语言大模型 / LLM - arXivDaily 专题

2405.00648 2024-09-04 cs.SE 89%

Drowzee: Metamorphic Testing for Fact-Conflicting Hallucination Detection in Large Language Models

Ningke Li, Yuekang Li, Yi Liu, Ling Shi, Kailong Wang, Haoyu Wang

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

Comments 29 pages, 11 figures, 4 tables, to appear in OOPSLA'24 (Vol.8, No.OOPSLA2, Article 336)

2408.03603 2024-08-08 cs.CR cs.AI cs.CL cs.LG 89%

EnJa: Ensemble Jailbreak on Large Language Models

Jiahao Zhang, Zilong Wang, Ruofan Wang, Xingjun Ma, Yu-Gang Jiang

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

2308.07269 2024-06-25 cs.CL cs.AI cs.CV cs.IR cs.LG 89%

EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models

Peng Wang, Ningyu Zhang, Bozhong Tian, Zekun Xi, Yunzhi Yao, Ziwen Xu, Mengru Wang, Shengyu Mao, Xiaohan Wang, Siyuan Cheng, Kangwei Liu, Yuansheng Ni, Guozhou Zheng, Huajun Chen

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

Comments ACL 2024 System Demonstrations; Code: https://github.com/zjunlp/EasyEdit HF Demo: https://huggingface.co/spaces/zjunlp/EasyEdit Video: https://youtu.be/Gm6T0QaaskU Docs: https://zjunlp.gitbook.io/easyedit

2406.13929 2024-06-21 cs.CL cs.AI cs.LG 89%

Large Language Models are Skeptics: False Negative Problem of Input-conflicting Hallucination

Jongyoon Song, Sangwon Yu, Sungroh Yoon

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

Comments 12 pages, 9 figures

2402.03190 2024-05-28 cs.CL cs.AI cs.IR cs.LG cs.MM 89%

Unified Hallucination Detection for Multimodal Large Language Models

Xiang Chen, Chenxi Wang, Yida Xue, Ningyu Zhang, Xiaoyan Yang, Qiang Li, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen

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

Comments Accepted by ACL 2024 (main conference)

2403.06710 2024-05-22 cs.HC 89%

HILL: A Hallucination Identifier for Large Language Models

Florian Leiser, Sven Eckhardt, Valentin Leuthe, Merlin Knaeble, Alexander Maedche, Gerhard Schwabe, Ali Sunyaev

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

2402.00024 2024-05-22 q-bio.BM cs.AI cs.CL cs.LG 89%

Can Large Language Models Understand Molecules?

Shaghayegh Sadeghi, Alan Bui, Ali Forooghi, Jianguo Lu, Alioune Ngom

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

2405.06806 2024-05-14 cs.SE 89%

An Empirical Study on the Effectiveness of Large Language Models for SATD Identification and Classification

Mohammad Sadegh Sheikhaei, Yuan Tian, Shaowei Wang, Bowen Xu

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

Comments This is the preprint version of a paper that has been submitted to Empirical Software Engineering

2310.02129 2024-05-14 cs.CL cs.AI cs.CV cs.DB cs.LG 89%

Unveiling the Pitfalls of Knowledge Editing for Large Language Models

Zhoubo Li, Ningyu Zhang, Yunzhi Yao, Mengru Wang, Xi Chen, Huajun Chen

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

Comments ICLR 2024

2404.17120 2024-04-30 cs.CL cs.AI cs.LG 89%

Talking Nonsense: Probing Large Language Models' Understanding of Adversarial Gibberish Inputs

Valeriia Cherepanova, James Zou

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

2403.01216 2024-04-05 cs.CL cs.AI cs.LG 89%

API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access

Jiayuan Su, Jing Luo, Hongwei Wang, Lu Cheng

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

2403.16645 2024-03-26 cs.HC 89%

Virtual Co-Pilot: Multimodal Large Language Model-enabled Quick-access Procedures for Single Pilot Operations

Fan Li, Shanshan Feng, Yuqi Yan, Ching-Hung Lee, Yew Soon Ong

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

Comments 10 pages,7 figures

2310.04475 2024-03-14 cs.CL cs.AI cs.LG 89%

Demystifying Embedding Spaces using Large Language Models

Guy Tennenholtz, Yinlam Chow, Chih-Wei Hsu, Jihwan Jeong, Lior Shani, Azamat Tulepbergenov, Deepak Ramachandran, Martin Mladenov, Craig Boutilier

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

Comments Accepted to ICLR 2024

2403.03397 2024-03-07 cs.NE 89%

Explaining Genetic Programming Trees using Large Language Models

Paula Maddigan, Andrew Lensen, Bing Xue

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

2311.09114 2024-02-27 cs.CL cs.AI cs.LG 89%

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

Haoqiang Kang, Juntong Ni, Huaxiu Yao

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

2402.08631 2024-02-20 cs.CL cs.AI cs.LG 89%

Knowledge Editing on Black-box Large Language Models

Xiaoshuai Song, Zhengyang Wang, Keqing He, Guanting Dong, Yutao Mou, Jinxu Zhao, Weiran Xu

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

Comments Work in progress

2312.16257 2023-12-29 cs.CL cs.AI cs.LG 89%

More than Correlation: Do Large Language Models Learn Causal Representations of Space?

Yida Chen, Yixian Gan, Sijia Li, Li Yao, Xiaohan Zhao

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

Comments 12 pages, 15 figures

2205.00584 2023-10-09 cs.IR 89%

Making Large Language Models Interactive: A Pioneer Study on Supporting Complex Information-Seeking Tasks with Implicit Constraints

Ali Ahmadvand, Negar Arabzadeh, Julia Kiseleva, Patricio Figueroa Sanz, Xin Deng, Sujay Jauhar, Michael Gamon, Eugene Agichtein, Ned Friend, Aniruddha

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

2309.10346 2023-09-20 cs.LG cs.AI cs.CL 89%

Explaining Agent Behavior with Large Language Models

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

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

Comments Human Multi-Robot Interaction Workshop at IROS 2023

2309.07172 2023-09-15 cs.AI cs.CL cs.LG 89%

Exploring Large Language Models for Ontology Alignment

Yuan He, Jiaoyan Chen, Hang Dong, Ian Horrocks

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

Comments Accepted at ISWC 2023 (Posters and Demos)

2309.06794 2023-09-14 cs.CL cs.AI cs.LG 89%

Cognitive Mirage: A Review of Hallucinations in Large Language Models

Hongbin Ye, Tong Liu, Aijia Zhang, Wei Hua, Weiqiang Jia

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

Comments work in progress; 21 pages

2306.05152 2023-09-06 cs.SE 89%

Towards Autonomous Testing Agents via Conversational Large Language Models

Robert Feldt, Sungmin Kang, Juyeon Yoon, Shin Yoo

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

2511.15005 2025-11-20 cs.CL cs.AI 89%

Mathematical Analysis of Hallucination Dynamics in Large Language Models: Uncertainty Quantification, Advanced Decoding, and Principled Mitigation

Moses Kiprono

机构 * Catholic University of America（美国天主教大学）

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

Comments 10 pages, theoretical/mathematical LLM research, no figures, intended for peer-reviewed journal

2408.13661 2024-08-27 cs.CV cs.AI cs.LG 89%

Hierarchical Network Fusion for Multi-Modal Electron Micrograph Representation Learning with Foundational Large Language Models

Sakhinana Sagar Srinivas, Geethan Sannidhi, Venkataramana Runkana

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

Comments Our paper is published at the workshop on Robustness of Few-shot and Zero-shot Learning in Foundation Models at NeurIPS 2023

2608.13333 2026-08-17 cs.AI 版本更新 89%

LLM-Guided Graph Generation for Structure-Based Local Improvement Methods

基于大语言模型引导的图生成的基于结构的局部改进方法

Hai Xia, Vaidyanathan Peruvemba Ramaswamy, Stefan Szeider

机构 * TU Wien（维也纳技术大学）

专题命中知识编辑与模型理解：LLM(title,summary_cn)；prompting(abstract)；分类 cs.AI

AI总结该研究构建了适用于MiniZinc格式问题的自动流程，引导LLM生成图生成器以辅助SLIM框架，在20个MiniZinc竞赛问题上使算法选择胜率大幅提升，证明LLM语义生成可实现高效的约束优化自动特征提取。

2606.17168 2026-06-23 cs.CL 新提交 89%

RepSelect: Robust LLM Unlearning via Representation Selectivity

RepSelect: 通过表示选择性实现鲁棒的大语言模型遗忘

Filip Sondej, Yushi Yang, Adam Mahdi

机构 * Independent（独立）； University of Oxford（牛津大学）

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

AI总结针对现有遗忘方法易被微调或少样本提示逆转的问题，提出RepSelect方法，通过梯度主成分坍塌隔离遗忘集表示，实现深度鲁棒遗忘。

2606.16244 2026-06-16 cs.CR cs.AI 新提交 89%

SPARK: Security Knowledge Priming and Representation-Guided Knowledge Activation for LLM-based Secure Code Generation

SPARK: 基于安全知识引导与表示激活的LLM安全代码生成

Xiaoyun Xu, Lichao Wu, Jona te Lintelo, Siyu Zhang, Stjepan Picek

机构 * Radboud University（拉德堡德大学）； University of Bristol（布里斯托大学）； University of Zagreb（扎格雷布大学）

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

AI总结提出SPARK方法，通过检索CWE条目并添加结构化提示激活模型内隐安全知识，结合预计算令牌偏置，无需重训练即可提升代码安全性。

2606.06214 2026-06-05 cs.SE cs.AI 89%

Towards the Readability of LLM-Generated Codes through Multitask Representation Engineering

面向大语言模型生成代码可读性的多任务表示工程

Huifan Gao, Liuhua He, Yinghui Pan, Shenbao Yu, Yifeng Zeng, Shengchao Qin, Weidi Sun

机构 * School of Aerospace Engineering, Xiamen University（厦门大学航空航天工程学院）； School of Artificial Intelligence, Shenzhen University（深圳大学人工智能学院）； College of Computer and Cyber Security, Fujian Normal University（福建师范大学计算机与网络安全部分）； Department of Computer & Information Sciences, Northumbria University（北爱尔兰北安普顿大学计算机与信息科学系）； School of Computer Science and Technology, Xidian University（西安电子科技大学计算机科学与技术学院）； Peking University（北京大学）

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

AI总结提出多任务表示工程框架，通过低数据依赖和低计算成本的表示工程方法提升LLM生成代码的可读性，并理论分析其对可读性与正确性权衡的影响。

2606.03136 2026-06-03 cs.CR cs.CL 89%

PsychoPass: Geometric Profiling of Multi-Turn Adversarial LLM Conversations

PsychoPass: 多轮对抗性LLM对话的几何轮廓分析

Muberra Ozmen, Subhabrata Majumdar

机构 * Coveo Montreal, QC, Canada（加拿大蒙特利尔 Coveo）； Indian Institute of Management Bangalore（班加罗尔印度管理学院）

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

AI总结提出PsychoPass框架，通过提取对话轨迹在嵌入空间中的几何特征，在有害内容生成前预测多轮越狱攻击，并发现早期几何信号具有鲁棒性。

2605.29354 2026-05-29 cs.CR cs.LG 89%

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills

无害却有害：针对Agent技能中隐蔽幻觉引导的中性提示攻击

Chia-Yi Hsu, Chia-Mu Yu, Chun-Ying Huang, Jun Sakuma

机构 * Department of Computer Science（计算机科学系）； National Yang Ming Chiao Tung University（阳明交通大学）； Department of Electronics and Electrical Engineering（电子与电气工程系）； School of Computing（计算学院）； Institute of Science Tokyo（东京科学研究所）

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

AI总结本文提出中性提示攻击（NPA），通过语义上看似无害的指令（如鼓励想象和详尽性）增加代码生成Agent的包幻觉倾向，从而引入软件供应链风险，并评估了其对多种编码LLM的有效性和逃避防御的能力。

Comments under review

1. 知识编辑与模型理解 7505 篇

Drowzee: Metamorphic Testing for Fact-Conflicting Hallucination Detection in Large Language Models

EnJa: Ensemble Jailbreak on Large Language Models

EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models

Large Language Models are Skeptics: False Negative Problem of Input-conflicting Hallucination

Unified Hallucination Detection for Multimodal Large Language Models

HILL: A Hallucination Identifier for Large Language Models

Can Large Language Models Understand Molecules?

An Empirical Study on the Effectiveness of Large Language Models for SATD Identification and Classification

Unveiling the Pitfalls of Knowledge Editing for Large Language Models

Talking Nonsense: Probing Large Language Models' Understanding of Adversarial Gibberish Inputs

API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access

Virtual Co-Pilot: Multimodal Large Language Model-enabled Quick-access Procedures for Single Pilot Operations

Demystifying Embedding Spaces using Large Language Models

Explaining Genetic Programming Trees using Large Language Models

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

Knowledge Editing on Black-box Large Language Models

More than Correlation: Do Large Language Models Learn Causal Representations of Space?

Making Large Language Models Interactive: A Pioneer Study on Supporting Complex Information-Seeking Tasks with Implicit Constraints

Explaining Agent Behavior with Large Language Models

Exploring Large Language Models for Ontology Alignment

Cognitive Mirage: A Review of Hallucinations in Large Language Models

Towards Autonomous Testing Agents via Conversational Large Language Models

Mathematical Analysis of Hallucination Dynamics in Large Language Models: Uncertainty Quantification, Advanced Decoding, and Principled Mitigation

Hierarchical Network Fusion for Multi-Modal Electron Micrograph Representation Learning with Foundational Large Language Models

LLM-Guided Graph Generation for Structure-Based Local Improvement Methods

RepSelect: Robust LLM Unlearning via Representation Selectivity

SPARK: Security Knowledge Priming and Representation-Guided Knowledge Activation for LLM-based Secure Code Generation

Towards the Readability of LLM-Generated Codes through Multitask Representation Engineering

PsychoPass: Geometric Profiling of Multi-Turn Adversarial LLM Conversations

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills