语言大模型 / LLM

Difficulty-Focused Contrastive Learning for Knowledge Tracing with a Large Language Model-Based Difficulty Prediction

Unggi Lee, Sungjun Yoon, Joon Seo Yun, Kyoungsoo Park, YoungHoon Jung, Damji Stratton, Hyeoncheol Kim

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

Comments 10 pages, 4 figures, 2 tables

Benchmarking Large Language Model Volatility

Boyang Yu

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

Comments 7 pages, 2 figures, Workshop on AI Safety and Robustness In Finance, ICAIF 2023

Assessing the Reliability of Large Language Model Knowledge

Weixuan Wang, Barry Haddow, Alexandra Birch, Wei Peng

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

SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models

Potsawee Manakul, Adian Liusie, Mark J. F. Gales

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

Comments EMNLP 2023 (main conference)

Benchmarking and Explaining Large Language Model-based Code Generation: A Causality-Centric Approach

Zhenlan Ji, Pingchuan Ma, Zongjie Li, Shuai 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)；分类 cs.AI

Zero-Resource Hallucination Prevention for Large Language Models

Junyu Luo, Cao Xiao, Fenglong Ma

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

Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty

Chen Ling, Xujiang Zhao, Xuchao Zhang, Yanchi Liu, Wei Cheng, Haoyu Wang, Zhengzhang Chen, Takao Osaki, Katsushi Matsuda, Haifeng Chen, Liang Zhao

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

DataTales: Investigating the use of Large Language Models for Authoring Data-Driven Articles

Nicole Sultanum, Arjun Srinivasan

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

Comments 4 pages, 3 figures

ProPILE: Probing Privacy Leakage in Large Language Models

Siwon Kim, Sangdoo Yun, Hwaran Lee, Martin Gubri, Sungroh Yoon, Seong Joon Oh

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

N2G: A Scalable Approach for Quantifying Interpretable Neuron Representations in Large Language Models

Alex Foote, Neel Nanda, Esben Kran, Ionnis Konstas, Fazl Barez

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

Comments To be published at ICLR 2023 Workshop on Trustworthy and Reliable Large-Scale Machine Learning Models

LMCanvas: Object-Oriented Interaction to Personalize Large Language Model-Powered Writing Environments

Tae Soo Kim, Arghya Sarkar, Yoonjoo Lee, Minsuk Chang, Juho Kim

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

Comments Accepted to CHI 2023 Workshop on Generative AI and HCI

AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts

Tongshuang Wu, Michael Terry, Carrie J. Cai

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

Enhancing LLM Agent Safety via Causal Influence Prompting

Dongyoon Hahm, Woogyeol Jin, June Suk Choi, Sungsoo Ahn, Kimin Lee

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

Comments Accepted at ACL 2025 Findings, Source code: https://github.com/HahmDY/causal_influence_prompting.git

The Geometry of Categorical and Hierarchical Concepts in Large Language Models

Kiho Park, Yo Joong Choe, Yibo Jiang, Victor Veitch

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；LLM(comments)

Comments Accepted for an oral presentation at ICLR 2025. Best Paper Award at the ICML 2024 Workshop on Mechanistic Interpretability. Code is available at https://github.com/KihoPark/LLM_Categorical_Hierarchical_Representations

"We Need Structured Output": Towards User-centered Constraints on Large Language Model Output

Michael Xieyang Liu, Frederick Liu, Alexander J. Fiannaca, Terry Koo, Lucas Dixon, Michael Terry, Carrie J. Cai

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

Journal ref "We Need Structured Output": Towards User-centered Constraints on LLM Output. In Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI EA '24), May 11-16, 2024, Honolulu, HI, USA

FlexModel: A Framework for Interpretability of Distributed Large Language Models

Matthew Choi, Muhammad Adil Asif, John Willes, David Emerson

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

Comments 14 pages, 8 figures. To appear at the Socially Responsible Language Modelling Research (SoLaR) Workshop, 37th Conference on Neural Information Processing Systems (NeurIPS 2023)

N-Critics: Self-Refinement of Large Language Models with Ensemble of Critics

Sajad Mousavi, Ricardo Luna Gutiérrez, Desik Rengarajan, Vineet Gundecha, Ashwin Ramesh Babu, Avisek Naug, Antonio Guillen, Soumyendu Sarkar

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；foundation model(journal_ref)

Journal ref NeurIPS 2023 Workshop on Robustness of Few-shot and Zero-shot Learning in Foundation Models 2023(NeurIPS 2023)

Represented but Ignored: A Causal Account of Prosodic Underuse in Audio-Language Models

被表征却被忽视：音频语言模型中韵律使用不足的因果解释

Linkai Peng, Baorian Nuchged

机构 * University of Connecticut（康涅狄格大学） ； The University of Texas at Austin（德克萨斯大学奥斯汀分校） 纠错

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

AI总结 本研究针对音频语言模型（audio-LLM）韵律使用不足的问题，通过阶段特定探测阶梯与隐藏状态干预实验，发现模型能表征韵律却未在输出中表达，瓶颈在于韵律的使用而非感知。

Grounded Optimization: A Layered Engineering Framework for Reducing LLM Hallucination in Automated Personal Document Rewriting

接地优化：一种减少自动个人文档重写中LLM幻觉的分层工程框架

Shashank Indukuri, Adarsh Agrawal

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、cs.AI

AI总结 提出五层接地优化框架，通过时间验证、污染检测、结构不变性、提示接地和评估器，将简历重写中的幻觉率降至0.04-0.24。

Comments 13 pages, 1 figure. Equal contribution by both authors. Code and data: https://github.com/shashank-indukuri/grounded-optimization

A Mechanistic View of Authority Hierarchy in LLM Sycophancy

LLM 谄媚中权威层级的机制性视角

Emil Joswin, Srujananjali Medicherla, Priyanka Mary Mammen

机构 * Independent Research（独立研究） 纠错

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

AI总结 通过受控医疗QA实验，发现LLM按感知权威程度分级响应，机制是特定后期层中正确答案表征被权威信号主动擦除，且该擦除与权威水平成比例、抵抗均值向量干预、仅部分可逆。

Quantifying Aleatoric Uncertainty of In-Context Learning for Robust Measure of LLM Prediction Confidence

量化上下文学习中的偶然不确定性以稳健衡量LLM预测置信度

Jinseok Chung, Minkyoung Song, Hyunji Jung, Namhoon Lee

机构 * POSTECH（浦项科技大学） 纠错

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

AI总结 针对上下文学习（ICL）中预测对提示设计敏感的问题，提出基于贝叶斯观点和机制可解释性的自函数向量，直接估计偶然不确定性，并设计严格评估协议，在合成和真实数据集上验证了方法的可靠性及在幻觉检测等应用中的实用性。

Comments Accepted to ACL 2026

Generative Explainability for Next-Generation Networks: LLM-Augmented XAI with Mutual Feature Interactions

下一代网络的生成式可解释性：基于互特征交互的LLM增强XAI

Kiarash Rezaei, Omran Ayoub, Sebastian Troia, Francesco Lelli, Paolo Monti, Carlos Natalino

机构 * Swedish Innovation Agency（瑞典创新署） ； Swiss Innovation Agency（瑞士创新署） 纠错

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.AI、cs.LG

AI总结 提出一种利用大语言模型和互特征交互数据生成自然语言解释的框架，在光传输质量估计用例中，相比基线方法，解释有用性和范围分别提升12.2%和6.2%，正确率达97.5%。

Comments 7 pages, with one page for appendix. Accepted for publication at the 2025 21th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)

Journal ref Proc. WiMob, Marrakesh, Morocco, 2025

Can I Take Another Dose? Evaluating LLM Decision-Making Under Temporal Uncertainty in OTC Dosing QA

我可以再服一剂吗？评估LLM在OTC剂量问答中时间不确定性下的决策能力

Maroof Kousar, Yibo Hu

机构 * Illinois Institute of Technology（伊利诺伊理工学院） 纠错

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、cs.AI

AI总结 提出DOSEBENCH基准测试，评估大语言模型在非处方药剂量问答中处理时间推理、约束遵循和不确定性的能力。

Comments 16 pages, 7 figures

Riemannian Geometry Speaks Louder Than Words: From Graph Foundation Model to Next-Generation Graph Intelligence

黎曼几何胜过言语：从图基础模型到下一代图智能

Philip S. Yu, Li Sun

机构 * University of Illinois Chicago（伊利诺伊大学香槟分校） ； Beijing University of Posts and Telecommunications（北京邮电大学） 纠错

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

AI总结 本文提出黎曼基础模型（RFM），通过内在几何捕捉复杂结构模式，推动图智能发展，实现从设计图模型到解决图结构应用的范式转变。

Comments 7 pages

A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models

Zihao Lin, Samyadeep Basu, Mohammad Beigi, Varun Manjunatha, Ryan A. Rossi, Zichao Wang, Yufan Zhou, Sriram Balasubramanian, Arman Zarei, Keivan Rezaei, Ying Shen, Barry Menglong Yao, Zhiyang Xu, Qin Liu, Yuxiang Zhang, Yan Sun, Shilong Liu, Li Shen, Hongxuan Li, Soheil Feizi, Lifu Huang

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

Comments 30 pages, 4 Figures, 10 Tables

Neuron-Level Knowledge Attribution in Large Language Models

Zeping Yu, Sophia Ananiadou

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.LG

Comments Accepted by EMNLP 2024 main. This paper aims to identify the important neurons in large language models

When LLMs Invent Rust Crates: An Empirical Study of Hallucination Patterns and Mitigation

当LLM发明Rust包：幻觉模式与缓解措施的实证研究

Jieming Zheng, Hao Guan, Yepang Liu

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

AI总结 本研究首次大规模实证分析LLM生成Rust代码中的包幻觉问题，发现不同模型幻觉率惊人一致且对参数不敏感，并探索了提示工程缓解策略。

Comments The work has been accepted by the 17th International Conference on Internetware

Understanding Fortunetelling with Large Language Models in China: User Practices, Perceptions, and Impacts on Beliefs and Decisions

理解中国大语言模型的算命现象：用户实践、认知及其对信念和决策的影响

Xueer Lin, Chenyu Li, Shuai Ma, Yuhan Lyu, Zhenhui Peng

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

AI总结 研究中国用户用大语言模型算命的情况，通过分析社交媒体帖子和访谈用户，发现用户把它当情感支持工具，结果少改信念决策，但引发思维模式转变和小行为调整，探讨了从中获益的意义。

Comments Accepted at ICWSM 2027

Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework

Safe-SAIL: 通过稀疏自编码解释框架构建大语言模型的细粒度安全景观

Jiaqi Weng, Han Zheng, Hanyu Zhang, Ej Zhou, Qinqin He, Jialing Tao, Hui Xue, Zhixuan Chu, Xiting Wang

机构 * Alibaba Group（阿里巴巴集团） ； The State Key Laboratory of Blockchain and Data Security, Zhejiang University（浙江大学区块链与数据安全国家重点实验室） ； Language Technology Lab, University of Cambridge（剑桥大学语言技术实验室） ； Renmin University of China（中国人民大学） 纠错

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

AI总结 本文提出Safe-SAIL框架，通过稀疏自编码解释方法高效识别安全领域特征，减少解释成本55%，并系统评估1758个安全相关特征，揭示风险特征识别和安全关键实体编码机制。

Journal ref Findings of the Association for Computational Linguistics: ACL 2026, pages 18916-18935 (2026)

Improving Code Understanding in Large Language Models through Concept-Aware Consistency Learning

通过概念感知一致性学习提高大语言模型中的代码理解能力

Xiaoning Ren, Qiang Hu, Wei Ma, Chongyang Liu, Yan Li, Yao Zhang, Lingxiao Jiang, Yongqiang Lyu, Yinxing Xue

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

AI总结 研究针对大语言模型对基本编程概念理解浅的问题，引入结合概念感知调整的反事实代码增强框架，经多模型和基准综合评估，证明此方法能引导大语言模型增强概念理解，有效提升其在代码相关任务中的表现。

Comments To appear at IJCAI 2026