paper-with-me

홈 › Papers

NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions

2025-02-18 · Weizhe Yuan, Jane Yu, Song Jiang, Karthik Padthe, Yang Li, Dong Wang, Ilia Kulikov, Kyunghyun Cho, Yuandong Tian, Jason E Weston, Xian Li

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.

📄 PDF Abstract BibTeX arXiv:2502.13124

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationMath

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

NaturalThoughts: Selecting and Distilling Reasoning Traces for General Reasoning Tasks

2025-07-02 · Yang Li, Youssef Emad, Karthik Padthe, Jack Lanchantin 외 arxiv

Recent work has shown that distilling reasoning traces from a larger teacher model via supervised finetuning outperforms reinforcement learning with the smaller student model alone (Guo et al. 2025). However, there has n…

Reinforcement Learning

WildSci: Advancing Scientific Reasoning from In-the-Wild Literature

2026-01-09 · Tengxiao Liu, Deepak Nathani, Zekun Li, Kevin Yang 외 arxiv

Recent progress in large language model (LLM) reasoning has focused on domains like mathematics and coding, where abundant high-quality data and objective evaluation metrics are readily available. In contrast, progress i…

Reinforcement Learning

ReXInTheWild: A Unified Benchmark for Medical Photograph Understanding

2026-03-19 · Oishi Banerjee, Sung Eun Kim, Alexandra N. Willauer, Julius M. Kernbach 외 arxiv

Everyday photographs taken with ordinary cameras are already widely used in telemedicine and other online health conversations, yet no comprehensive benchmark evaluates whether vision-language models can interpret their …

WildTableBench: Benchmarking Multimodal Foundation Models on Table Understanding In the Wild

2026-05-01 · Junzhe Huang, Xiaoxiao Sun, Yan Yang, Yuxuan Hou 외 arxiv

Using multimodal foundation models to analyze table images is a high-value yet challenging application in consumer and enterprise scenarios. Despite its importance, current evaluations rely largely on structured-text tab…

WildFireVQA: A Large-Scale Radiometric Thermal VQA Benchmark for Aerial Wildfire Monitoring

2026-04-22 · Mobin Habibpour, Niloufar Alipour Talemi, John Spodnik, Camren J. Khoury 외 arxiv

Wildfire monitoring requires timely, actionable situational awareness from airborne platforms, yet existing aerial visual question answering (VQA) benchmarks do not evaluate wildfire-specific multimodal reasoning grounde…

Visual Question AnsweringMultimodal ReasoningAnswer Generation