NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions

• URL: http://arxiv.org/abs/2502.13124v2
• Date: Fri, 21 Feb 2025 16:02:42 GMT
• Title: NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions
• Authors: Weizhe Yuan, Jane Yu, Song Jiang, Karthik Padthe, Yang Li, Dong Wang, Ilia Kulikov, Kyunghyun Cho, Yuandong Tian, Jason E Weston, Xian Li,
• Abstract summary: We present NaturalReasoning, a comprehensive dataset comprising 2.8 million questions that span multiple domains.<n>We show that NaturalReasoning can effectively elicit and transfer reasoning capabilities from a strong teacher model.<n>It is also effective for unsupervised self-training using external reward models or self-rewarding.
• Score: 86.15997774820934
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Scaling reasoning capabilities beyond traditional domains such as math and coding is hindered by the lack of diverse and high-quality questions. To overcome this limitation, we introduce a scalable approach for generating diverse and challenging reasoning questions, accompanied by reference answers. We present NaturalReasoning, a comprehensive dataset comprising 2.8 million questions that span multiple domains, including STEM fields (e.g., Physics, Computer Science), Economics, Social Sciences, and more. We demonstrate the utility of the questions in NaturalReasoning through knowledge distillation experiments which show that NaturalReasoning can effectively elicit and transfer reasoning capabilities from a strong teacher model. Furthermore, we demonstrate that NaturalReasoning is also effective for unsupervised self-training using external reward models or self-rewarding.

Related papers

• SR-FoT: A Syllogistic-Reasoning Framework of Thought for Large Language Models Tackling Knowledge-based Reasoning Tasks [42.392103712958445]
  Large Language Models (LLMs) might not follow the correct reasoning paths.<n>We propose a multi-stage Syllogistic-Reasoning Framework of Thought (SR-FoT)<n>Our SR-FoT begins by interpreting the question and then uses the interpretation and the original question to propose a suitable major premise.
  arXiv  Detail & Related papers  (2025-01-20T17:00:41Z)
• Multi-Faceted Question Complexity Estimation Targeting Topic Domain-Specificity [0.0]
  This paper presents a novel framework for domain-specific question difficulty estimation, leveraging a suite of NLP techniques and knowledge graph analysis. We introduce four key parameters: Topic Retrieval Cost, Topic Salience, Topic Coherence, and Topic Superficiality. A model trained on these features demonstrates the efficacy of our approach in predicting question difficulty.
  arXiv  Detail & Related papers  (2024-08-23T05:40:35Z)
• Analyzing Human Questioning Behavior and Causal Curiosity through Natural Queries [91.70689724416698]
  We present NatQuest, a collection of 13,500 naturally occurring questions from three diverse sources. Our analysis reveals a significant presence of causal questions (up to 42%) within the dataset.
  arXiv  Detail & Related papers  (2024-05-30T17:55:28Z)
• Don't Just Say "I don't know"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanations [70.6395572287422]
  Self-alignment method is capable of not only refusing to answer but also providing explanation to the unanswerability of unknown questions. We conduct disparity-driven self-curation to select qualified data for fine-tuning the LLM itself for aligning the responses to unknown questions as desired.
  arXiv  Detail & Related papers  (2024-02-23T02:24:36Z)
• ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent [50.508669199496474]
  We develop a ReAct-style LLM agent with the ability to reason and act upon external knowledge. We refine the agent through a ReST-like method that iteratively trains on previous trajectories. Starting from a prompted large model and after just two iterations of the algorithm, we can produce a fine-tuned small model.
  arXiv  Detail & Related papers  (2023-12-15T18:20:15Z)
• MacGyver: Are Large Language Models Creative Problem Solvers? [87.70522322728581]
  We explore the creative problem-solving capabilities of modern LLMs in a novel constrained setting. We create MACGYVER, an automatically generated dataset consisting of over 1,600 real-world problems. We present our collection to both LLMs and humans to compare and contrast their problem-solving abilities.
  arXiv  Detail & Related papers  (2023-11-16T08:52:27Z)
• Causal Deep Learning [77.49632479298745]
  Causality has the potential to transform the way we solve real-world problems. But causality often requires crucial assumptions which cannot be tested in practice. We propose a new way of thinking about causality -- we call this causal deep learning.
  arXiv  Detail & Related papers  (2023-03-03T19:19:18Z)
• Towards a Holistic Understanding of Mathematical Questions with Contrastive Pre-training [65.10741459705739]
  We propose a novel contrastive pre-training approach for mathematical question representations, namely QuesCo. We first design two-level question augmentations, including content-level and structure-level, which generate literally diverse question pairs with similar purposes. Then, to fully exploit hierarchical information of knowledge concepts, we propose a knowledge hierarchy-aware rank strategy.
  arXiv  Detail & Related papers  (2023-01-18T14:23:29Z)
• Social Commonsense Reasoning with Multi-Head Knowledge Attention [24.70946979449572]
  Social Commonsense Reasoning requires understanding of text, knowledge about social events and their pragmatic implications, as well as commonsense reasoning skills. We propose a novel multi-head knowledge attention model that encodes semi-structured commonsense inference rules and learns to incorporate them in a transformer-based reasoning cell.
  arXiv  Detail & Related papers  (2020-10-12T10:24:40Z)
• Reinforced Multi-task Approach for Multi-hop Question Generation [47.15108724294234]
  We take up Multi-hop question generation, which aims at generating relevant questions based on supporting facts in the context. We employ multitask learning with the auxiliary task of answer-aware supporting fact prediction to guide the question generator. We demonstrate the effectiveness of our approach through experiments on the multi-hop question answering dataset, HotPotQA.
  arXiv  Detail & Related papers  (2020-04-05T10:16:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.