大模型推理能力

Is Long Context All You Need? Leveraging LLM's Extended Context for NL2SQL

Yeounoh Chung, Gaurav T. Kakkar, Yu Gan, Brenton Milne, Fatma Ozcan

机构 * Google（谷歌） 纠错

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.AI

Comments 13 pages, 6 figures, VLDB 2025

Chain of Methodologies: Scaling Test Time Computation without Training

Cong Liu, Jie Wu, Weigang Wu, Xu Chen, Liang Lin, Wei-Shi Zheng

机构 * Sun Yat-sen University（中山大学） ； Temple University 纠错

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.CL

Journal ref ACL 2025

GRAPE: Optimize Data Mixture for Group Robust Multi-target Adaptive Pretraining

Simin Fan, Maria Ios Glarou, Martin Jaggi

机构 * EPFL（瑞士联邦理工学院） 纠错

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.LG

Multilingual Test-Time Scaling via Initial Thought Transfer

Prasoon Bajpai, Tanmoy Chakraborty

机构 * IIT Delhi（德里印度理工学院） 纠错

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.CL

Comments 14 pages, 9 figures, 5 Tables

A*-Decoding: Token-Efficient Inference Scaling

Giannis Chatziveroglou

机构 * MIT（麻省理工学院） ； Cohere 纠错

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.AI

MR. Judge: Multimodal Reasoner as a Judge

Renjie Pi, Felix Bai, Qibin Chen, Simon Wang, Jiulong Shan, Kieran Liu, Meng Cao

机构 * HKUST（香港科技大学） ； Apple（苹果公司） 纠错

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.CL

InfoPO: On Mutual Information Maximization for Large Language Model Alignment

Teng Xiao, Zhen Ge, Sujay Sanghavi, Tian Wang, Julian Katz-Samuels, Marc Versage, Qingjun Cui, Trishul Chilimbi

机构 * Amazon（亚马逊） 纠错

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.LG

Comments NAACL 2025

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models

Hang Wu, Jianian Zhu, Yinghui Li, Haojie Wang, Biao Hou, Jidong Zhai

专题命中 测试时计算 ：verifier(abstract)；分类 cs.LG

Comments 10 pages

Semantic Probabilistic Control of Language Models

Kareem Ahmed, Catarina G Belem, Padhraic Smyth, Sameer Singh

专题命中 测试时计算 ：verifier(abstract)；分类 cs.LG

GenCLS++: Pushing the Boundaries of Generative Classification in LLMs Through Comprehensive SFT and RL Studies Across Diverse Datasets

Mingqian He, Fei Zhao, Chonggang Lu, Ziyan Liu, Yue Wang, Haofu Qian

机构 * Zhejiang University（浙江大学） ； Xiaohongshu Inc.（小红书公司） ； Beijing University of Posts and Telecommunications（北京邮电大学） ； Nanjing University（南京大学） 纠错

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.CL

EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

Yuhui Li, Fangyun Wei, Chao Zhang, Hongyang Zhang

机构 * Peking University（北京大学） ； Microsoft Research（微软研究院） ； University of Waterloo（滑铁卢大学） ； Vector Institute（向量研究所） 纠错

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.CL

Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment

Chenhang Cui, An Zhang, Yiyang Zhou, Zhaorun Chen, Gelei Deng, Huaxiu Yao, Tat-Seng Chua

机构 * National University of Singapore（新加坡国立大学） ； UNC-Chapel Hill（北卡罗来纳大学教堂山分校） ； University of Chicago（芝加哥大学） ； Nanyang Technological University（南洋理工大学） 纠错

专题命中 测试时计算 ：verifier(abstract)；分类 cs.CL

Comments 23 pages; Published as a conference paper at ICLR 2025

Exploring Expert Failures Improves LLM Agent Tuning

Li-Cheng Lan, Andrew Bai, Minhao Cheng, Cho-Jui Hsieh, Tianyi Zhou

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.AI

PAFFA: Premeditated Actions For Fast Agents

Shambhavi Krishna, Zheng Chen, Yuan Ling, Xiaojiang Huang, Yingjie Li, Fan Yang, Xiang Li

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.AI

Comments 16 pages

Video-T1: Test-Time Scaling for Video Generation

Fangfu Liu, Hanyang Wang, Yimo Cai, Kaiyan Zhang, Xiaohang Zhan, Yueqi Duan

专题命中 测试时计算 ：test-time compute(abstract)；分类 cs.AI

Comments Project page: https://liuff19.github.io/Video-T1

MoRE-LLM: Mixture of Rule Experts Guided by a Large Language Model

Alexander Koebler, Ingo Thon, Florian Buettner

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.LG

Comments 2024 IEEE International Conference on Data Mining (ICDM)

Improving the End-to-End Efficiency of Offline Inference for Multi-LLM Applications Based on Sampling and Simulation

Jingzhi Fang, Yanyan Shen, Yue Wang, Lei Chen

专题命中 测试时计算 ：planning(abstract)；分类 cs.LG

Enhancing Zero-Shot Image Recognition in Vision-Language Models through Human-like Concept Guidance

Hui Liu, Wenya Wang, Kecheng Chen, Jie Liu, Yibing Liu, Tiexin Qin, Peisong He, Xinghao Jiang, Haoliang Li

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.LG

Comments 21 pages, 7 figures 7 tables

Better Process Supervision with Bi-directional Rewarding Signals

Wenxiang Chen, Wei He, Zhiheng Xi, Honglin Guo, Boyang Hong, Jiazheng Zhang, Rui Zheng, Nijun Li, Tao Gui, Yun Li, Qi Zhang, Xuanjing Huang

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.CL

Inference Scaling for Long-Context Retrieval Augmented Generation

Zhenrui Yue, Honglei Zhuang, Aijun Bai, Kai Hui, Rolf Jagerman, Hansi Zeng, Zhen Qin, Dong Wang, Xuanhui Wang, Michael Bendersky

专题命中 测试时计算 ：test-time compute(abstract)；分类 cs.CL

Comments ICLR 2025

Teleology-Driven Affective Computing: A Causal Framework for Sustained Well-Being

Bin Yin, Chong-Yi Liu, Liya Fu, Jinkun Zhang

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.AI

Comments 24 pages, 7 figures

Governing AI Beyond the Pretraining Frontier

Nicholas A. Caputo

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.AI

Comments 14 pages

Multi-Novelty: Improve the Diversity and Novelty of Contents Generated by Large Language Models via inference-time Multi-Views Brainstorming

Arash Lagzian, Srinivas Anumasa, Dianbo Liu

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.CL

To Bin or not to Bin: Alternative Representations of Mass Spectra

Niek de Jonge, Justin J. J. van der Hooft, Daniel Probst

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.LG

Comments This manuscript has been submitted to the tiny paper track at the LMRL workshop at ICLR 2025

LLMmap: Fingerprinting For Large Language Models

Dario Pasquini, Evgenios M. Kornaropoulos, Giuseppe Ateniese

专题命中 测试时计算 ：chain-of-thought(abstract)；分类 cs.AI

Comments Appearing in the proceedings of the 34th USENIX Security Symposium

Language Models Prefer What They Know: Relative Confidence Estimation via Confidence Preferences

Vaishnavi Shrivastava, Ananya Kumar, Percy Liang

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.CL

Data-and-Semantic Dual-Driven Spectrum Map Construction for 6G Spectrum Management

Jiayu Liu, Fuhui Zhou, Xiaodong Liu, Rui Ding, Lu Yuan, Qihui Wu

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.LG

Comments This paper has been accepted for presentation at the IEEE Global Communications Conference (GLOBECOM), Cape Town, South Africa, December 2024

MQM-APE: Toward High-Quality Error Annotation Predictors with Automatic Post-Editing in LLM Translation Evaluators

Qingyu Lu, Liang Ding, Kanjian Zhang, Jinxia Zhang, Dacheng Tao

专题命中 测试时计算 ：verifier(abstract)；分类 cs.CL

Comments COLING 2025

VLMs meet UDA: Boosting Transferability of Open Vocabulary Segmentation with Unsupervised Domain Adaptation

Roberto Alcover-Couso, Marcos Escudero-Viñolo, Juan C. SanMiguel, Jesus Bescos

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.AI

Learning to Reason via Self-Iterative Process Feedback for Small Language Models

Kaiyuan Chen, Jin Wang, Xuejie Zhang

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.CL

Comments Accepted by COLING 2025