大模型推理能力

Strata-Sword: A Hierarchical Safety Evaluation towards LLMs based on Reasoning Complexity of Jailbreak Instructions

Shiji Zhao, Ranjie Duan, Jiexi Liu, Xiaojun Jia, Fengxiang Wang, Cheng Wei, Ruoxi Cheng, Yong Xie, Chang Liu, Qing Guo, Jialing Tao, Hui Xue, Xingxing Wei

专题命中 推理评测 ：reasoning(title,abstract)；chain-of-thought(abstract)；CoT(abstract)

StoryReasoning Dataset: Using Chain-of-Thought for Scene Understanding and Grounded Story Generation

Daniel A. P. Oliveira, David Martins de Matos

机构 * Instituto Superior Técnico, Universidade de Lisboa（里斯本大学技术学院） ； INESC-ID Lisboa（里斯本INESC-ID） 纠错

专题命中 推理评测 ：chain-of-thought(title,abstract)；reasoning(abstract)；分类 cs.CL

Comments 31 pages, 14 figures

NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model

NVIDIA, :, Aarti Basant, Abhijit Khairnar, Abhijit Paithankar, Abhinav Khattar, Adithya Renduchintala, Aditya Malte, Akhiad Bercovich, Akshay Hazare, Alejandra Rico, Aleksander Ficek, Alex Kondratenko, Alex Shaposhnikov, Alexander Bukharin, Ali Taghibakhshi, Amelia Barton, Ameya Sunil Mahabaleshwarkar, Amy Shen, Andrew Tao, Ann Guan, Anna Shors, Anubhav Mandarwal, Arham Mehta, Arun Venkatesan, Ashton Sharabiani, Ashwath Aithal, Ashwin Poojary, Ayush Dattagupta, Balaram Buddharaju, Banghua Zhu, Barnaby Simkin, Bilal Kartal, Bita Darvish Rouhani, Bobby Chen, Boris Ginsburg, Brandon Norick, Brian Yu, Bryan Catanzaro, Charles Wang, Charlie Truong, Chetan Mungekar, Chintan Patel, Chris Alexiuk, Christian Munley, Christopher Parisien, Dan Su, Daniel Afrimi, Daniel Korzekwa, Daniel Rohrer, Daria Gitman, David Mosallanezhad, Deepak Narayanan, Dima Rekesh, Dina Yared, Dmytro Pykhtar, Dong Ahn, Duncan Riach, Eileen Long, Elliott Ning, Eric Chung, Erick Galinkin, Evelina Bakhturina, Gargi Prasad, Gerald Shen, Haifeng Qian, Haim Elisha, Harsh Sharma, Hayley Ross, Helen Ngo, Herman Sahota, Hexin Wang, Hoo Chang Shin, Hua Huang, Iain Cunningham, Igor Gitman, Ivan Moshkov, Jaehun Jung, Jan Kautz, Jane Polak Scowcroft, Jared Casper, Jian Zhang, Jiaqi Zeng, Jimmy Zhang, Jinze Xue, Jocelyn Huang, Joey Conway, John Kamalu, Jonathan Cohen, Joseph Jennings, Julien Veron Vialard, Junkeun Yi, Jupinder Parmar, Kari Briski, Katherine Cheung, Katherine Luna, Keith Wyss, Keshav Santhanam, Kezhi Kong, Krzysztof Pawelec, Kumar Anik, Kunlun Li, Kushan Ahmadian, Lawrence McAfee, Laya Sleiman, Leon Derczynski, Luis Vega, Maer Rodrigues de Melo, Makesh Narsimhan Sreedhar, Marcin Chochowski, Mark Cai, Markus Kliegl, Marta Stepniewska-Dziubinska, Matvei Novikov, Mehrzad Samadi, Meredith Price, Meriem Boubdir, Michael Boone, Michael Evans, Michal Bien, Michal Zawalski, Miguel Martinez, Mike Chrzanowski, Mohammad Shoeybi, Mostofa Patwary, Namit Dhameja, Nave Assaf, Negar Habibi, Nidhi Bhatia, Nikki Pope, Nima Tajbakhsh, Nirmal Kumar Juluru, Oleg Rybakov, Oleksii Hrinchuk, Oleksii Kuchaiev, Oluwatobi Olabiyi, Pablo Ribalta, Padmavathy Subramanian, Parth Chadha, Pavlo Molchanov, Peter Dykas, Peter Jin, Piotr Bialecki, Piotr Januszewski, Pradeep Thalasta, Prashant Gaikwad, Prasoon Varshney, Pritam Gundecha, Przemek Tredak, Rabeeh Karimi Mahabadi, Rajen Patel, Ran El-Yaniv, Ranjit Rajan, Ria Cheruvu, Rima Shahbazyan, Ritika Borkar, Ritu Gala, Roger Waleffe, Ruoxi Zhang, Russell J. Hewett, Ryan Prenger, Sahil Jain, Samuel Kriman, Sanjeev Satheesh, Saori Kaji, Sarah Yurick, Saurav Muralidharan, Sean Narenthiran, Seonmyeong Bak, Sepehr Sameni, Seungju Han, Shanmugam Ramasamy, Shaona Ghosh, Sharath Turuvekere Sreenivas, Shelby Thomas, Shizhe Diao, Shreya Gopal, Shrimai Prabhumoye, Shubham Toshniwal, Shuoyang Ding, Siddharth Singh, Siddhartha Jain, Somshubra Majumdar, Soumye Singhal, Stefania Alborghetti, Syeda Nahida Akter, Terry Kong, Tim Moon, Tomasz Hliwiak, Tomer Asida, Tony Wang, Tugrul Konuk, Twinkle Vashishth, Tyler Poon, Udi Karpas, Vahid Noroozi, Venkat Srinivasan, Vijay Korthikanti, Vikram Fugro, Vineeth Kalluru, Vitaly Kurin, Vitaly Lavrukhin, Wasi Uddin Ahmad, Wei Du, Wonmin Byeon, Ximing Lu, Xin Dong, Yashaswi Karnati, Yejin Choi, Yian Zhang, Ying Lin, Yonggan Fu, Yoshi Suhara, Zhen Dong, Zhiyu Li, Zhongbo Zhu, Zijia Chen

机构 * NVIDIA 纠错

专题命中 推理评测 ：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

KoBLEX: Open Legal Question Answering with Multi-hop Reasoning

Jihyung Lee, Daehui Kim, Seonjeong Hwang, Hyounghun Kim, Gary Lee

机构 * Graduate School of Artificial Intelligence, POSTECH, Republic of Korea（人工智能研究生院，POSTECH，韩国） ； Department of Computer Science and Engineering, POSTECH, Republic of Korea（计算机科学与工程系，POSTECH，韩国） ； AI Future Lab, KT, Republic of Korea（AI未来实验室，KT，韩国） 纠错

专题命中 推理评测 ：reasoning(title,abstract)；分类 cs.CL

Comments EMNLP 2025 Main Conference

Personalized Causal Graph Reasoning for LLMs: An Implementation for Dietary Recommendations

Zhongqi Yang, Amir Rahmani

机构 * Department of Computer Science, University of California, Irvine（加州大学尔湾分校计算机科学系） ； School of Nursing, University of California, Irvine（加州大学尔湾分校护理学院） 纠错

专题命中 推理评测 ：reasoning(title,abstract)；分类 cs.CL

The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang

Fenghua Liu, Yulong Chen, Yixuan Liu, Zhujun Jin, Solomon Tsai, Ming Zhong

机构 * University of Cambridge（剑桥大学） ； University of Oxford（牛津大学） ； UIUC（伊利诺伊大学香槟分校） 纠错

专题命中 推理评测 ：reasoning(title,abstract)；分类 cs.CL

Comments Working in progress

KRETA: A Benchmark for Korean Reading and Reasoning in Text-Rich VQA Attuned to Diverse Visual Contexts

Taebaek Hwang, Minseo Kim, Gisang Lee, Seonuk Kim, Hyunjun Eun

机构 * Waddle ； Seoul National University（首尔国立大学） ； Krafton ； UNIST（全南大学） ； SK Telecom（SK电信） 纠错

专题命中 推理评测 ：reasoning(title,abstract)；分类 cs.CL

Comments Accepted to EMNLP 2025 (Main Conference)

LUMIR: an LLM-Driven Unified Agent Framework for Multi-task Infrared Spectroscopy Reasoning

Zujie Xie, Zixuan Chen, Jiheng Liang, Xiangyang Yu, Ziru Yu

专题命中 推理评测 ：reasoning(title,abstract)；分类 cs.AI

Comments 19 pages

Distill Visual Chart Reasoning Ability from LLMs to MLLMs

Wei He, Zhiheng Xi, Wanxu Zhao, Xiaoran Fan, Yiwen Ding, Zifei Shan, Tao Gui, Qi Zhang, Xuanjing Huang

机构 * School of Computer Science, Fudan University（复旦大学计算机学院） ； Weixin Group, Tencent（腾讯Weixin部门） ； Shanghai Innovation Institute（上海创新研究院） ； Shanghai Key Lab of Intelligent Information Processing（上海智能信息处理重点实验室） 纠错

专题命中 推理评测 ：reasoning(title,abstract)；分类 cs.CL

Comments Accepted to EMNLP 2025 Findings. The code and dataset are publicly available at https://github.com/hewei2001/ReachQA

Detecting Visual Information Manipulation Attacks in Augmented Reality: A Multimodal Semantic Reasoning Approach

Yanming Xiu, Maria Gorlatova

机构 * Duke University（杜克大学） 纠错

专题命中 推理评测 ：reasoning(title,abstract)

Comments The paper has been accepted to the 2025 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), and selected for publication in the 2025 IEEE Transactions on Visualization and Computer Graphics (TVCG) special issue

FActBench: A Benchmark for Fine-grained Automatic Evaluation of LLM-Generated Text in the Medical Domain

Anum Afzal, Juraj Vladika, Florian Matthes

机构 * Technical University of Munich（慕尼黑技术大学） 纠错

专题命中 推理评测 ：chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL

VLM-AD: End-to-End Autonomous Driving through Vision-Language Model Supervision

Yi Xu, Yuxin Hu, Zaiwei Zhang, Gregory P. Meyer, Siva Karthik Mustikovela, Siddhartha Srinivasa, Eric M. Wolff, Xin Huang

机构 * Cruise LLC (GM)（Cruise LLC（GM）） ； Northeastern University（东北大学） ； OpenAI（开放人工智能研究所） ； Meta ； University of Washington（华盛顿大学） ； Waymo LLC 纠错

专题命中 推理评测 ：reasoning(abstract)；planning(abstract)；分类 cs.LG

Comments Accepted by CoRL 2025

Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture

Wanyue Zhang, Yibin Huang, Yangbin Xu, JingJing Huang, Helu Zhi, Shuo Ren, Wang Xu, Jiajun Zhang

专题命中 推理评测 ：reasoning(abstract)；planning(abstract)

Comments The benchmark MulSeT is available at https://huggingface.co/datasets/WanyueZhang/MulSeT

Towards High Data Efficiency in Reinforcement Learning with Verifiable Reward

Xinyu Tang, Zhenduo Zhang, Yurou Liu, Wayne Xin Zhao, Zujie Wen, Zhiqiang Zhang, Jun Zhou

机构 * Gaoling School of Artificial Intelligence, Renmin University of China 2 Ant Group（中国人民大学北京校区人工智能学院，中国人民大学 2 抗集团） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.CL、cs.LG

Enhancing Large Language Model for Knowledge Graph Completion via Structure-Aware Alignment-Tuning

Yu Liu, Yanan Cao, Xixun Lin, Yanmin Shang, Shi Wang, Shirui Pan

机构 * Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所） ； School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院） ； Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所） ； Griffith University（格里菲斯大学） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments EMNLP 2025, Main, Long Paper

A Multi-granularity Concept Sparse Activation and Hierarchical Knowledge Graph Fusion Framework for Rare Disease Diagnosis

Mingda Zhang, Na Zhao, Jianglong Qin, Guoyu Ye, Ruixiang Tang

机构 * School of Software, Yunnan University（云南大学软件学院） ； Yunnan Key Laboratory of Software Engineering（云南软件工程重点实验室） ； Yunnan Provincial Hospital of Traditional Chinese Medicine（云南中医药省人民医院） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 12 pages,3 figures

LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation

Ming Zhang, Yujiong Shen, Zelin Li, Huayu Sha, Binze Hu, Yuhui Wang, Chenhao Huang, Shichun Liu, Jingqi Tong, Changhao Jiang, Mingxu Chai, Zhiheng Xi, Shihan Dou, Tao Gui, Qi Zhang, Xuanjing Huang

机构 * College of Computer Science and Artificial Intelligence, Fudan University（计算机科学与人工智能学院，复旦大学） ； Shanghai Key Lab of Intelligent Information Processing（上海智能信息处理重点实验室） ； Shanghai AI Laboratory（上海人工智能实验室） ； Northwestern University（西北大学） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.CL、cs.AI

Mitigating Catastrophic Forgetting in Continual Learning through Model Growth

Ege Süalp, Mina Rezaei

机构 * Department of Statistics Ludwig-Maximilian University（统计系路德维希-马克西米利安大学） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.CL

Point, Detect, Count: Multi-Task Medical Image Understanding with Instruction-Tuned Vision-Language Models

Sushant Gautam, Michael A. Riegler, Pål Halvorsen

机构 * Simula Metropolitan Center for Digital Engineering (SimulaMet), Norway（Simula数字工程中心（SimulaMet）） ； Oslo Metropolitan University (OsloMet), Norway（奥斯陆 Metropolitan 大学（OsloMet）） ； Simula Research Laboratory, Norway（Simula研究实验室） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.AI

Comments Accepted as a full paper at the 38th IEEE International Symposium on Computer-Based Medical Systems (CBMS) 2025

FactGenius: Combining Zero-Shot Prompting and Fuzzy Relation Mining to Improve Fact Verification with Knowledge Graphs

Sushant Gautam

机构 * Simula Metropolitan Center for Digital Engineering（模拟元数字工程中心） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.CL

Comments accepted and presented at the 6th IN5550 Workshop on Neural Natural Language Processing (WNNLP 2024) at the University of Oslo, Norway

Why Not Transform Chat Large Language Models to Non-English?

Xiang Geng, Ming Zhu, Jiahuan Li, Zhejian Lai, Wei Zou, Shuaijie She, Jiaxin Guo, Xiaofeng Zhao, Yinglu Li, Yuang Li, Chang Su, Yanqing Zhao, Xinglin Lyu, Min Zhang, Jiajun Chen, Hao Yang, Shujian Huang

机构 * National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China（新型软件技术国家重点实验室，南京大学，南京） ； Translation Services Center, Huawei Inc., Beijing 100085, China（翻译服务部，华为公司，北京） 纠错

专题命中 推理评测 ：chain-of-thought(abstract)；分类 cs.CL

Comments The article has been accepted by Frontiers of Computer Science (FCS), with the DOI: {10.1007/s11704-025-50646-z}

VideoRewardBench: Comprehensive Evaluation of Multimodal Reward Models for Video Understanding

Zhihong Zhang, Xiaojian Huang, Jin Xu, Zhuodong Luo, Xinzhi Wang, Jiansheng Wei, Xuejin Chen

机构 * University of Science and Technology of China（中国科学技术大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.AI

Comments https://videorewardbench.github.io/

Activation Steering Meets Preference Optimization: Defense Against Jailbreaks in Vision Language Models

Sihao Wu, Gaojie Jin, Wei Huang, Jianhong Wang, Xiaowei Huang

机构 * University of Liverpool（利物浦大学） ； University of Exeter（埃克塞特大学） ； Purple Mountain Laboratories（紫金山实验室） ； University of Bristol（布里斯托大学） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.AI

ManipBench: Benchmarking Vision-Language Models for Low-Level Robot Manipulation

Enyu Zhao, Vedant Raval, Hejia Zhang, Jiageng Mao, Zeyu Shangguan, Stefanos Nikolaidis, Yue Wang, Daniel Seita

机构 * Department of Computer Science, University of Southern California（计算机科学系，南加州大学） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.AI

Comments Conference on Robot Learning (CoRL) 2025. 50 pages and 30 figures. v2 is the camera-ready and includes a few more new experiments compared to v1