大模型推理能力 - arXivDaily 专题

2402.11651 2024-04-17 cs.CL 57%

Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents

Renxi Wang, Haonan Li, Xudong Han, Yixuan Zhang, Timothy Baldwin

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments Agent, LLM, Large Language Model

2404.09492 2024-04-16 cs.CL 57%

Bridging the Gap between Different Vocabularies for LLM Ensemble

Yangyifan Xu, Jinliang Lu, Jiajun Zhang

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments Accepted to the main conference of NAACL 2024

2404.01226 2024-04-02 cs.CL 57%

Stable Code Technical Report

Nikhil Pinnaparaju, Reshinth Adithyan, Duy Phung, Jonathan Tow, James Baicoianu, Ashish Datta, Maksym Zhuravinskyi, Dakota Mahan, Marco Bellagente, Carlos Riquelme, Nathan Cooper

专题命中数学推理：reasoning(abstract)；分类 cs.CL

2310.13522 2024-04-02 cs.CL 57%

Teaching Language Models to Self-Improve through Interactive Demonstrations

Xiao Yu, Baolin Peng, Michel Galley, Jianfeng Gao, Zhou Yu

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments NAACL 2024 main

2403.12373 2024-03-25 cs.CL 57%

RankPrompt: Step-by-Step Comparisons Make Language Models Better Reasoners

Chi Hu, Yuan Ge, Xiangnan Ma, Hang Cao, Qiang Li, Yonghua Yang, Tong Xiao, Jingbo Zhu

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments LREC-Coling 2024 Long Paper

2403.04571 2024-03-08 cs.AI 57%

Machine learning and information theory concepts towards an AI Mathematician

Yoshua Bengio, Nikolay Malkin

专题命中数学推理：reasoning(abstract)；分类 cs.AI

Comments To appear in the Bulletin of the AMS, 2024

2311.08107 2024-03-04 cs.CL 57%

SAIE Framework: Support Alone Isn't Enough -- Advancing LLM Training with Adversarial Remarks

Mengsay Loem, Masahiro Kaneko, Naoaki Okazaki

专题命中数学推理：reasoning(abstract)；分类 cs.CL

2402.12080 2024-02-20 cs.CL 57%

Can LLMs Compute with Reasons?

Harshit Sandilya, Peehu Raj, Jainit Sushil Bafna, Srija Mukhopadhyay, Shivansh Sharma, Ellwil Sharma, Arastu Sharma, Neeta Trivedi, Manish Shrivastava, Rajesh Kumar

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments 8 pages

2310.01045 2024-02-13 cs.CL 57%

Tool-Augmented Reward Modeling

Lei Li, Yekun Chai, Shuohuan Wang, Yu Sun, Hao Tian, Ningyu Zhang, Hua Wu

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments ICLR 2024 Spotlight

2402.04004 2024-02-12 cs.LG 57%

Understanding the Effect of Noise in LLM Training Data with Algorithmic Chains of Thought

Alex Havrilla, Maia Iyer

专题命中数学推理：CoT(abstract)；分类 cs.LG

2402.00723 2024-02-02 cs.CL 57%

Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders

Yingji Zhang, Danilo S. Carvalho, Marco Valentino, Ian Pratt-Hartmann, Andre Freitas

专题命中数学推理：reasoning(abstract)；分类 cs.CL

2401.12869 2024-01-24 cs.AI 57%

TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks

Zhiruo Wang, Daniel Fried, Graham Neubig

专题命中数学推理：reasoning(abstract)；分类 cs.AI

2308.08090 2024-01-19 cs.CL 57%

Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation

Xinshuo Hu, Dongfang Li, Baotian Hu, Zihao Zheng, Zhenyu Liu, Min Zhang

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments AAAI 2024; The first two authors contributed equally to this paper

2312.04333 2024-01-10 cs.CL 57%

Is Bigger and Deeper Always Better? Probing LLaMA Across Scales and Layers

Nuo Chen, Ning Wu, Shining Liang, Ming Gong, Linjun Shou, Dongmei Zhang, Jia Li

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments 15 pages

2308.06744 2023-12-05 cs.CL 57%

Token-Scaled Logit Distillation for Ternary Weight Generative Language Models

Minsoo Kim, Sihwa Lee, Janghwan Lee, Sukjin Hong, Du-Seong Chang, Wonyong Sung, Jungwook Choi

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments NeurIPS 2023 Camera Ready

2311.07961 2023-11-15 cs.CL 57%

The ART of LLM Refinement: Ask, Refine, and Trust

Kumar Shridhar, Koustuv Sinha, Andrew Cohen, Tianlu Wang, Ping Yu, Ram Pasunuru, Mrinmaya Sachan, Jason Weston, Asli Celikyilmaz

专题命中数学推理：reasoning(abstract)；分类 cs.CL

2309.12161 2023-11-02 cs.CL 57%

Code Soliloquies for Accurate Calculations in Large Language Models

Shashank Sonkar, MyCo Le, Xinghe Chen, Naiming Liu, Debshila Basu Mallick, Richard G. Baraniuk

专题命中数学推理：reasoning(abstract)；分类 cs.CL

2310.13615 2023-10-23 cs.CL 57%

Three Questions Concerning the Use of Large Language Models to Facilitate Mathematics Learning

An-Zi Yen, Wei-Ling Hsu

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments Accepted by EMNLP 2023 Findings

2310.10047 2023-10-17 cs.CL 57%

Improving Large Language Model Fine-tuning for Solving Math Problems

Yixin Liu, Avi Singh, C. Daniel Freeman, John D. Co-Reyes, Peter J. Liu

专题命中数学推理：verifier(abstract)；分类 cs.CL

2310.10035 2023-10-17 cs.CL 57%

Empirical Study of Zero-Shot NER with ChatGPT

Tingyu Xie, Qi Li, Jian Zhang, Yan Zhang, Zuozhu Liu, Hongwei Wang

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments Accepted to EMNLP 2023 (Main Conference)

2304.01933 2023-10-10 cs.CL 57%

LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models

Zhiqiang Hu, Lei Wang, Yihuai Lan, Wanyu Xu, Ee-Peng Lim, Lidong Bing, Xing Xu, Soujanya Poria, Roy Ka-Wei Lee

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments EMNLP 2023. The code of our framework can be found at AGI-Edgerunners/LLM-Adapters" target="_blank" rel="noopener">https://github.com/AGI-Edgerunners/LLM-Adapters. We will keep all of the code open-source and continue to update the framework with new adapters, LLMs, and tasks

2309.16609 2023-09-29 cs.CL 57%

Qwen Technical Report

Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, Binyuan Hui, Luo Ji, Mei Li, Junyang Lin, Runji Lin, Dayiheng Liu, Gao Liu, Chengqiang Lu, Keming Lu, Jianxin Ma, Rui Men, Xingzhang Ren, Xuancheng Ren, Chuanqi Tan, Sinan Tan, Jianhong Tu, Peng Wang, Shijie Wang, Wei Wang, Shengguang Wu, Benfeng Xu, Jin Xu, An Yang, Hao Yang, Jian Yang, Shusheng Yang, Yang Yao, Bowen Yu, Hongyi Yuan, Zheng Yuan, Jianwei Zhang, Xingxuan Zhang, Yichang Zhang, Zhenru Zhang, Chang Zhou, Jingren Zhou, Xiaohuan Zhou, Tianhang Zhu

专题命中数学推理：planning(abstract)；分类 cs.CL

Comments 59 pages, 5 figures

2309.05529 2023-09-12 cs.AI math.ST stat.TH 57%

On the meaning of uncertainty for ethical AI: philosophy and practice

Cassandra Bird, Daniel Williamson, Sabina Leonelli

专题命中数学推理：reasoning(abstract)；分类 cs.AI

Comments 26 pages, 2 figures

2308.14732 2023-08-29 cs.AI 57%

Bayesian artificial brain with ChatGPT

Renato A. Krohling

专题命中数学推理：reasoning(abstract)；分类 cs.AI

2307.03381 2023-07-10 cs.LG 57%

Teaching Arithmetic to Small Transformers

Nayoung Lee, Kartik Sreenivasan, Jason D. Lee, Kangwook Lee, Dimitris Papailiopoulos

专题命中数学推理：chain-of-thought(abstract)；分类 cs.LG

2210.17017 2023-06-28 cs.CL cs.SD eess.AS 57%

Blank Collapse: Compressing CTC emission for the faster decoding

Minkyu Jung, Ohhyeok Kwon, Seunghyun Seo, Soonshin Seo

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments Accepted in Interspeech 2023

2304.10977 2023-04-24 cs.CL stat.ML 57%

Evaluating Transformer Language Models on Arithmetic Operations Using Number Decomposition

Matteo Muffo, Aldo Cocco, Enrico Bertino

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments 7 pages, 1 figure, published at LREC 2022

Journal ref Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022), pages 291-297

2302.07974 2023-02-17 cs.CL 57%

Tree-Based Representation and Generation of Natural and Mathematical Language

Alexander Scarlatos, Andrew Lan

专题命中数学推理：reasoning(abstract)；分类 cs.CL

2302.03145 2023-02-08 cs.CL cs.SC 57%

Techniques to Improve Neural Math Word Problem Solvers

Youyuan Zhang

专题命中数学推理：reasoning(abstract)；分类 cs.CL

2205.10513 2022-11-23 cs.AI 57%

Computable Artificial General Intelligence

Michael Timothy Bennett

专题命中数学推理：reasoning(abstract)；分类 cs.AI

Comments Experiment code available on TechRxiv: https://www.techrxiv.org/articles/preprint/Computable_Artificial_General_Intelligence/19740190

1. 数学推理 3222 篇

Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents

Bridging the Gap between Different Vocabularies for LLM Ensemble

Stable Code Technical Report

Teaching Language Models to Self-Improve through Interactive Demonstrations

RankPrompt: Step-by-Step Comparisons Make Language Models Better Reasoners

Machine learning and information theory concepts towards an AI Mathematician

SAIE Framework: Support Alone Isn't Enough -- Advancing LLM Training with Adversarial Remarks

Can LLMs Compute with Reasons?

Tool-Augmented Reward Modeling

Understanding the Effect of Noise in LLM Training Data with Algorithmic Chains of Thought

Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders

TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks

Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation

Is Bigger and Deeper Always Better? Probing LLaMA Across Scales and Layers

Token-Scaled Logit Distillation for Ternary Weight Generative Language Models

The ART of LLM Refinement: Ask, Refine, and Trust

Code Soliloquies for Accurate Calculations in Large Language Models

Three Questions Concerning the Use of Large Language Models to Facilitate Mathematics Learning

Improving Large Language Model Fine-tuning for Solving Math Problems

Empirical Study of Zero-Shot NER with ChatGPT

LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models

Qwen Technical Report

On the meaning of uncertainty for ethical AI: philosophy and practice

Bayesian artificial brain with ChatGPT

Teaching Arithmetic to Small Transformers

Blank Collapse: Compressing CTC emission for the faster decoding

Evaluating Transformer Language Models on Arithmetic Operations Using Number Decomposition

Tree-Based Representation and Generation of Natural and Mathematical Language

Techniques to Improve Neural Math Word Problem Solvers

Computable Artificial General Intelligence