语言大模型 / LLM - arXivDaily 专题

2403.03174 2024-09-05 cs.RO cs.AI 83%

MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting

Fangchen Liu, Kuan Fang, Pieter Abbeel, Sergey Levine

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

2401.06855 2024-08-14 cs.CL 83%

Fine-grained Hallucination Detection and Editing for Language Models

Abhika Mishra, Akari Asai, Vidhisha Balachandran, Yizhong Wang, Graham Neubig, Yulia Tsvetkov, Hannaneh Hajishirzi

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

Comments Our code, data, and demo are available at https://fine-grained-hallucination.github.io. Published as a conference paper at COLM 2024

2407.19922 2024-08-13 cs.AI 83%

Monetizing Currency Pair Sentiments through LLM Explainability

Lior Limonad, Fabiana Fournier, Juan Manuel Vera Díaz, Inna Skarbovsky, Shlomit Gur, Raquel Lazcano

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

Comments 7 pages, 3 figures, AIFin@ECAI 2024

Journal ref AIFin workshop at ECAI 2024

2304.00740 2024-08-13 cs.CL 83%

Inspecting and Editing Knowledge Representations in Language Models

Evan Hernandez, Belinda Z. Li, Jacob Andreas

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

Comments Published in COLM 2024

2408.02103 2024-08-06 cs.CL 83%

Effective Demonstration Annotation for In-Context Learning via Language Model-Based Determinantal Point Process

Peng Wang, Xiaobin Wang, Chao Lou, Shengyu Mao, Pengjun Xie, Yong Jiang

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

2407.21092 2024-08-01 cs.CL cond-mat.stat-mech hep-th math.DG 83%

Entropy, Thermodynamics and the Geometrization of the Language Model

Wenzhe Yang

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

Comments 18 pages

2407.00994 2024-07-09 cs.CL 83%

LLM Uncertainty Quantification through Directional Entailment Graph and Claim Level Response Augmentation

Longchao Da, Tiejin Chen, Lu Cheng, Hua Wei

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

Comments 11 pages main content, 5 pages appendix

2405.18672 2024-06-04 cs.CV cs.CL 83%

LLM-based Hierarchical Concept Decomposition for Interpretable Fine-Grained Image Classification

Renyi Qu, Mark Yatskar

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

2405.08026 2024-05-15 cs.LG 83%

ExplainableDetector: Exploring Transformer-based Language Modeling Approach for SMS Spam Detection with Explainability Analysis

Mohammad Amaz Uddin, Muhammad Nazrul Islam, Leandros Maglaras, Helge Janicke, Iqbal H. Sarker

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

2403.10381 2024-03-18 cs.CL 83%

Monotonic Representation of Numeric Properties in Language Models

Benjamin Heinzerling, Kentaro Inui

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

2403.07627 2024-03-13 cs.HC cs.LG 83%

generAItor: Tree-in-the-Loop Text Generation for Language Model Explainability and Adaptation

Thilo Spinner, Rebecca Kehlbeck, Rita Sevastjanova, Tobias Stähle, Daniel A. Keim, Oliver Deussen, Mennatallah El-Assady

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

Comments 24 pages paper, 4 pages references, 3 pages appendix, 8 figures

2310.12794 2023-12-25 cs.CL 83%

Are Structural Concepts Universal in Transformer Language Models? Towards Interpretable Cross-Lingual Generalization

Ningyu Xu, Qi Zhang, Jingting Ye, Menghan Zhang, Xuanjing Huang

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

Comments Findings of EMNLP 2023 (Camera-Ready)

2312.01701 2023-12-05 cs.CV cs.CL 83%

Mitigating Fine-Grained Hallucination by Fine-Tuning Large Vision-Language Models with Caption Rewrites

Lei Wang, Jiabang He, Shenshen Li, Ning Liu, Ee-Peng Lim

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

Comments MMM 2024

2311.11012 2023-11-21 cs.CL 83%

Bit Cipher -- A Simple yet Powerful Word Representation System that Integrates Efficiently with Language Models

Haoran Zhao, Jake Ryland Williams

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

2305.13302 2023-11-21 cs.CL 83%

Language-Agnostic Bias Detection in Language Models with Bias Probing

Abdullatif Köksal, Omer Faruk Yalcin, Ahmet Akbiyik, M. Tahir Kilavuz, Anna Korhonen, Hinrich Schütze

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

Comments EMNLP 2023 Findings

2311.10098 2023-11-20 cs.AI 83%

Automated Parliaments: A Solution to Decision Uncertainty and Misalignment in Language Models

Thomas Forster, Jonathan Ouwerx, Shak Ragoler

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

Comments 39 pages, 4 figures

2306.09347 2023-10-25 cs.CV cs.LG cs.RO 83%

Segment Any Point Cloud Sequences by Distilling Vision Foundation Models

Youquan Liu, Lingdong Kong, Jun Cen, Runnan Chen, Wenwei Zhang, Liang Pan, Kai Chen, Ziwei Liu

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

Comments NeurIPS 2023 (Spotlight); 37 pages, 16 figures, 15 tables; Code at https://github.com/youquanl/Segment-Any-Point-Cloud

2310.14491 2023-10-24 cs.CL 83%

Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models

Yifan Hou, Jiaoda Li, Yu Fei, Alessandro Stolfo, Wangchunshu Zhou, Guangtao Zeng, Antoine Bosselut, Mrinmaya Sachan

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

Comments This work is published in EMNLP 2023

2308.15299 2023-08-30 cs.CL 83%

TaskLAMA: Probing the Complex Task Understanding of Language Models

Quan Yuan, Mehran Kazemi, Xin Xu, Isaac Noble, Vaiva Imbrasaite, Deepak Ramachandran

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

2308.03740 2023-08-08 cs.CY cs.AI 83%

A Cost Analysis of Generative Language Models and Influence Operations

Micah Musser

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

Comments 21 pages, 5 figures; associated GitHub repository available at https://github.com/georgetown-cset/disinfo-costs

2301.00591 2023-06-09 cs.CL cs.SD eess.AS 83%

Analysing Discrete Self Supervised Speech Representation for Spoken Language Modeling

Amitay Sicherman, Yossi Adi

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

Comments Accepted at ICASSP 2023

2304.02202 2023-04-06 cs.CV cs.HC cs.LG 83%

Towards Self-Explainability of Deep Neural Networks with Heatmap Captioning and Large-Language Models

Osman Tursun, Simon Denman, Sridha Sridharan, Clinton Fookes

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

2207.01736 2022-07-06 cs.CL 83%

Probing via Prompting

Jiaoda Li, Ryan Cotterell, Mrinmaya Sachan

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

Comments NAACL 2022

2110.01113 2021-10-05 cs.CL 83%

Probing Language Models for Understanding of Temporal Expressions

Shivin Thukral, Kunal Kukreja, Christian Kavouras

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

Comments Accepted for publication in BlackboxNLP (EMNLP 2021)

2012.14388 2021-09-13 cs.CL 83%

Universal Sentence Representation Learning with Conditional Masked Language Model

Ziyi Yang, Yinfei Yang, Daniel Cer, Jax Law, Eric Darve

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

Comments Accepted to the 2021 Conference on Empirical Methods in Natural Language Processing

2602.04718 2026-08-13 cs.LG cs.AI cs.CL 版本更新 83%

Superposition Without Interference? Towards Isolated Interventions via Almost Orthogonal Features in Language Models

通过语言模型中几乎正交的特征实现孤立干预

Moritz Miller, Florent Draye, Bernhard Schölkopf

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

AI总结该研究基于机械可解释性前提，针对语言模型特征纠缠问题，受“独立因果机制”启发，提出将内部特征约束为几乎正交，通过形式化问题、界定干扰传播并关联正则化，实现对数学推理概念更孤立的干预且保留模型性能。

Comments Published as a conference paper at the Conference on Language Modeling (COLM) 2026

2606.21075 2026-06-23 cs.CL cs.AI cs.LG 新提交 83%

FiLM-Coordinated Dual-Branch Transformer for Global-Local Dependency Modeling in Language Modeling

FiLM协调的双分支Transformer用于语言建模中的全局-局部依赖建模

Zhiqiang Zhou, Xu Ling, Junliang Dai

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

AI总结提出FiLM协调的双分支Transformer，通过特征级线性调制动态协调全局与局部分支，在轻量级设置下优于单分支基线。

Comments 14 pages, 7 figures, 7 tables. Small-scale language modeling study on FiLM-coordinated dual-branch Transformer architectures, including multi-seed evaluation, cross-dataset validation, ablation studies, efficiency analysis, and parameter-matched fairness baselines

2512.07564 2025-12-11 cs.CV cs.AI cs.CL cs.LG 83%

Toward More Reliable Artificial Intelligence: Reducing Hallucinations in Vision-Language Models

迈向更可靠的人工智能：减少视觉-语言模型中的幻觉

Kassoum Sanogo, Renzo Ardiccioni

机构 * Department of CS AI and Data Science（计算机科学与数据科学系）； ESEO Engineering School（ESEO工程学院）； Faculty of Law, Economy, Management（法学院、经济与管理学院）

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

AI总结本文提出无需训练的自我纠正框架，通过不确定性引导的视觉再注意力减少视觉-语言模型中的幻觉，提升响应准确性。

Comments 24 pages, 3 figures, 2 tables. Training-free self-correction framework for vision-language models. Code and implementation details will be released at: https://github.com/kassoumsanogo1/self-correcting-vlm-re-Attention.git

Journal ref The 4th National and International Academic Conference Celebrating the 20th Anniversary of Rajapruk University (2026)

2511.06073 2025-11-11 cs.CL cs.AI cs.LG cs.LO 83%

Stemming Hallucination in Language Models Using a Licensing Oracle

Simeon Emanuilov, Richard Ackermann

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

Comments 23 pages, 4 figures, 8 tables. Introduces the Licensing Oracle, an architectural solution for eliminating hallucinations in language models through formal SHACL validation against knowledge graphs. All datasets and models are available at https://huggingface.co/collections/s-emanuilov/licensing-oracle-experiments

2608.16970 2026-08-19 cs.CR cs.AI cs.LG 新提交 82%

Probing the Prefill: Detecting Code Vulnerabilities via Latent Activations

探测预填充：通过潜在激活检测代码漏洞

Alizishaan Khatri

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

AI总结该研究从四个LLM提取预填充标记激活训练MLP探测器，在四个代码漏洞基准上实现平均F1值41.7%，证明LLM自身代码表示含漏洞信息，为轻量原生筛查提供方向。

1. 知识编辑与模型理解 7608 篇

MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting

Fine-grained Hallucination Detection and Editing for Language Models

Monetizing Currency Pair Sentiments through LLM Explainability

Inspecting and Editing Knowledge Representations in Language Models

Effective Demonstration Annotation for In-Context Learning via Language Model-Based Determinantal Point Process

Entropy, Thermodynamics and the Geometrization of the Language Model

LLM Uncertainty Quantification through Directional Entailment Graph and Claim Level Response Augmentation

LLM-based Hierarchical Concept Decomposition for Interpretable Fine-Grained Image Classification

ExplainableDetector: Exploring Transformer-based Language Modeling Approach for SMS Spam Detection with Explainability Analysis

Monotonic Representation of Numeric Properties in Language Models

generAItor: Tree-in-the-Loop Text Generation for Language Model Explainability and Adaptation

Are Structural Concepts Universal in Transformer Language Models? Towards Interpretable Cross-Lingual Generalization

Mitigating Fine-Grained Hallucination by Fine-Tuning Large Vision-Language Models with Caption Rewrites

Bit Cipher -- A Simple yet Powerful Word Representation System that Integrates Efficiently with Language Models

Language-Agnostic Bias Detection in Language Models with Bias Probing

Automated Parliaments: A Solution to Decision Uncertainty and Misalignment in Language Models

Segment Any Point Cloud Sequences by Distilling Vision Foundation Models

Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models

TaskLAMA: Probing the Complex Task Understanding of Language Models

A Cost Analysis of Generative Language Models and Influence Operations

Analysing Discrete Self Supervised Speech Representation for Spoken Language Modeling

Towards Self-Explainability of Deep Neural Networks with Heatmap Captioning and Large-Language Models

Probing via Prompting

Probing Language Models for Understanding of Temporal Expressions

Universal Sentence Representation Learning with Conditional Masked Language Model

Superposition Without Interference? Towards Isolated Interventions via Almost Orthogonal Features in Language Models

FiLM-Coordinated Dual-Branch Transformer for Global-Local Dependency Modeling in Language Modeling

Toward More Reliable Artificial Intelligence: Reducing Hallucinations in Vision-Language Models

Stemming Hallucination in Language Models Using a Licensing Oracle

Probing the Prefill: Detecting Code Vulnerabilities via Latent Activations