语言大模型 / LLM - arXivDaily 专题

2010.06189 2020-10-28 cs.CL 79%

X-FACTR: Multilingual Factual Knowledge Retrieval from Pretrained Language Models

Zhengbao Jiang, Antonios Anastasopoulos, Jun Araki, Haibo Ding, Graham Neubig

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

Comments EMNLP 2020

2010.05731 2020-10-13 cs.CL 79%

Probing Pretrained Language Models for Lexical Semantics

Ivan Vulić, Edoardo Maria Ponti, Robert Litschko, Goran Glavaš, Anna Korhonen

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

Comments EMNLP 2020: Long paper

2009.08636 2020-09-21 cs.CL 79%

Hierarchical GPT with Congruent Transformers for Multi-Sentence Language Models

Jihyeon Roh, Huiseong Gim, Soo-Young Lee

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

2004.13897 2020-07-01 cs.CL 79%

Empower Entity Set Expansion via Language Model Probing

Yunyi Zhang, Jiaming Shen, Jingbo Shang, Jiawei Han

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

Comments ACL 2020

2004.04877 2020-06-17 cs.CL 79%

Probing Neural Language Models for Human Tacit Assumptions

Nathaniel Weir, Adam Poliak, Benjamin Van Durme

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

Comments To be published in CogSci 2020

1911.03343 2020-05-18 cs.CL 79%

Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly

Nora Kassner, Hinrich Schütze

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

Comments ACL 2020

2005.05864 2020-05-13 cs.CL 79%

Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach

Wenyu Du, Zhouhan Lin, Yikang Shen, Timothy J. O'Donnell, Yoshua Bengio, Yue Zhang

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

Comments ACL20

2005.05716 2020-05-13 cs.LG stat.ML 79%

AttViz: Online exploration of self-attention for transparent neural language modeling

Blaž Škrlj, Nika Eržen, Shane Sheehan, Saturnino Luz, Marko Robnik-Šikonja, Senja Pollak

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

1910.14286 2019-11-01 cs.CL 79%

A neural document language modeling framework for spoken document retrieval

Li-Phen Yen, Zhen-Yu Wu, Kuan-Yu Chen

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

1909.01380 2019-09-05 cs.CL 79%

The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives

Elena Voita, Rico Sennrich, Ivan Titov

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

Comments EMNLP 2019 (camera-ready)

1906.10007 2019-06-25 cs.CL 79%

Language Modelling Makes Sense: Propagating Representations through WordNet for Full-Coverage Word Sense Disambiguation

Daniel Loureiro, Alipio Jorge

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

Comments Accepted to ACL 2019. Code and data: https://github.com/danlou/lmms

1906.07285 2019-06-19 cs.CL 79%

Tabula nearly rasa: Probing the Linguistic Knowledge of Character-Level Neural Language Models Trained on Unsegmented Text

Michael Hahn, Marco Baroni

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

Comments Accepted by Transactions of the Association for Computational Linguistics

1906.04068 2019-06-11 cs.CL 79%

Hierarchical Representation in Neural Language Models: Suppression and Recovery of Expectations

Ethan Wilcox, Roger Levy, Richard Futrell

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

Comments Proceedings of BlackboxNLP 2019, ACL, Florence, Italy

1904.02181 2019-04-05 cs.CL 79%

Probing Biomedical Embeddings from Language Models

Qiao Jin, Bhuwan Dhingra, William W. Cohen, Xinghua Lu

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

Comments NAACL-HLT 2019 Workshop on Evaluating Vector Space Representations for NLP (RepEval)

1903.07435 2019-04-03 cs.CL 79%

The emergence of number and syntax units in LSTM language models

Yair Lakretz, German Kruszewski, Theo Desbordes, Dieuwke Hupkes, Stanislas Dehaene, Marco Baroni

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

Comments To appear in Proceedings of NAACL, Minneapolis, MN, 2019

1704.08012 2017-10-16 cs.CL 79%

Topically Driven Neural Language Model

Jey Han Lau, Timothy Baldwin, Trevor Cohn

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

Comments 11 pages, Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL 2017) (to appear)

Journal ref In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL 2017), pp. 355--365

1707.06130 2017-07-20 cs.CL 79%

Improving Language Modeling using Densely Connected Recurrent Neural Networks

Fréderic Godin, Joni Dambre, Wesley De Neve

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

Comments Accepted at Workshop on Representation Learning, ACL2017

1606.08689 2016-06-29 cs.CL cs.IR 79%

Hierarchical Neural Language Models for Joint Representation of Streaming Documents and their Content

Nemanja Djuric, Hao Wu, Vladan Radosavljevic, Mihajlo Grbovic, Narayan Bhamidipati

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

Comments 24th International World Wide Web Conference

1605.03832 2016-05-13 cs.CL 79%

Polyglot Neural Language Models: A Case Study in Cross-Lingual Phonetic Representation Learning

Yulia Tsvetkov, Sunayana Sitaram, Manaal Faruqui, Guillaume Lample, Patrick Littell, David Mortensen, Alan W Black, Lori Levin, Chris Dyer

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

Comments Proceedings of NAACL 2016; 10 pages

1510.01562 2015-10-07 cs.IR cs.CL 79%

Parameterized Neural Network Language Models for Information Retrieval

Benjamin Piwowarski, Sylvain Lamprier, Nicolas Despres

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

1501.04324 2015-01-20 cs.CL 79%

Phrase Based Language Model For Statistical Machine Translation

Jia Xu, Geliang Chen

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

Comments 5 pages. This version of the paper was submitted for review to EMNLP 2013. The title, the idea and the content of this paper was presented by the first author in the machine translation group meeting at the MSRA-NLC lab (Microsoft Research Asia, Natural Language Computing) on July 16, 2013

2602.05128 2026-02-06 cs.HC 79%

Reporting and Reviewing LLM-Integrated Systems in HCI: Challenges and Considerations

在人机交互中报告和审查集成大语言模型的系统：挑战与考虑

Karla Felix Navarro, Eugene Syriani, Ian Arawjo

专题命中知识编辑与模型理解：LLM(title,abstract)

AI总结本文探讨了在人机交互中报告和审查集成大语言模型系统时的挑战，指出信任规范受大语言模型行为不确定性和夸大宣传影响，并提出作者与评审者在标准应用上的不一致及情境依赖的提示报告问题。

Comments 18 pages, 1 figure, 2 tables. For proposed reporting guidelines, see https://ianarawjo.github.io/Guidelines-for-Reporting-LLM-Integrated-Systems-in-HCI/

2509.15243 2025-09-22 cs.CV 79%

Multi-Modal Interpretability for Enhanced Localization in Vision-Language Models

Muhammad Imran, Yugyung Lee

机构 * Computer Science, School of Science and Engineering, University of Missouri - Kansas City（计算机科学系，科学与工程学院，密苏里大学-堪萨斯城分校）

专题命中知识编辑与模型理解：language model(title,abstract)

Comments 8 pages, 6 figures, 3 tables

Journal ref Non-Archival track - The First Workshop on Multimodal Knowledge and Language Modeling IJCAI 2025 Workshop, August 16, 2025 IJCAI 2025 Workshop, August 16, 2025 Room 516B, Palais des congrès, Montreal, Canada

2412.02700 2025-03-31 cs.CV 79%

Motion Prompting: Controlling Video Generation with Motion Trajectories

Daniel Geng, Charles Herrmann, Junhwa Hur, Forrester Cole, Serena Zhang, Tobias Pfaff, Tatiana Lopez-Guevara, Carl Doersch, Yusuf Aytar, Michael Rubinstein, Chen Sun, Oliver Wang, Andrew Owens, Deqing Sun

专题命中知识编辑与模型理解：prompting(title,abstract)

Comments CVPR 2025 camera ready. Project page: https://motion-prompting.github.io/

2407.13111 2024-07-19 cs.MM cs.CV 79%

PG-Attack: A Precision-Guided Adversarial Attack Framework Against Vision Foundation Models for Autonomous Driving

Jiyuan Fu, Zhaoyu Chen, Kaixun Jiang, Haijing Guo, Shuyong Gao, Wenqiang Zhang

专题命中知识编辑与模型理解：foundation model(title,abstract)

Comments First-Place in the CVPR 2024 Workshop Challenge: Black-box Adversarial Attacks on Vision Foundation Models

2608.07531 2026-08-19 cs.CL cs.AI 版本更新 79%

Search-G1: Grounded Search Agents via Representation-Based Intrinsic Rewards

Search-G1：基于表征内在奖励的接地搜索智能体

Ruoxi Cheng, Haoxuan Ma, Hongyi Zhang, Junming Zhang, Ranjie Duan, Qiaolin Xia, Hao Wang, Yu Lu, Haibo Shi, Xingjun Ma

专题命中知识编辑与模型理解：LLM(abstract,abstract_cn)；language agent(abstract)；分类 cs.CL、cs.AI

AI总结该研究提出Search-G1框架，通过两个经干预校准的读数构成的表征内在奖励，改善了搜索增强语言智能体的接地性与搜索成本的权衡，在多基准和模型规模上验证了其有效性。

2606.31087 2026-08-12 cs.CL cs.AI 版本更新 79%

When Reranking Hurts: Uncertainty-Based Gating for Few-Shot Reranking

当重排序有害时：基于不确定性的门控机制用于少样本重排序

Orian Dabod, Amir DN Cohen, Gabriel Stanovsky

机构 * The Hebrew University of Jerusalem（耶路撒冷希伯来大学）； OriginAI

专题命中知识编辑与模型理解：LLM(summary_cn,abstract_cn)；分类 cs.CL、cs.AI

AI总结针对少样本选择中重排序可能降低性能的问题，提出无训练门控重排序方法，基于模型不确定性决定是否重排序，在8个LLM上降低15%-80%计算成本并提升平均性能达2%。

2601.19245 2026-08-12 cs.AI cs.LG 79%

Beyond In-Domain Detection: SpikeScore for Cross-Domain Hallucination Detection

超越领域检测：SpikeScore用于跨领域幻觉检测

Yongxin Deng, Zhen Fang, Sharon Li, Ling Chen

机构 * University of Technology Sydney（技术科技大学）； University of Wisconsin-Madison（威斯康星大学麦迪逊分校）

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

AI总结本文提出SpikeScore方法，通过量化多轮对话中的不确定性波动，实现跨领域幻觉检测的高效识别与高泛化性能。

Journal ref In Proceedings of the Fourteenth International Conference on Learning Representations (ICLR 2026)

2606.07998 2026-08-11 cs.LG cs.AI 版本更新 79%

Enhancing AI Interpretability with Localised Architectures

通过局部化架构增强AI可解释性与安全性

Ian Seet, Jonas Bozenhard, Simon Ostermann

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

AI总结针对大型生成式AI模型可解释性差、计算成本高的问题，提出局部化机器学习架构，通过降低带宽、提高节点表达能力来提升可解释性和效率，并评估了多种硬件实现方案的适用性。

2607.17883 2026-07-21 cs.CL cs.AI 新提交 79%

Zero Hallucination, by Construction: Hallucination-Aware Layered Oversight for Trustworthy Enterprise AI

通过构建实现零幻觉：用于可信企业人工智能的幻觉感知分层监督

Bogdan Raduta, Horia Velicu, Alexandru Preda, Serban Chiricescu

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

AI总结研究企业AI因幻觉难以被信任的问题时，提出HALO架构，通过六层防御将幻觉视为可控制故障模式，详细介绍各层并关注基于证据的置信度，以实现可信企业AI，在索赔提取工作负载上进行了架构说明。

Comments 12 pages, 2 figures

1. 知识编辑与模型理解 7552 篇

X-FACTR: Multilingual Factual Knowledge Retrieval from Pretrained Language Models

Probing Pretrained Language Models for Lexical Semantics

Hierarchical GPT with Congruent Transformers for Multi-Sentence Language Models

Empower Entity Set Expansion via Language Model Probing

Probing Neural Language Models for Human Tacit Assumptions

Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly

Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach

AttViz: Online exploration of self-attention for transparent neural language modeling

A neural document language modeling framework for spoken document retrieval

The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives

Language Modelling Makes Sense: Propagating Representations through WordNet for Full-Coverage Word Sense Disambiguation

Tabula nearly rasa: Probing the Linguistic Knowledge of Character-Level Neural Language Models Trained on Unsegmented Text

Hierarchical Representation in Neural Language Models: Suppression and Recovery of Expectations

Probing Biomedical Embeddings from Language Models

The emergence of number and syntax units in LSTM language models

Topically Driven Neural Language Model

Improving Language Modeling using Densely Connected Recurrent Neural Networks

Hierarchical Neural Language Models for Joint Representation of Streaming Documents and their Content

Polyglot Neural Language Models: A Case Study in Cross-Lingual Phonetic Representation Learning

Parameterized Neural Network Language Models for Information Retrieval

Phrase Based Language Model For Statistical Machine Translation

Reporting and Reviewing LLM-Integrated Systems in HCI: Challenges and Considerations

Multi-Modal Interpretability for Enhanced Localization in Vision-Language Models

Motion Prompting: Controlling Video Generation with Motion Trajectories

PG-Attack: A Precision-Guided Adversarial Attack Framework Against Vision Foundation Models for Autonomous Driving

Search-G1: Grounded Search Agents via Representation-Based Intrinsic Rewards

When Reranking Hurts: Uncertainty-Based Gating for Few-Shot Reranking

Beyond In-Domain Detection: SpikeScore for Cross-Domain Hallucination Detection

Enhancing AI Interpretability with Localised Architectures

Zero Hallucination, by Construction: Hallucination-Aware Layered Oversight for Trustworthy Enterprise AI