大模型推理能力 - arXivDaily 专题

2405.17430 2024-07-30 cs.CV cs.AI cs.CL cs.LG 67%

Matryoshka Multimodal Models

Mu Cai, Jianwei Yang, Jianfeng Gao, Yong Jae Lee

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Project Page: https://matryoshka-mm.github.io/

2302.04449 2024-07-23 cs.LG cs.AI cs.CL 67%

Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals

Yue Wu, Yewen Fan, Paul Pu Liang, Amos Azaria, Yuanzhi Li, Tom M. Mitchell

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2406.18676 2024-07-19 cs.CL cs.AI cs.LG 67%

Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation

Guanting Dong, Yutao Zhu, Chenghao Zhang, Zechen Wang, Zhicheng Dou, Ji-Rong Wen

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Work in progress

2406.13173 2024-07-17 cs.CV cs.AI cs.CL cs.LG 67%

Biomedical Visual Instruction Tuning with Clinician Preference Alignment

Hejie Cui, Lingjun Mao, Xin Liang, Jieyu Zhang, Hui Ren, Quanzheng Li, Xiang Li, Carl Yang

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2403.12014 2024-07-15 cs.CL cs.AI cs.LG 67%

EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents

Abhay Zala, Jaemin Cho, Han Lin, Jaehong Yoon, Mohit Bansal

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments COLM 2024; First two authors contributed equally; Project website: https://envgen-llm.github.io/

2403.10854 2024-07-12 cs.CV 67%

A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment

Tianhe Wu, Kede Ma, Jie Liang, Yujiu Yang, Lei Zhang

专题命中其他推理：reasoning(abstract)；chain-of-thought(abstract)

2402.13228 2024-07-04 cs.CL cs.AI cs.LG 67%

Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive

Arka Pal, Deep Karkhanis, Samuel Dooley, Manley Roberts, Siddartha Naidu, Colin White

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2406.04031 2024-07-02 cs.CV cs.CR 67%

Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt

Zonghao Ying, Aishan Liu, Tianyuan Zhang, Zhengmin Yu, Siyuan Liang, Xianglong Liu, Dacheng Tao

专题命中其他推理：reasoning(abstract)；chain-of-thought(abstract)

2402.05602 2024-06-11 cs.CL cs.AI cs.CV cs.LG 67%

AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers

Reduan Achtibat, Sayed Mohammad Vakilzadeh Hatefi, Maximilian Dreyer, Aakriti Jain, Thomas Wiegand, Sebastian Lapuschkin, Wojciech Samek

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2401.06102 2024-06-10 cs.CL cs.AI cs.LG 67%

Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models

Asma Ghandeharioun, Avi Caciularu, Adam Pearce, Lucas Dixon, Mor Geva

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ICML 2024 (to appear)

2405.14863 2024-05-24 cs.CL cs.AI cs.LG 67%

A Nurse is Blue and Elephant is Rugby: Cross Domain Alignment in Large Language Models Reveal Human-like Patterns

Asaf Yehudai, Taelin Karidi, Gabriel Stanovsky, Ariel Goldstein, Omri Abend

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments CogSci

2403.19669 2024-05-13 cs.LG cs.AI cs.CL cs.CV 67%

Analyzing the Roles of Language and Vision in Learning from Limited Data

Allison Chen, Ilia Sucholutsky, Olga Russakovsky, Thomas L. Griffiths

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 8 pages, 4 figures

2402.07148 2024-04-02 cond-mat.soft cond-mat.dis-nn cs.AI cs.CL cs.LG q-bio.QM 67%

X-LoRA: Mixture of Low-Rank Adapter Experts, a Flexible Framework for Large Language Models with Applications in Protein Mechanics and Molecular Design

Eric L. Buehler, Markus J. Buehler

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2403.18406 2024-03-28 cs.CV cs.AI cs.CL cs.LG 67%

An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM

Wonkyun Kim, Changin Choi, Wonseok Lee, Wonjong Rhee

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Our code is available at https://github.com/imagegridworth/IG-VLM

2403.10949 2024-03-27 cs.CL cs.AI cs.LG 67%

SelfIE: Self-Interpretation of Large Language Model Embeddings

Haozhe Chen, Carl Vondrick, Chengzhi Mao

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2305.11490 2024-03-19 cs.CV cs.AI cs.CL cs.LG 67%

LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation

Suhyeon Lee, Won Jun Kim, Jinho Chang, Jong Chul Ye

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 21 pages, 8 figures; ICLR 2024 (poster)

2402.16038 2024-02-27 cs.CL cs.AI cs.LG 67%

Deep Learning Approaches for Improving Question Answering Systems in Hepatocellular Carcinoma Research

Shuning Huo, Yafei Xiang, Hanyi Yu, Mengran Zhu, Yulu Gong

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2311.09114 2024-02-27 cs.CL cs.AI cs.LG 67%

Ever: Mitigating Hallucination in Large Language Models through Real-Time Verification and Rectification

Haoqiang Kang, Juntong Ni, Huaxiu Yao

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2402.07069 2024-02-13 cs.LG cs.AI cs.CL 67%

Using Large Language Models to Automate and Expedite Reinforcement Learning with Reward Machine

Shayan Meshkat Alsadat, Jean-Raphael Gaglione, Daniel Neider, Ufuk Topcu, Zhe Xu

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

2402.00070 2024-02-02 cs.NE cs.AI cs.CL cs.LG 67%

EvoMerge: Neuroevolution for Large Language Models

Yushu Jiang

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments The current submission is the first draft, published for the sole purpose of sharing an idea and encouraging community effort. A more consolidated version may come later

2309.15427 2024-01-01 cs.CL cs.AI cs.LG 67%

Graph Neural Prompting with Large Language Models

Yijun Tian, Huan Song, Zichen Wang, Haozhu Wang, Ziqing Hu, Fang Wang, Nitesh V. Chawla, Panpan Xu

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted by AAAI 2024

2312.06820 2023-12-13 cs.AI cs.CL cs.LG stat.ME 67%

Extracting Self-Consistent Causal Insights from Users Feedback with LLMs and In-context Learning

Sara Abdali, Anjali Parikh, Steve Lim, Emre Kiciman

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2311.16079 2023-11-28 cs.CL cs.AI cs.LG 67%

MEDITRON-70B: Scaling Medical Pretraining for Large Language Models

Zeming Chen, Alejandro Hernández Cano, Angelika Romanou, Antoine Bonnet, Kyle Matoba, Francesco Salvi, Matteo Pagliardini, Simin Fan, Andreas Köpf, Amirkeivan Mohtashami, Alexandre Sallinen, Alireza Sakhaeirad, Vinitra Swamy, Igor Krawczuk, Deniz Bayazit, Axel Marmet, Syrielle Montariol, Mary-Anne Hartley, Martin Jaggi, Antoine Bosselut

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2305.14930 2023-11-28 cs.AI cs.CL cs.LG 67%

In-Context Impersonation Reveals Large Language Models' Strengths and Biases

Leonard Salewski, Stephan Alaniz, Isabel Rio-Torto, Eric Schulz, Zeynep Akata

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Published in NeurIPS 2023 (Spotlight)

2310.00034 2023-11-09 cs.LG cs.AI cs.CL 67%

PB-LLM: Partially Binarized Large Language Models

Yuzhang Shang, Zhihang Yuan, Qiang Wu, Zhen Dong

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Frist work using network binarization for large language model compression

2305.14926 2023-10-24 cs.CL cs.AI cs.LG 67%

Universal Self-Adaptive Prompting

Xingchen Wan, Ruoxi Sun, Hootan Nakhost, Hanjun Dai, Julian Martin Eisenschlos, Sercan O. Arik, Tomas Pfister

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments EMNLP 2023 (Main). 10 pages, 5 figures, 4 tables (26 pages, 9 figures and 13 tables including references and appendices)

2305.08732 2023-10-12 cs.CL cs.AI cs.IR cs.LG 67%

Knowledge Rumination for Pre-trained Language Models

Yunzhi Yao, Peng Wang, Shengyu Mao, Chuanqi Tan, Fei Huang, Huajun Chen, Ningyu Zhang

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments EMNLP 2023

2310.06825 2023-10-11 cs.CL cs.AI cs.LG 67%

Mistral 7B

Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, Lélio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Models and code are available at https://mistral.ai/news/announcing-mistral-7b/

2309.10346 2023-09-20 cs.LG cs.AI cs.CL 67%

Explaining Agent Behavior with Large Language Models

Xijia Zhang, Yue Guo, Simon Stepputtis, Katia Sycara, Joseph Campbell

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Human Multi-Robot Interaction Workshop at IROS 2023

2304.09960 2023-09-15 cs.CL cs.AI cs.LG 67%

A Latent Space Theory for Emergent Abilities in Large Language Models

Hui Jiang

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

Comments 17 pages, 3 figures

1. 其他推理 5849 篇

Matryoshka Multimodal Models

Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals

Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation

Biomedical Visual Instruction Tuning with Clinician Preference Alignment

EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents

A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment

Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive

Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt

AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers

Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models

A Nurse is Blue and Elephant is Rugby: Cross Domain Alignment in Large Language Models Reveal Human-like Patterns

Analyzing the Roles of Language and Vision in Learning from Limited Data

X-LoRA: Mixture of Low-Rank Adapter Experts, a Flexible Framework for Large Language Models with Applications in Protein Mechanics and Molecular Design

An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM

SelfIE: Self-Interpretation of Large Language Model Embeddings

LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation

Deep Learning Approaches for Improving Question Answering Systems in Hepatocellular Carcinoma Research

Ever: Mitigating Hallucination in Large Language Models through Real-Time Verification and Rectification

Using Large Language Models to Automate and Expedite Reinforcement Learning with Reward Machine

EvoMerge: Neuroevolution for Large Language Models

Graph Neural Prompting with Large Language Models

Extracting Self-Consistent Causal Insights from Users Feedback with LLMs and In-context Learning

MEDITRON-70B: Scaling Medical Pretraining for Large Language Models

In-Context Impersonation Reveals Large Language Models' Strengths and Biases

PB-LLM: Partially Binarized Large Language Models

Universal Self-Adaptive Prompting

Knowledge Rumination for Pre-trained Language Models

Mistral 7B

Explaining Agent Behavior with Large Language Models

A Latent Space Theory for Emergent Abilities in Large Language Models