大模型推理能力 - arXivDaily 专题

2405.11222 2024-05-21 cs.CL 57%

Transformer based neural networks for emotion recognition in conversations

Claudiu Creanga, Liviu P. Dinu

专题命中其他推理：reasoning(abstract)；分类 cs.CL

2405.10959 2024-05-21 cs.CY cs.LG 57%

Foundation Models for Education: Promises and Prospects

Tianlong Xu, Richard Tong, Jing Liang, Xing Fan, Haoyang Li, Qingsong Wen

专题命中其他推理：reasoning(abstract)；分类 cs.LG

Comments Accepted by IEEE Intelligent Systems

2405.00390 2024-05-21 cs.CL 57%

CofiPara: A Coarse-to-fine Paradigm for Multimodal Sarcasm Target Identification with Large Multimodal Models

Hongzhan Lin, Zixin Chen, Ziyang Luo, Mingfei Cheng, Jing Ma, Guang Chen

专题命中其他推理：reasoning(abstract)；分类 cs.CL

Comments ACL 2024

2405.08154 2024-05-15 cs.HC cs.AI 57%

LLM Theory of Mind and Alignment: Opportunities and Risks

Winnie Street

专题命中其他推理：reasoning(abstract)；分类 cs.AI

Journal ref Proceedings of Workshop on Theory of Mind in Human-AI Interaction at CHI 2024 (ToMinHAI at CHI 2024)

2405.08007 2024-05-15 cs.HC cs.AI 57%

People cannot distinguish GPT-4 from a human in a Turing test

Cameron R. Jones, Benjamin K. Bergen

专题命中其他推理：reasoning(abstract)；分类 cs.AI

Comments 23 pages, 13 figures

2405.05957 2024-05-10 cs.CL 57%

OpenBA-V2: Reaching 77.3% High Compression Ratio with Fast Multi-Stage Pruning

Dan Qiao, Yi Su, Pinzheng Wang, Jing Ye, Wenjing Xie, Yuechi Zhou, Yuyang Ding, Zecheng Tang, Jikai Wang, Yixin Ji, Yue Wang, Pei Guo, Zechen Sun, Zikang Zhang, Juntao Li, Pingfu Chao, Wenliang Chen, Guohong Fu, Guodong Zhou, Qiaoming Zhu, Min Zhang

专题命中其他推理：reasoning(abstract)；分类 cs.CL

2310.08842 2024-05-08 cs.AI 57%

A Case-Based Persistent Memory for a Large Language Model

Ian Watson

专题命中其他推理：reasoning(abstract)；分类 cs.AI

Comments 8 pages, 1 figure

2404.09491 2024-05-07 cs.LG 57%

Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning

Sungwon Han, Jinsung Yoon, Sercan O Arik, Tomas Pfister

专题命中其他推理：reasoning(abstract)；分类 cs.LG

Comments Accepted to ICML, 2024

2405.02712 2024-05-07 cs.CL 57%

CoE-SQL: In-Context Learning for Multi-Turn Text-to-SQL with Chain-of-Editions

Hanchong Zhang, Ruisheng Cao, Hongshen Xu, Lu Chen, Kai Yu

专题命中其他推理：reasoning(abstract)；分类 cs.CL

2405.01942 2024-05-06 cs.CL 57%

CRCL at SemEval-2024 Task 2: Simple prompt optimizations

Clément Brutti-Mairesse, Loïc Verlingue

专题命中其他推理：CoT(abstract)；分类 cs.CL

Journal ref SemEval-2024

2405.01359 2024-05-03 cs.CL physics.acc-ph 57%

GAIA: A General AI Assistant for Intelligent Accelerator Operations

Frank Mayet

专题命中其他推理：reasoning(abstract)；分类 cs.CL

2405.00467 2024-05-02 cs.CL 57%

Harnessing the Power of Multiple Minds: Lessons Learned from LLM Routing

KV Aditya Srivatsa, Kaushal Kumar Maurya, Ekaterina Kochmar

专题命中其他推理：reasoning(abstract)；分类 cs.CL

Comments Accepted to Workshop on Insights from Negative Results in NLP 2024 (co-located with NAACL 2024)

2312.09801 2024-05-02 cs.CL 57%

ProCoT: Stimulating Critical Thinking and Writing of Students through Engagement with Large Language Models (LLMs)

Tosin Adewumi, Lama Alkhaled, Claudia Buck, Sergio Hernandez, Saga Brilioth, Mkpe Kekung, Yelvin Ragimov, Elisa Barney

专题命中其他推理：chain-of-thought(abstract)；分类 cs.CL

Comments 8 pages, 4 figures

2404.19737 2024-05-01 cs.CL 57%

Better & Faster Large Language Models via Multi-token Prediction

Fabian Gloeckle, Badr Youbi Idrissi, Baptiste Rozière, David Lopez-Paz, Gabriel Synnaeve

专题命中其他推理：reasoning(abstract)；分类 cs.CL

2404.17460 2024-04-29 cs.CL 57%

Ruffle&Riley: Insights from Designing and Evaluating a Large Language Model-Based Conversational Tutoring System

Robin Schmucker, Meng Xia, Amos Azaria, Tom Mitchell

专题命中其他推理：reasoning(abstract)；分类 cs.CL

Comments arXiv admin note: substantial text overlap with arXiv:2310.01420

2404.15317 2024-04-25 cs.SE cs.HC cs.LG 57%

Concept-Guided LLM Agents for Human-AI Safety Codesign

Florian Geissler, Karsten Roscher, Mario Trapp

专题命中其他推理：reasoning(abstract)；分类 cs.LG

Comments 5 pages

Journal ref Proceedings of the AAAI-make Spring Symposium, 2024

2404.14779 2024-04-24 cs.CL 57%

Med42 -- Evaluating Fine-Tuning Strategies for Medical LLMs: Full-Parameter vs. Parameter-Efficient Approaches

Clément Christophe, Praveen K Kanithi, Prateek Munjal, Tathagata Raha, Nasir Hayat, Ronnie Rajan, Ahmed Al-Mahrooqi, Avani Gupta, Muhammad Umar Salman, Gurpreet Gosal, Bhargav Kanakiya, Charles Chen, Natalia Vassilieva, Boulbaba Ben Amor, Marco AF Pimentel, Shadab Khan

专题命中其他推理：reasoning(abstract)；分类 cs.CL

Comments Published at AAAI 2024 Spring Symposium - Clinical Foundation Models

2404.01855 2024-04-24 cs.IR cs.AI 57%

Where to Move Next: Zero-shot Generalization of LLMs for Next POI Recommendation

Shanshan Feng, Haoming Lyu, Caishun Chen, Yew-Soon Ong

专题命中其他推理：reasoning(abstract)；分类 cs.AI

2310.19268 2024-04-23 cs.SI cs.CL cs.CY 57%

Moral Sparks in Social Media Narratives

Ruijie Xi, Munindar P. Singh

专题命中其他推理：reasoning(abstract)；分类 cs.CL

2311.01949 2024-04-19 cs.CL 57%

Hint-enhanced In-Context Learning wakes Large Language Models up for knowledge-intensive tasks

Yifan Wang, Qingyan Guo, Xinzhe Ni, Chufan Shi, Lemao Liu, Haiyun Jiang, Yujiu Yang

专题命中其他推理：reasoning(abstract)；分类 cs.CL

Comments Accepted by ICASSP 2024

2307.12798 2024-04-18 cs.CL cs.IR 57%

RRAML: Reinforced Retrieval Augmented Machine Learning

Andrea Bacciu, Florin Cuconasu, Federico Siciliano, Fabrizio Silvestri, Nicola Tonellotto, Giovanni Trappolini

专题命中其他推理：reasoning(abstract)；分类 cs.CL

Journal ref CEUR Workshop Proceedings (2023, Vol. 3537, pp. 29-37)

2403.04772 2024-04-17 cs.AI cs.LO 57%

Representing Pedagogic Content Knowledge Through Rough Sets

A Mani

专题命中其他推理：reasoning(abstract)；分类 cs.AI

Comments 15+ pages

2402.10688 2024-04-17 cs.CL 57%

Towards Uncovering How Large Language Model Works: An Explainability Perspective

Haiyan Zhao, Fan Yang, Bo Shen, Himabindu Lakkaraju, Mengnan Du

专题命中其他推理：reasoning(abstract)；分类 cs.CL

Comments 8 pages, 2 figures

2309.05452 2024-04-16 cs.CL 57%

Evaluating the Deductive Competence of Large Language Models

Spencer M. Seals, Valerie L. Shalin

专题命中其他推理：reasoning(abstract)；分类 cs.CL

Comments 17 pages, 7 figures, accepted to NAACL 2024

2304.06819 2024-04-16 cs.CV cs.AI q-bio.GN q-bio.QM q-bio.TO 57%

Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction

Guillaume Jaume, Anurag Vaidya, Richard Chen, Drew Williamson, Paul Liang, Faisal Mahmood

专题命中其他推理：reasoning(abstract)；分类 cs.AI

Comments Accepted to CVPR 2024

2310.06671 2024-04-16 cs.CL 57%

Making Large Language Models Perform Better in Knowledge Graph Completion

Yichi Zhang, Zhuo Chen, Lingbing Guo, Yajing Xu, Wen Zhang, Huajun Chen

专题命中其他推理：reasoning(abstract)；分类 cs.CL

Comments Working in progress

2404.08589 2024-04-15 cs.CV cs.AI 57%

Enhancing Visual Question Answering through Question-Driven Image Captions as Prompts

Övgü Özdemir, Erdem Akagündüz

专题命中其他推理：reasoning(abstract)；分类 cs.AI

Comments The paper has been accepted for presentation at CVPR 2024 Workshop on Prompting in Vision

2309.04284 2024-04-15 cs.LG 57%

Viewing the process of generating counterfactuals as a source of knowledge: a new approach for explaining classifiers

Vincent Lemaire, Nathan Le Boudec, Victor Guyomard, Françoise Fessant

专题命中其他推理：reasoning(abstract)；分类 cs.LG

Comments 8 pages

2311.07811 2024-04-11 cs.CL 57%

In-context Learning Generalizes, But Not Always Robustly: The Case of Syntax

Aaron Mueller, Albert Webson, Jackson Petty, Tal Linzen

专题命中其他推理：chain-of-thought(abstract)；分类 cs.CL

Comments Accepted to NAACL 2024

2404.05225 2024-04-09 cs.CV cs.CL 57%

LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding

Chuwei Luo, Yufan Shen, Zhaoqing Zhu, Qi Zheng, Zhi Yu, Cong Yao

专题命中其他推理：chain-of-thought(abstract)；分类 cs.CL

Comments CVPR 2024

1. 其他推理 5918 篇

Transformer based neural networks for emotion recognition in conversations

Foundation Models for Education: Promises and Prospects

CofiPara: A Coarse-to-fine Paradigm for Multimodal Sarcasm Target Identification with Large Multimodal Models

LLM Theory of Mind and Alignment: Opportunities and Risks

People cannot distinguish GPT-4 from a human in a Turing test

OpenBA-V2: Reaching 77.3% High Compression Ratio with Fast Multi-Stage Pruning

A Case-Based Persistent Memory for a Large Language Model

Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning

CoE-SQL: In-Context Learning for Multi-Turn Text-to-SQL with Chain-of-Editions

CRCL at SemEval-2024 Task 2: Simple prompt optimizations

GAIA: A General AI Assistant for Intelligent Accelerator Operations

Harnessing the Power of Multiple Minds: Lessons Learned from LLM Routing

ProCoT: Stimulating Critical Thinking and Writing of Students through Engagement with Large Language Models (LLMs)

Better & Faster Large Language Models via Multi-token Prediction

Ruffle&Riley: Insights from Designing and Evaluating a Large Language Model-Based Conversational Tutoring System

Concept-Guided LLM Agents for Human-AI Safety Codesign

Med42 -- Evaluating Fine-Tuning Strategies for Medical LLMs: Full-Parameter vs. Parameter-Efficient Approaches

Where to Move Next: Zero-shot Generalization of LLMs for Next POI Recommendation

Moral Sparks in Social Media Narratives

Hint-enhanced In-Context Learning wakes Large Language Models up for knowledge-intensive tasks

RRAML: Reinforced Retrieval Augmented Machine Learning

Representing Pedagogic Content Knowledge Through Rough Sets

Towards Uncovering How Large Language Model Works: An Explainability Perspective

Evaluating the Deductive Competence of Large Language Models

Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction

Making Large Language Models Perform Better in Knowledge Graph Completion

Enhancing Visual Question Answering through Question-Driven Image Captions as Prompts

Viewing the process of generating counterfactuals as a source of knowledge: a new approach for explaining classifiers

In-context Learning Generalizes, But Not Always Robustly: The Case of Syntax

LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding