大模型推理能力 - arXivDaily 专题

2406.11911 2024-10-10 cs.AI cs.CL cs.LG 67%

A Notion of Complexity for Theory of Mind via Discrete World Models

X. Angelo Huang, Emanuele La Malfa, Samuele Marro, Andrea Asperti, Anthony Cohn, Michael Wooldridge

专题命中复杂问题求解：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted EMNLP 2024, Website https://flecart.github.io/complexity-tom-dwm

2402.05200 2024-09-26 cond-mat.mtrl-sci cs.AI cs.CL cs.LG 67%

Are LLMs Ready for Real-World Materials Discovery?

Santiago Miret, N M Anoop Krishnan

专题命中复杂问题求解：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2404.04351 2024-09-20 cs.CL cs.AI cs.LG 67%

Assisting humans in complex comparisons: automated information comparison at scale

Truman Yuen, Graham A. Watt, Yuri Lawryshyn

专题命中复杂问题求解：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 11 pages, 7 figures, 5 tables

2409.09383 2024-09-18 cs.LG cs.AI cs.CL 67%

LLM-Powered Ensemble Learning for Paper Source Tracing: A GPU-Free Approach

Kunlong Chen, Junjun Wang, Zhaoqun Chen, Kunjin Chen, Yitian Chen

专题命中复杂问题求解：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2409.09415 2024-09-17 cs.CL cs.AI cs.LG 67%

Enhancing LLM Problem Solving with REAP: Reflection, Explicit Problem Deconstruction, and Advanced Prompting

Ryan Lingo, Martin Arroyo, Rajeev Chhajer

专题命中复杂问题求解：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 524 pages, 3 figures

2402.02636 2024-09-11 cs.CL cs.AI cs.IT cs.LG math.IT 67%

Can Large Language Models Learn Independent Causal Mechanisms?

Gaël Gendron, Bao Trung Nguyen, Alex Yuxuan Peng, Michael Witbrock, Gillian Dobbie

专题命中复杂问题求解：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 20 pages, 7 pages for the main paper and 13 pages for references and appendices, 17 figures

2409.02141 2024-09-05 cs.LG cs.AI cs.CL 67%

Efficient and Scalable Estimation of Tool Representations in Vector Space

Suhong Moon, Siddharth Jha, Lutfi Eren Erdogan, Sehoon Kim, Woosang Lim, Kurt Keutzer, Amir Gholami

专题命中复杂问题求解：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2404.10501 2024-08-22 cs.CV cs.AI cs.CL cs.LG 67%

Self-Supervised Visual Preference Alignment

Ke Zhu, Zheng Ge, Liang Zhao, Xiangyu Zhang

专题命中复杂问题求解：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments MM2024 oral

2407.15720 2024-08-13 cs.CL cs.AI cs.LG 67%

Do Large Language Models Have Compositional Ability? An Investigation into Limitations and Scalability

Zhuoyan Xu, Zhenmei Shi, Yingyu Liang

专题命中复杂问题求解：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2304.08354 2024-08-07 cs.CL cs.AI cs.LG 67%

Tool Learning with Foundation Models

Yujia Qin, Shengding Hu, Yankai Lin, Weize Chen, Ning Ding, Ganqu Cui, Zheni Zeng, Yufei Huang, Chaojun Xiao, Chi Han, Yi Ren Fung, Yusheng Su, Huadong Wang, Cheng Qian, Runchu Tian, Kunlun Zhu, Shihao Liang, Xingyu Shen, Bokai Xu, Zhen Zhang, Yining Ye, Bowen Li, Ziwei Tang, Jing Yi, Yuzhang Zhu, Zhenning Dai, Lan Yan, Xin Cong, Yaxi Lu, Weilin Zhao, Yuxiang Huang, Junxi Yan, Xu Han, Xian Sun, Dahai Li, Jason Phang, Cheng Yang, Tongshuang Wu, Heng Ji, Zhiyuan Liu, Maosong Sun

专题命中复杂问题求解：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2311.12890 2024-08-06 cs.CV 67%

De-fine: Decomposing and Refining Visual Programs with Auto-Feedback

Minghe Gao, Juncheng Li, Hao Fei, Liang Pang, Wei Ji, Guoming Wang, Zheqi Lv, Wenqiao Zhang, Siliang Tang, Yueting Zhuang

专题命中复杂问题求解：reasoning(abstract)；logical reasoning(abstract)

2406.04496 2024-07-24 cs.CL cs.AI cs.LG 67%

Time Sensitive Knowledge Editing through Efficient Finetuning

Xiou Ge, Ali Mousavi, Edouard Grave, Armand Joulin, Kun Qian, Benjamin Han, Mostafa Arefiyan, Yunyao Li

专题命中复杂问题求解：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ACL 2024 main

2307.07319 2024-07-16 eess.SP 67%

The Power of Large Language Models for Wireless Communication System Development: A Case Study on FPGA Platforms

Yuyang Du, Hongyu Deng, Soung Chang Liew, Kexin Chen, Yulin Shao, He Chen

专题命中复杂问题求解：chain-of-thought(abstract)；CoT(abstract)

2310.05797 2024-07-12 cs.CL cs.AI cs.LG 67%

In-Context Explainers: Harnessing LLMs for Explaining Black Box Models

Nicholas Kroeger, Dan Ley, Satyapriya Krishna, Chirag Agarwal, Himabindu Lakkaraju

专题命中复杂问题求解：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2311.05661 2024-07-04 cs.CL cs.AI cs.LG 67%

Prompt Engineering a Prompt Engineer

Qinyuan Ye, Maxamed Axmed, Reid Pryzant, Fereshte Khani

专题命中复杂问题求解：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to ACL 2024 Findings. Camera-ready version

2310.02905 2024-06-25 cs.LG cs.AI cs.CL 67%

Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers

Xiaoqiang Lin, Zhaoxuan Wu, Zhongxiang Dai, Wenyang Hu, Yao Shu, See-Kiong Ng, Patrick Jaillet, Bryan Kian Hsiang Low

专题命中复杂问题求解：chain-of-thought(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to ICML 2024

2406.12832 2024-06-19 cs.CL cs.AI cs.LG 67%

LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation

Seyedarmin Azizi, Souvik Kundu, Massoud Pedram

专题命中复杂问题求解：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2404.01291 2024-06-19 cs.CV cs.AI cs.CL cs.LG cs.MM 67%

Evaluating Text-to-Visual Generation with Image-to-Text Generation

Zhiqiu Lin, Deepak Pathak, Baiqi Li, Jiayao Li, Xide Xia, Graham Neubig, Pengchuan Zhang, Deva Ramanan

专题命中复杂问题求解：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments We open-source our data, model, and code at: https://github.com/linzhiqiu/t2v_metrics ; Project page: https://linzhiqiu.github.io/papers/vqascore

2401.18070 2024-06-18 cs.CL cs.AI cs.LG 67%

Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?

Andreas Opedal, Alessandro Stolfo, Haruki Shirakami, Ying Jiao, Ryan Cotterell, Bernhard Schölkopf, Abulhair Saparov, Mrinmaya Sachan

专题命中复杂问题求解：planning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted at ICML 2024

2406.06559 2024-06-12 cs.CL cs.AI cs.LG 67%

Harnessing Business and Media Insights with Large Language Models

Yujia Bao, Ankit Parag Shah, Neeru Narang, Jonathan Rivers, Rajeev Maksey, Lan Guan, Louise N. Barrere, Shelley Evenson, Rahul Basole, Connie Miao, Ankit Mehta, Fabien Boulay, Su Min Park, Natalie E. Pearson, Eldhose Joy, Tiger He, Sumiran Thakur, Koustav Ghosal, Josh On, Phoebe Morrison, Tim Major, Eva Siqi Wang, Gina Escobar, Jiaheng Wei, Tharindu Cyril Weerasooriya, Queena Song, Daria Lashkevich, Clare Chen, Gyuhak Kim, Dengpan Yin, Don Hejna, Mo Nomeli, Wei Wei

专题命中复杂问题求解：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2406.04501 2024-06-10 cs.LG cs.AI cs.CL stat.ML 67%

FLUID-LLM: Learning Computational Fluid Dynamics with Spatiotemporal-aware Large Language Models

Max Zhu, Adrián Bazaga, Pietro Liò

专题命中复杂问题求解：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2403.05826 2024-06-03 cs.NI eess.SP 67%

Cached Model-as-a-Resource: Provisioning Large Language Model Agents for Edge Intelligence in Space-air-ground Integrated Networks

Minrui Xu, Dusit Niyato, Hongliang Zhang, Jiawen Kang, Zehui Xiong, Shiwen Mao, Zhu Han

专题命中复杂问题求解：chain-of-thought(abstract)；CoT(abstract)

2310.09297 2024-05-21 cs.LG cs.AI cs.CL 67%

A Framework for Inference Inspired by Human Memory Mechanisms

Xiangyu Zeng, Jie Lin, Piao Hu, Ruizheng Huang, Zhicheng Zhang

专题命中复杂问题求解：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2307.13854 2024-04-17 cs.AI cs.CL cs.LG 67%

WebArena: A Realistic Web Environment for Building Autonomous Agents

Shuyan Zhou, Frank F. Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, Uri Alon, Graham Neubig

专题命中复杂问题求解：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Our code, data, environment reproduction resources, and video demonstrations are publicly available at https://webarena.dev/

2404.07498 2024-04-12 cs.CL cs.AI cs.HC cs.LG 67%

Interactive Prompt Debugging with Sequence Salience

Ian Tenney, Ryan Mullins, Bin Du, Shree Pandya, Minsuk Kahng, Lucas Dixon

专题命中复杂问题求解：chain-of-thought(abstract)；分类 cs.CL、cs.AI、cs.LG

2310.05861 2024-04-03 cs.CL cs.AI cs.CV cs.LG 67%

Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models

Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal

专题命中复杂问题求解：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ICLR 2024 camera-ready (23 pages), Code: https://github.com/archiki/RepARe

2403.14141 2024-03-22 cs.CV 67%

Empowering Segmentation Ability to Multi-modal Large Language Models

Yuqi Yang, Peng-Tao Jiang, Jing Wang, Hao Zhang, Kai Zhao, Jinwei Chen, Bo Li

专题命中复杂问题求解：reasoning(abstract)；chain-of-thought(abstract)

Comments 10 pages, 4 figures

2311.16974 2024-03-20 cs.CV 67%

COLE: A Hierarchical Generation Framework for Multi-Layered and Editable Graphic Design

Peidong Jia, Chenxuan Li, Yuhui Yuan, Zeyu Liu, Yichao Shen, Bohan Chen, Xingru Chen, Yinglin Zheng, Dong Chen, Ji Li, Xiaodong Xie, Shanghang Zhang, Baining Guo

专题命中复杂问题求解：reasoning(abstract)；planning(abstract)

Comments Technical report. Project page: https://graphic-design-generation-github-io.vercel.app/

2305.17126 2024-03-12 cs.LG cs.AI cs.CL stat.ML 67%

Large Language Models as Tool Makers

Tianle Cai, Xuezhi Wang, Tengyu Ma, Xinyun Chen, Denny Zhou

专题命中复杂问题求解：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Code available at https://github.com/ctlllll/LLM-ToolMaker

2402.01812 2024-02-06 cs.CL cs.AI cs.LG 67%

Distilling LLMs' Decomposition Abilities into Compact Language Models

Denis Tarasov, Kumar Shridhar

专题命中复杂问题求解：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments https://github.com/DT6A/GSM8K-AI-SubQ

1. 复杂问题求解 5001 篇

A Notion of Complexity for Theory of Mind via Discrete World Models

Are LLMs Ready for Real-World Materials Discovery?

Assisting humans in complex comparisons: automated information comparison at scale

LLM-Powered Ensemble Learning for Paper Source Tracing: A GPU-Free Approach

Enhancing LLM Problem Solving with REAP: Reflection, Explicit Problem Deconstruction, and Advanced Prompting

Can Large Language Models Learn Independent Causal Mechanisms?

Efficient and Scalable Estimation of Tool Representations in Vector Space

Self-Supervised Visual Preference Alignment

Do Large Language Models Have Compositional Ability? An Investigation into Limitations and Scalability

Tool Learning with Foundation Models

De-fine: Decomposing and Refining Visual Programs with Auto-Feedback

Time Sensitive Knowledge Editing through Efficient Finetuning

The Power of Large Language Models for Wireless Communication System Development: A Case Study on FPGA Platforms

In-Context Explainers: Harnessing LLMs for Explaining Black Box Models

Prompt Engineering a Prompt Engineer

Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers

LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation

Evaluating Text-to-Visual Generation with Image-to-Text Generation

Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?

Harnessing Business and Media Insights with Large Language Models

FLUID-LLM: Learning Computational Fluid Dynamics with Spatiotemporal-aware Large Language Models

Cached Model-as-a-Resource: Provisioning Large Language Model Agents for Edge Intelligence in Space-air-ground Integrated Networks

A Framework for Inference Inspired by Human Memory Mechanisms

WebArena: A Realistic Web Environment for Building Autonomous Agents

Interactive Prompt Debugging with Sequence Salience

Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models

Empowering Segmentation Ability to Multi-modal Large Language Models

COLE: A Hierarchical Generation Framework for Multi-Layered and Editable Graphic Design

Large Language Models as Tool Makers

Distilling LLMs' Decomposition Abilities into Compact Language Models