语言大模型 / LLM - arXivDaily 专题

2406.06487 2024-11-06 cs.LG 57%

When is Multicalibration Post-Processing Necessary?

Dutch Hansen, Siddartha Devic, Preetum Nakkiran, Vatsal Sharan

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.LG

2411.00986 2024-11-05 cs.CY cs.AI q-bio.NC 57%

Taking AI Welfare Seriously

Robert Long, Jeff Sebo, Patrick Butlin, Kathleen Finlinson, Kyle Fish, Jacqueline Harding, Jacob Pfau, Toni Sims, Jonathan Birch, David Chalmers

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.AI

2410.22244 2024-10-30 cs.LG stat.ML 57%

Abrupt Learning in Transformers: A Case Study on Matrix Completion

Pulkit Gopalani, Ekdeep Singh Lubana, Wei Hu

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.LG

Comments NeurIPS 2024 Poster

2405.14312 2024-10-30 cs.CV cs.CL cs.MM 57%

Improving Gloss-free Sign Language Translation by Reducing Representation Density

Jinhui Ye, Xing Wang, Wenxiang Jiao, Junwei Liang, Hui Xiong

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL

Comments Accepted at NeurIPS'24; Representation Density Problem and Performance Drop in Gloss-free SLT

2410.20652 2024-10-29 cs.CL 57%

Visualizing attention zones in machine reading comprehension models

Yiming Cui, Wei-Nan Zhang, Ting Liu

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL

Comments 17 pages, published in STAR Protocols

2407.12315 2024-10-29 cs.CV cs.AI cs.HC cs.IR 57%

ModalChorus: Visual Probing and Alignment of Multi-modal Embeddings via Modal Fusion Map

Yilin Ye, Shishi Xiao, Xingchen Zeng, Wei Zeng

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.AI

Comments VIS 2024

2311.06647 2024-10-29 cs.CL 57%

Robust Text Classification: Analyzing Prototype-Based Networks

Zhivar Sourati, Darshan Deshpande, Filip Ilievski, Kiril Gashteovski, Sascha Saralajew

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL

Comments Published at EMNLP Findings 2024

2405.19345 2024-10-24 eess.SP cs.LG 57%

Review of Deep Representation Learning Techniques for Brain-Computer Interfaces and Recommendations

Pierre Guetschel, Sara Ahmadi, Michael Tangermann

专题命中知识编辑与模型理解：foundation model(abstract)；分类 cs.LG

Comments Submitted to: Journal of Neural Engineering (JNE)

Journal ref Journal of Neural Engineering (2024)

2410.15926 2024-10-22 cs.CV cs.CL 57%

Mitigating Object Hallucination via Concentric Causal Attention

Yun Xing, Yiheng Li, Ivan Laptev, Shijian Lu

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL

Comments To appear at NeurIPS 2024. Code is available at https://github.com/xing0047/cca-llava

2410.01820 2024-10-22 cs.CV cs.AI 57%

PixelBytes: Catching Unified Representation for Multimodal Generation

Fabien Furfaro

专题命中知识编辑与模型理解：foundation model(abstract)；分类 cs.AI

Comments 12 pages, 4 figures

2410.13887 2024-10-21 cs.SI cs.CL 57%

Observing the Southern US Culture of Honor Using Large-Scale Social Media Analysis

Juho Kim, Michael Guerzhoy

专题命中知识编辑与模型理解：LLM(abstract)；分类 cs.CL

Comments Accepted to SICon Workshop at the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024)

2307.09384 2024-10-21 cs.IR cs.CL 57%

ZeQR: Zero-shot Query Reformulation for Conversational Search

Dayu Yang, Yue Zhang, Hui Fang

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL

Comments Accepted by the 9th ACM SIGIR International Conference on the Theory of Information Retrieval

2406.14214 2024-10-15 cs.AI 57%

REVEAL-IT: REinforcement learning with Visibility of Evolving Agent poLicy for InTerpretability

Shuang Ao, Simon Khan, Haris Aziz, Flora D. Salim

专题命中知识编辑与模型理解：post-training(abstract)；分类 cs.AI

2403.11747 2024-10-15 cs.CL 57%

Embedded Named Entity Recognition using Probing Classifiers

Nicholas Popovič, Michael Färber

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL

Comments EMNLP 2024 (main)

2407.03788 2024-10-11 cs.CV cs.CL 57%

MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning

Thong Nguyen, Yi Bin, Xiaobao Wu, Xinshuai Dong, Zhiyuan Hu, Khoi Le, Cong-Duy Nguyen, See-Kiong Ng, Luu Anh Tuan

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL

Comments Accepted to ECCV 2024

2406.12746 2024-10-10 cs.CL 57%

Diversify, Rationalize, and Combine: Ensembling Multiple QA Strategies for Zero-shot Knowledge-based VQA

Miaoyu Li, Haoxin Li, Zilin Du, Boyang Li

专题命中知识编辑与模型理解：LLM(abstract)；分类 cs.CL

Comments Accepted to Findings of EMNLP2024

2406.09790 2024-10-08 cs.CL 57%

Pcc-tuning: Breaking the Contrastive Learning Ceiling in Semantic Textual Similarity

Bowen Zhang, Chunping Li

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL

Comments Accepted by EMNLP 2024 (Main)

2410.03478 2024-10-07 cs.CV cs.LG 57%

VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning

Han Lin, Tushar Nagarajan, Nicolas Ballas, Mido Assran, Mojtaba Komeili, Mohit Bansal, Koustuv Sinha

专题命中知识编辑与模型理解：pretraining(abstract)；分类 cs.LG

Comments 10 pages

2410.03334 2024-10-07 cs.CV cs.AI 57%

An X-Ray Is Worth 15 Features: Sparse Autoencoders for Interpretable Radiology Report Generation

Ahmed Abdulaal, Hugo Fry, Nina Montaña-Brown, Ayodeji Ijishakin, Jack Gao, Stephanie Hyland, Daniel C. Alexander, Daniel C. Castro

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.AI

2410.03176 2024-10-07 cs.CV cs.AI 57%

Investigating and Mitigating Object Hallucinations in Pretrained Vision-Language (CLIP) Models

Yufang Liu, Tao Ji, Changzhi Sun, Yuanbin Wu, Aimin Zhou

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.AI

Comments EMNLP 2024

2406.13692 2024-10-07 cs.CL 57%

Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation

Di Wu, Jia-Chen Gu, Fan Yin, Nanyun Peng, Kai-Wei Chang

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL

Comments EMNLP 2024

2401.06034 2024-10-07 cs.CL 57%

LinguAlchemy: Fusing Typological and Geographical Elements for Unseen Language Generalization

Muhammad Farid Adilazuarda, Samuel Cahyawijaya, Alham Fikri Aji, Genta Indra Winata, Ayu Purwarianti

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL

2410.00857 2024-10-02 cs.CL 57%

Quantifying reliance on external information over parametric knowledge during Retrieval Augmented Generation (RAG) using mechanistic analysis

Reshmi Ghosh, Rahul Seetharaman, Hitesh Wadhwa, Somyaa Aggarwal, Samyadeep Basu, Soundararajan Srinivasan, Wenlong Zhao, Shreyas Chaudhari, Ehsan Aghazadeh

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL

Comments Accepted to Blackbox NLP @ EMNLP 2024

2409.20429 2024-10-01 cs.CL cs.CV 57%

HELPD: Mitigating Hallucination of LVLMs by Hierarchical Feedback Learning with Vision-enhanced Penalty Decoding

Fan Yuan, Chi Qin, Xiaogang Xu, Piji Li

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL

Comments Accepted at Main Conference of EMNLP 2024

2406.08958 2024-10-01 cs.LG 57%

An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Records

Joakim Edin, Maria Maistro, Lars Maaløe, Lasse Borgholt, Jakob D. Havtorn, Tuukka Ruotsalo

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.LG

Comments Accepted to EMNLP 2024 Main

2409.13187 2024-09-25 cs.MA cs.AI 57%

Cooperative Resilience in Artificial Intelligence Multiagent Systems

Manuela Chacon-Chamorro, Luis Felipe Giraldo, Nicanor Quijano, Vicente Vargas-Panesso, César González, Juan Sebastián Pinzón, Rubén Manrique, Manuel Ríos, Yesid Fonseca, Daniel Gómez-Barrera, Mónica Perdomo-Pérez

专题命中知识编辑与模型理解：LLM(abstract)；分类 cs.AI

Comments Supplementary material in https://github.com/mavivi95/resilience/blob/main/Supplementary_File.pdf

2409.15158 2024-09-24 cs.AI 57%

Automatic Feature Learning for Essence: a Case Study on Car Sequencing

Alessio Pellegrino, Özgür Akgün, Nguyen Dang, Zeynep Kiziltan, Ian Miguel

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.AI

2409.13716 2024-09-24 cs.CL 57%

Constrained Multi-Layer Contrastive Learning for Implicit Discourse Relationship Recognition

Yiheng Wu, Junhui Li, Muhua Zhu

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL

2305.06294 2024-09-24 cs.CL 57%

CADGE: Context-Aware Dialogue Generation Enhanced with Graph-Structured Knowledge Aggregation

Hongbo Zhang, Chen Tang, Tyler Loakman, Bohao Yang, Stefan Goetze, Chenghua Lin

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL

Comments Accepted by INLG 2024

2308.11295 2024-09-18 cs.LG 57%

Uncertainty Estimation of Transformers' Predictions via Topological Analysis of the Attention Matrices

Elizaveta Kostenok, Daniil Cherniavskii, Alexey Zaytsev

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.LG

1. 知识编辑与模型理解 7596 篇

When is Multicalibration Post-Processing Necessary?

Taking AI Welfare Seriously

Abrupt Learning in Transformers: A Case Study on Matrix Completion

Improving Gloss-free Sign Language Translation by Reducing Representation Density

Visualizing attention zones in machine reading comprehension models

ModalChorus: Visual Probing and Alignment of Multi-modal Embeddings via Modal Fusion Map

Robust Text Classification: Analyzing Prototype-Based Networks

Review of Deep Representation Learning Techniques for Brain-Computer Interfaces and Recommendations

Mitigating Object Hallucination via Concentric Causal Attention

PixelBytes: Catching Unified Representation for Multimodal Generation

Observing the Southern US Culture of Honor Using Large-Scale Social Media Analysis

ZeQR: Zero-shot Query Reformulation for Conversational Search

REVEAL-IT: REinforcement learning with Visibility of Evolving Agent poLicy for InTerpretability

Embedded Named Entity Recognition using Probing Classifiers

MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning

Diversify, Rationalize, and Combine: Ensembling Multiple QA Strategies for Zero-shot Knowledge-based VQA

Pcc-tuning: Breaking the Contrastive Learning Ceiling in Semantic Textual Similarity

VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning

An X-Ray Is Worth 15 Features: Sparse Autoencoders for Interpretable Radiology Report Generation

Investigating and Mitigating Object Hallucinations in Pretrained Vision-Language (CLIP) Models

Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation

LinguAlchemy: Fusing Typological and Geographical Elements for Unseen Language Generalization

Quantifying reliance on external information over parametric knowledge during Retrieval Augmented Generation (RAG) using mechanistic analysis

HELPD: Mitigating Hallucination of LVLMs by Hierarchical Feedback Learning with Vision-enhanced Penalty Decoding

An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Records

Cooperative Resilience in Artificial Intelligence Multiagent Systems

Automatic Feature Learning for Essence: a Case Study on Car Sequencing

Constrained Multi-Layer Contrastive Learning for Implicit Discourse Relationship Recognition

CADGE: Context-Aware Dialogue Generation Enhanced with Graph-Structured Knowledge Aggregation

Uncertainty Estimation of Transformers' Predictions via Topological Analysis of the Attention Matrices