大模型推理能力 - arXivDaily 专题

2406.18312 2024-08-29 cs.CL cs.AI 62%

AI-native Memory: A Pathway from LLMs Towards AGI

Jingbo Shang, Zai Zheng, Jiale Wei, Xiang Ying, Felix Tao, Mindverse Team

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

2405.05109 2024-08-27 cs.CL cs.AI 62%

QFMTS: Generating Query-Focused Summaries over Multi-Table Inputs

Weijia Zhang, Vaishali Pal, Jia-Hong Huang, Evangelos Kanoulas, Maarten de Rijke

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

Comments Accepted by the 27th European Conference on Artificial Intelligence (ECAI-2024)

2407.16160 2024-08-22 cs.AI cs.CL 62%

UniMEL: A Unified Framework for Multimodal Entity Linking with Large Language Models

Liu Qi, He Yongyi, Lian Defu, Zheng Zhi, Xu Tong, Liu Che, Chen Enhong

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

Comments CIKM 2024. The first two authors contributed equally to this work

2303.13988 2024-08-09 cs.CL cs.AI 62%

Machine Psychology

Thilo Hagendorff, Ishita Dasgupta, Marcel Binz, Stephanie C. Y. Chan, Andrew Lampinen, Jane X. Wang, Zeynep Akata, Eric Schulz

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

2408.00584 2024-08-02 cs.CL cs.AI 62%

Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses

Gabriele Sarti, Tommaso Caselli, Malvina Nissim, Arianna Bisazza

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

Comments Code: https://github.com/gsarti/verbalized-rebus. Artifacts: https://huggingface.co/collections/gsarti/verbalized-rebus-clic-it-2024-66ab8f11cb04e68bdf4fb028

2407.21040 2024-08-01 cs.AI cs.CL cs.DB cs.SE 62%

Towards Automated Data Sciences with Natural Language and SageCopilot: Practices and Lessons Learned

Yuan Liao, Jiang Bian, Yuhui Yun, Shuo Wang, Yubo Zhang, Jiaming Chu, Tao Wang, Kewei Li, Yuchen Li, Xuhong Li, Shilei Ji, Haoyi Xiong

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

2407.17545 2024-07-26 cs.SE cs.AI cs.CL 62%

Large Language Models for Anomaly Detection in Computational Workflows: from Supervised Fine-Tuning to In-Context Learning

Hongwei Jin, George Papadimitriou, Krishnan Raghavan, Pawel Zuk, Prasanna Balaprakash, Cong Wang, Anirban Mandal, Ewa Deelman

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

Comments 12 pages, 14 figures, paper is accepted by SC'24, source code, see: https://github.com/PoSeiDon-Workflows/LLM_AD

2407.15366 2024-07-23 cs.CL cs.AI cs.CY 62%

Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias

Rongwu Xu, Zi'an Zhou, Tianwei Zhang, Zehan Qi, Su Yao, Ke Xu, Wei Xu, Han Qiu

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

2404.07922 2024-07-17 cs.CL cs.CV cs.LG 62%

LaVy: Vietnamese Multimodal Large Language Model

Chi Tran, Huong Le Thanh

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

Comments 5 pages

2312.12736 2024-07-04 cs.CL cs.LG 62%

Learning and Forgetting Unsafe Examples in Large Language Models

Jiachen Zhao, Zhun Deng, David Madras, James Zou, Mengye Ren

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

Comments accepted by ICML 24

2407.02203 2024-07-03 cs.CL cs.AI 62%

Automatic Adaptation Rule Optimization via Large Language Models

Yusei Ishimizu, Jialong Li, Jinglue Xu, Jinyu Cai, Hitoshi Iba, Kenji Tei

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

2406.11217 2024-06-25 cs.AI cs.CL cs.CV physics.ao-ph 62%

WeatherQA: Can Multimodal Language Models Reason about Severe Weather?

Chengqian Ma, Zhanxiang Hua, Alexandra Anderson-Frey, Vikram Iyer, Xin Liu, Lianhui Qin

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

Comments 26 pages, 9 figures

2406.13121 2024-06-21 cs.CL cs.AI cs.IR 62%

Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?

Jinhyuk Lee, Anthony Chen, Zhuyun Dai, Dheeru Dua, Devendra Singh Sachan, Michael Boratko, Yi Luan, Sébastien M. R. Arnold, Vincent Perot, Siddharth Dalmia, Hexiang Hu, Xudong Lin, Panupong Pasupat, Aida Amini, Jeremy R. Cole, Sebastian Riedel, Iftekhar Naim, Ming-Wei Chang, Kelvin Guu

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

Comments 29 pages. Dataset available at https://github.com/google-deepmind/loft

2402.15301 2024-06-19 cs.CL cs.LG stat.ME 62%

Causal Graph Discovery with Retrieval-Augmented Generation based Large Language Models

Yuzhe Zhang, Yipeng Zhang, Yidong Gan, Lina Yao, Chen Wang

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

2406.07794 2024-06-18 cs.CL cs.AI 62%

Making Task-Oriented Dialogue Datasets More Natural by Synthetically Generating Indirect User Requests

Amogh Mannekote, Jinseok Nam, Ziming Li, Jian Gao, Kristy Elizabeth Boyer, Bonnie J. Dorr

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

2402.11684 2024-06-18 cs.CL cs.AI 62%

ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models

Guiming Hardy Chen, Shunian Chen, Ruifei Zhang, Junying Chen, Xiangbo Wu, Zhiyi Zhang, Zhihong Chen, Jianquan Li, Xiang Wan, Benyou Wang

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

Comments 22 pages

2406.10261 2024-06-18 cs.CL cs.AI 62%

FoodSky: A Food-oriented Large Language Model that Passes the Chef and Dietetic Examination

Pengfei Zhou, Weiqing Min, Chaoran Fu, Ying Jin, Mingyu Huang, Xiangyang Li, Shuhuan Mei, Shuqiang Jiang

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

Comments 32 pages, 19 figures

2406.07572 2024-06-13 cs.AI cs.CE cs.LG 62%

Domain-specific ReAct for physics-integrated iterative modeling: A case study of LLM agents for gas path analysis of gas turbines

Tao Song, Yuwei Fan, Chenlong Feng, Keyu Song, Chao Liu, Dongxiang Jiang

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

2403.08337 2024-06-13 eess.SY cs.AI cs.LG cs.SY 62%

LLM-Assisted Light: Leveraging Large Language Model Capabilities for Human-Mimetic Traffic Signal Control in Complex Urban Environments

Maonan Wang, Aoyu Pang, Yuheng Kan, Man-On Pun, Chung Shue Chen, Bo Huang

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

Comments 20 pages, 11 figures

2401.02009 2024-06-10 cs.CL cs.AI 62%

Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives

Wenqi Zhang, Yongliang Shen, Linjuan Wu, Qiuying Peng, Jun Wang, Yueting Zhuang, Weiming Lu

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

Comments Accepted by ACL 2024 Main

2406.04276 2024-06-07 cs.LG cs.AI 62%

Generative AI-in-the-loop: Integrating LLMs and GPTs into the Next Generation Networks

Han Zhang, Akram Bin Sediq, Ali Afana, Melike Erol-Kantarci

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

2404.07677 2024-06-05 cs.CL cs.AI 62%

ODA: Observation-Driven Agent for integrating LLMs and Knowledge Graphs

Lei Sun, Zhengwei Tao, Youdi Li, Hiroshi Arakawa

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

Comments LLM+KG

2310.00809 2024-06-05 cs.LG cs.AI stat.ME stat.ML 62%

Towards Causal Foundation Model: on Duality between Causal Inference and Attention

Jiaqi Zhang, Joel Jennings, Agrin Hilmkil, Nick Pawlowski, Cheng Zhang, Chao Ma

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

2405.20846 2024-06-03 cs.CL cs.AI 62%

Don't Buy it! Reassessing the Ad Understanding Abilities of Contrastive Multimodal Models

A. Bavaresco, A. Testoni, R. Fernández

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

Comments Accepted to the main conference ACL 2024

2405.17438 2024-05-29 cs.PL cs.AI cs.LG 62%

An LLM-Tool Compiler for Fused Parallel Function Calling

Simranjit Singh, Andreas Karatzas, Michael Fore, Iraklis Anagnostopoulos, Dimitrios Stamoulis

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

2312.17259 2024-05-29 cs.CL cs.AI 62%

Empowering Working Memory for Large Language Model Agents

Jing Guo, Nan Li, Jianchuan Qi, Hang Yang, Ruiqiao Li, Yuzhen Feng, Si Zhang, Ming Xu

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

2405.13039 2024-05-24 cs.CL cs.AI 62%

Surgical Feature-Space Decomposition of LLMs: Why, When and How?

Arnav Chavan, Nahush Lele, Deepak Gupta

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

Comments Accepted at ACL 2024

2405.11403 2024-05-21 cs.CL cs.AI 62%

MapCoder: Multi-Agent Code Generation for Competitive Problem Solving

Md. Ashraful Islam, Mohammed Eunus Ali, Md Rizwan Parvez

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

2405.08644 2024-05-15 cs.CL cs.AI 62%

Thinking Tokens for Language Modeling

David Herel, Tomas Mikolov

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

Comments AITP 2023 (May 10, 2023)

2405.01585 2024-05-06 cs.AI cs.CL cs.IR 62%

Tabular Embedding Model (TEM): Finetuning Embedding Models For Tabular RAG Applications

Sujit Khanna, Shishir Subedi

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

Comments 11 pages, 5 figures

1. 复杂问题求解 5004 篇

AI-native Memory: A Pathway from LLMs Towards AGI

QFMTS: Generating Query-Focused Summaries over Multi-Table Inputs

UniMEL: A Unified Framework for Multimodal Entity Linking with Large Language Models

Machine Psychology

Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses

Towards Automated Data Sciences with Natural Language and SageCopilot: Practices and Lessons Learned

Large Language Models for Anomaly Detection in Computational Workflows: from Supervised Fine-Tuning to In-Context Learning

Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias

LaVy: Vietnamese Multimodal Large Language Model

Learning and Forgetting Unsafe Examples in Large Language Models

Automatic Adaptation Rule Optimization via Large Language Models

WeatherQA: Can Multimodal Language Models Reason about Severe Weather?

Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?

Causal Graph Discovery with Retrieval-Augmented Generation based Large Language Models

Making Task-Oriented Dialogue Datasets More Natural by Synthetically Generating Indirect User Requests

ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models

FoodSky: A Food-oriented Large Language Model that Passes the Chef and Dietetic Examination

Domain-specific ReAct for physics-integrated iterative modeling: A case study of LLM agents for gas path analysis of gas turbines

LLM-Assisted Light: Leveraging Large Language Model Capabilities for Human-Mimetic Traffic Signal Control in Complex Urban Environments

Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives

Generative AI-in-the-loop: Integrating LLMs and GPTs into the Next Generation Networks

ODA: Observation-Driven Agent for integrating LLMs and Knowledge Graphs

Towards Causal Foundation Model: on Duality between Causal Inference and Attention

Don't Buy it! Reassessing the Ad Understanding Abilities of Contrastive Multimodal Models

An LLM-Tool Compiler for Fused Parallel Function Calling

Empowering Working Memory for Large Language Model Agents

Surgical Feature-Space Decomposition of LLMs: Why, When and How?

MapCoder: Multi-Agent Code Generation for Competitive Problem Solving

Thinking Tokens for Language Modeling

Tabular Embedding Model (TEM): Finetuning Embedding Models For Tabular RAG Applications