conduct a systematic analysis…

Chain-of-thought prompting combined with pre-trained large language models has achieved encouraging results on complex reasoning tasks. In this paper, we propose a new decoding strategy, self-consistency, to replace the naive greedy…

Large Vision-Language Models (LVLMs) have shown exceptional performance in multimodal tasks, but their effectiveness in complex visual reasoning is still constrained, especially when employing Chain-of-Thought prompting techniques. In this…

Integrating free-text explanations to in-context learning of large language models (LLM) is shown to elicit strong reasoning capabilities along with reasonable explanations. In this paper, we consider the problem of leveraging the…

The effectiveness of Reinforcement Learning (RL) in Large Language Models (LLMs) depends on the nature and diversity of the data used before and during RL. In particular, reasoning problems can often be approached in multiple ways that rely…

Generating high-quality stories spanning thousands of tokens requires competency across a variety of skills, from tracking plot and character arcs to keeping a consistent and engaging style. Due to the difficulty of sourcing labeled…

Recent advances in self-refinement have demonstrated significant potential for improving the outputs of large language models (LLMs) through iterative refinement. However, most existing self-refinement methods rely on a reactive process…

Improving the reasoning abilities of large language models (LLMs) has largely relied on iterative self-training with model-generated data. While effective at boosting accuracy, existing approaches primarily reinforce successful reasoning…

A common practice in knowledge-grounded dialogue generation is to explicitly utilize intermediate steps (e.g., web-search, memory retrieval) with modular approaches. However, data for such steps are often inaccessible compared to those of…

Retrieval-augmented large language models, when optimized with outcome-level rewards, can achieve strong answer accuracy on multi-hop questions. However, under noisy retrieval, models frequently suffer from "right-answer-wrong-reason…

As comprehensive large model evaluation becomes prohibitively expensive, predicting model performance from limited observations has become essential. However, existing statistical methods struggle with pattern shifts, data sparsity, and…

The reasoning steps generated by LLMs might be incomplete, as they mimic logical leaps common in everyday communication found in their pre-training data: underlying rationales are frequently left implicit (unstated). To address this…

Chain-of-Thought reasoning significantly improves the performance of large language models on complex tasks, but incurs high inference latency due to long generation traces. Step-level speculative reasoning aims to mitigate this cost, yet…