paper-with-me

Papers

Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths

2024-10-07 · Yew Ken Chia, Guizhen Chen, Weiwen Xu, Luu Anh Tuan, Soujanya Poria, Lidong Bing

Advanced models such as OpenAI o1 exhibit impressive problem-solving capabilities through step-by-step reasoning. However, they may still falter on more complex problems, making errors that disrupt their reasoning paths. We attribute this to the expansive solution space, where each step has the risk of diverging into mistakes. To enhance language model reasoning, we introduce a specialized training framework called Reasoning Paths Optimization (RPO), which enables learning to reason and explore from diverse paths. Our approach encourages favorable branches at each reasoning step while penalizing unfavorable ones, enhancing the model's overall problem-solving performance. Reasoning Paths Optimization does not rely on large-scale human-annotated rationales or outputs from closed-source models, making it scalable and data-efficient. We focus on multi-step reasoning tasks, such as math word problems and science-based exam questions. The experiments demonstrate that our framework significantly enhances the reasoning performance of large language models, with up to 3.1% and 4.3% improvement on GSM8K and MMLU (STEM) respectively. Our data and code can be found at https://reasoning-paths.github.io.

📄 PDF Abstract BibTeX arXiv:2410.10858

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeGSM8KLanguage ModelingLanguage ModellingMathMMLU

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Evolution of Thought: Diverse and High-Quality Reasoning via Multi-Objective Optimization

2024-11-24 · Biqing Qi, Zhouyi Qian, Yiang Luo, Junqi Gao 외

As multi-modal large language models (MLLMs) are increasingly applied to complex reasoning tasks, the diversity and quality of reasoning paths become crucial factors affecting their performance. Although current methods …

Diversity

Improving LLM Reasoning with Multi-Agent Tree-of-Thought Validator Agent

2024-09-17 · Fatemeh Haji, Mazal Bethany, Maryam Tabar, Jason Chiang 외

Multi-agent strategies have emerged as a promising approach to enhance the reasoning abilities of Large Language Models (LLMs) by assigning specialized roles in the problem-solving process. Concurrently, Tree of Thoughts…

GSM8KQuestion Answeringvalid

Just Ask One More Time! Self-Agreement Improves Reasoning of Language Models in (Almost) All Scenarios

2023-11-14 · Lei Lin, Jiayi Fu, Pengli Liu, Qingyang Li 외

Although chain-of-thought (CoT) prompting combined with language models has achieved encouraging results on complex reasoning tasks, the naive greedy decoding used in CoT prompting usually causes the repetitiveness and l…

AllDecoderLanguage Modelling

Diverse Thinking Schemata Elicit Better Reasoning in Large Language Models

2026-06-08 · Xinyue Liang, Yizhe Yang, Yu Bai, Bin Xu 외 arxiv

Large reasoning models (LRMs) have attracted increasing attention for their ability to solve complex mathematical problems by generating extended reasoning chains. In this work, we focus on two critical yet underexplored…

Reinforcement LearningMathematical Reasoning

Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative Probabilities

2026-02-05 · Pengyi Li, Elizaveta Goncharova, Andrey Kuznetsov, Ivan Oseledets arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an indispensable paradigm for enhancing reasoning in Large Language Models (LLMs). However, standard policy optimization methods, such as Group Relativ…

Reinforcement Learning