语言大模型 / LLM

What Matters in Memorizing and Recalling Facts? Multifaceted Benchmarks for Knowledge Probing in Language Models

Xin Zhao, Naoki Yoshinaga, Daisuke Oba

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

Comments 29 pages, 8 figures, 25 tables, Accepted by EMNLP 2024 (Findings)

Unleashing the Potentials of Likelihood Composition for Multi-modal Language Models

Shitian Zhao, Renrui Zhang, Xu Luo, Yan Wang, Shanghang Zhang, Peng Gao

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

LLM Internal States Reveal Hallucination Risk Faced With a Query

Ziwei Ji, Delong Chen, Etsuko Ishii, Samuel Cahyawijaya, Yejin Bang, Bryan Wilie, Pascale Fung

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

Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis

Zeping Yu, Sophia Ananiadou

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

Comments Accepted by EMNLP 2024 main. Mechanistic interpretability for arithmetic tasks in large language models

MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions

Zexuan Zhong, Zhengxuan Wu, Christopher D. Manning, Christopher Potts, Danqi Chen

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

Comments EMNLP 2023. Our code and datasets are available at https://github.com/princeton-nlp/MQuAKE

Enhance Modality Robustness in Text-Centric Multimodal Alignment with Adversarial Prompting

Yun-Da Tsai, Ting-Yu Yen, Keng-Te Liao, Shou-De Lin

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

Comments arXiv admin note: text overlap with arXiv:2407.05036

BEAF: Observing BEfore-AFter Changes to Evaluate Hallucination in Vision-language Models

Moon Ye-Bin, Nam Hyeon-Woo, Wonseok Choi, Tae-Hyun Oh

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

Comments Accepted at ECCV 2024. [Project Pages] https://beafbench.github.io/

LLM-Empowered State Representation for Reinforcement Learning

Boyuan Wang, Yun Qu, Yuhang Jiang, Jianzhun Shao, Chang Liu, Wenming Yang, Xiangyang Ji

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

DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection

Herun Wan, Shangbin Feng, Zhaoxuan Tan, Heng Wang, Yulia Tsvetkov, Minnan Luo

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

Language Models can Exploit Cross-Task In-context Learning for Data-Scarce Novel Tasks

Anwoy Chatterjee, Eshaan Tanwar, Subhabrata Dutta, Tanmoy Chakraborty

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

Comments Accepted at ACL 2024 Main

Uncertainty Aware Learning for Language Model Alignment

Yikun Wang, Rui Zheng, Liang Ding, Qi Zhang, Dahua Lin, Dacheng Tao

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

Comments ACL 2024

Enhanced Language Model Truthfulness with Learnable Intervention and Uncertainty Expression

Farima Fatahi Bayat, Xin Liu, H. V. Jagadish, Lu Wang

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

Comments ACL 2024 Findings (Long paper)

Facilitating Human-LLM Collaboration through Factuality Scores and Source Attributions

Hyo Jin Do, Rachel Ostrand, Justin D. Weisz, Casey Dugan, Prasanna Sattigeri, Dennis Wei, Keerthiram Murugesan, Werner Geyer

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

Comments Submitted to the Trust and Reliance in Evolving Human-AI Workflows (TREW) Workshop at CHI 2024

A Philosophical Introduction to Language Models - Part II: The Way Forward

Raphaël Millière, Cameron Buckner

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

Concept-Guided LLM Agents for Human-AI Safety Codesign

Florian Geissler, Karsten Roscher, Mario Trapp

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

Comments 5 pages

Journal ref Proceedings of the AAAI-make Spring Symposium, 2024

LLM-based Extraction of Contradictions from Patents

Stefan Trapp, Joachim Warschat

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

Comments 10 pages, 2 tables

PeerGPT: Probing the Roles of LLM-based Peer Agents as Team Moderators and Participants in Children's Collaborative Learning

Jiawen Liu, Yuanyuan Yao, Pengcheng An, Qi Wang

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

Comments To appear at CHI EA '24

Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning

Xiaoxin He, Xavier Bresson, Thomas Laurent, Adam Perold, Yann LeCun, Bryan Hooi

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

Comments In Proceedings of ICLR 2024

Do LLMs Know about Hallucination? An Empirical Investigation of LLM's Hidden States

Hanyu Duan, Yi Yang, Kar Yan Tam

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

Comments 9 pages, 8 figures, 2 tables (13 pages, 12 figures, 13 tables including references and appendices)

Probing Language Models' Gesture Understanding for Enhanced Human-AI Interaction

Philipp Wicke

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

Comments Preprint

ESGReveal: An LLM-based approach for extracting structured data from ESG reports

Yi Zou, Mengying Shi, Zhongjie Chen, Zhu Deng, ZongXiong Lei, Zihan Zeng, Shiming Yang, HongXiang Tong, Lei Xiao, Wenwen Zhou

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

Evaluating Object Hallucination in Large Vision-Language Models

Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Wayne Xin Zhao, Ji-Rong Wen

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

Comments Accepted to EMNLP 2023

GPT-MolBERTa: GPT Molecular Features Language Model for molecular property prediction

Suryanarayanan Balaji, Rishikesh Magar, Yayati Jadhav, Amir Barati Farimani

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

Comments Paper has 17 pages, 4 figures and 4 tables, along with 71 references

Exploring the Relationship between LLM Hallucinations and Prompt Linguistic Nuances: Readability, Formality, and Concreteness

Vipula Rawte, Prachi Priya, S. M Towhidul Islam Tonmoy, S M Mehedi Zaman, Amit Sheth, Amitava Das

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

The Geometry of Harmful Intent: Training-Free Anomaly Detection via Angular Deviation in LLM Residual Streams

有害意图的几何学：通过残差流中的角度偏差实现无训练异常检测

Isaac Llorente-Saguer

机构 * Independent Researcher（独立研究者） 纠错

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

AI总结 本文提出LatentBiopsy方法，通过分析大语言模型残差流激活的几何特性，无需训练即可检测有害提示。该方法基于残差流激活的主成分分析和角度偏差，实现高精度的异常检测，具有低延迟和强鲁棒性。

Comments 20 pages, 10 figures, 3 tables. Training-free harmful-prompt detector via angular deviation in LLM residual streams. Evaluated on six Qwen variants (base / instruct / abliterated). Achieves AUROC over 0.937 (harmful-vs-normative) and 1.000 (harmful-vs-benign-aggressive) with no harmful training data

Evolving Personalities in Chaos: An LLM-Augmented Framework for Character Discovery in the Iterated Prisoners Dilemma under Environmental Stress

混沌中的性格演变：一种结合大语言模型的框架用于在环境压力下的迭代囚徒困境中发现角色

Oguzhan Yildirim

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

AI总结 本文提出一种结合大语言模型的框架，在环境压力下通过迭代囚徒困境发现可解释的角色原型，提升策略的鲁棒性和可解释性。

Comments 10 pages, 5 figures. Project assignment; exploratory study on LLM-based adaptive agents

DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation

DexterSQL：用于Text-to-SQL生成的深度模式探索与基于规则的修正

Anik Pramanik, Murat Kantarcioglu, Vincent Oria, Shantanu Sharma

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

AI总结 DexterSQL是基于提示的非微调Text-to-SQL系统，通过深度模式探索器、数据库无关规则创建器、多路径SQL生成三个组件，在BIRD-Dev数据集上提升了开源与闭源大语言模型的Text-to-SQL生成准确率。

Attention-Path Fragility as an Uncertainty Signal in Large Language Models

注意力路径脆弱性作为大语言模型中的不确定性信号

Minsoo Kim, Sungyoung Ji, Kisung Moon, Ilyong Yoon

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

AI总结 本研究提出 ASMI 作为大语言模型的不确定性信号，通过掩码注意力头测量子网络间的 BALD 互信息，在基于事实的问答任务中优于基线，可有效识别自信但脆弱的预测。

Comments 19 pages, Under review

Cultural Awareness is Represented but Not Decoded: Tracing Mythological Knowledge across 18 Open-Source LLMs

文化意识被表征但未被解码：追踪18个开源大语言模型（LLM）中的神话知识

Iaroslav Chelombitko, Ekaterina Chelombitko, Mika Hämäläinen

机构 * DataSpike ； Metropolia University of Applied Sciences（梅托波利亞應用科學大學） ； Neapolis University Pafos（帕福斯尼阿波利斯大學） 纠错

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

AI总结 该研究分析18个开源LLM的神话知识表征，发现文化表征存在于模型残差流中，但解码器因提示语言偏差无法解码非主导文化内容，还发布了相关跨文化研究工具与基准。

Comments 45 pages, 23 figures, 18 tables. Dataset: https://huggingface.co/datasets/Aragoner/folkmotif Code: https://github.com/AragonerUA/folkmotif

Moir: Let the Model Direct Its Own Story for Robust Cross-Domain Knowledge Editing

莫尔：让模型为稳健的跨域知识编辑指引自身方向

Jea Kwon, Jiwon Kim, Dong-kyum Kim, Meeyoung Cha

机构 * Max Planck Institute for Security and Privacy（马克斯·普朗克安全与隐私研究所） 纠错

专题命中 知识编辑与模型理解 ：SFT(abstract,abstract_cn)；language model(abstract)；pretraining(abstract)；post-training(abstract)

AI总结 研究针对语言模型训练后知识编辑核心能力退化问题，提出莫尔方法，通过从模型自身解码分布采样估计保留协方差，无需外部数据，可作插入组件。实验表明该方法能在多模型上扩展保留能力，提升准确率，凸显分布对齐对无损编辑的关键作用。