语言大模型 / LLM - arXivDaily 专题

2404.00925 2024-04-02 cs.CV cs.CL 70%

LLMs are Good Sign Language Translators

Jia Gong, Lin Geng Foo, Yixuan He, Hossein Rahmani, Jun Liu

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

Comments Accepted to CVPR 2024

2403.17306 2024-04-02 cs.AI 70%

Visual Hallucination: Definition, Quantification, and Prescriptive Remediations

Anku Rani, Vipula Rawte, Harshad Sharma, Neeraj Anand, Krishnav Rajbangshi, Amit Sheth, Amitava Das

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

2403.16913 2024-03-26 cs.CL 70%

New Intent Discovery with Attracting and Dispersing Prototype

Shun Zhang, Jian Yang, Jiaqi Bai, Chaoran Yan, Tongliang Li, Zhao Yan, Zhoujun Li

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

Comments COLING 2024

2403.12244 2024-03-20 cs.CL 70%

Zero-Shot Multi-task Hallucination Detection

Patanjali Bhamidipati, Advaith Malladi, Manish Shrivastava, Radhika Mamidi

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

2403.04427 2024-03-08 cs.CE cs.AI 70%

Sentiment-driven prediction of financial returns: a Bayesian-enhanced FinBERT approach

Raffaele Giuseppe Cestari, Simone Formentin

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

Comments Version exposed at XXV Workshop on Quantitative Finance Bologna (Italy), April 11-13 2024 (not peer reviewed but accepted for the workshop)

2311.09800 2024-03-05 cs.CL 70%

$\textit{Dial BeInfo for Faithfulness}$: Improving Factuality of Information-Seeking Dialogue via Behavioural Fine-Tuning

Evgeniia Razumovskaia, Ivan Vulić, Pavle Marković, Tomasz Cichy, Qian Zheng, Tsung-Hsien Wen, Paweł Budzianowski

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

2402.15059 2024-02-26 cs.CL cs.IR 70%

ColBERT-XM: A Modular Multi-Vector Representation Model for Zero-Shot Multilingual Information Retrieval

Antoine Louis, Vageesh Saxena, Gijs van Dijck, Gerasimos Spanakis

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

Comments Under review. Code is available at https://github.com/ant-louis/xm-retrievers

2402.13584 2024-02-22 cs.CL 70%

WinoViz: Probing Visual Properties of Objects Under Different States

Woojeong Jin, Tejas Srinivasan, Jesse Thomason, Xiang Ren

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

Comments Preprint

2402.11324 2024-02-20 cs.CL 70%

EVEDIT: Event-based Knowledge Editing with Deductive Editing Boundaries

Jiateng Liu, Pengfei Yu, Yuji Zhang, Sha Li, Zixuan Zhang, Heng Ji

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

2402.11190 2024-02-20 cs.CL 70%

Disclosure and Mitigation of Gender Bias in LLMs

Xiangjue Dong, Yibo Wang, Philip S. Yu, James Caverlee

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

Comments The first two authors contribute equally

2402.09642 2024-02-16 cs.CL 70%

Answer is All You Need: Instruction-following Text Embedding via Answering the Question

Letian Peng, Yuwei Zhang, Zilong Wang, Jayanth Srinivasa, Gaowen Liu, Zihan Wang, Jingbo Shang

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

2402.02006 2024-02-14 cs.LG 70%

PresAIse, A Prescriptive AI Solution for Enterprises

Wei Sun, Scott McFaddin, Linh Ha Tran, Shivaram Subramanian, Kristjan Greenewald, Yeshi Tenzin, Zack Xue, Youssef Drissi, Markus Ettl

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

Comments 14 pages

2306.13149 2024-02-09 cs.HC cs.LG 70%

"Filling the Blanks'': Identifying Micro-activities that Compose Complex Human Activities of Daily Living

Soumyajit Chatterjee, Bivas Mitra, Sandip Chakraborty

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

Comments 23 pages, 4 tables, 7 figures

2402.05110 2024-02-08 cs.LG 70%

Opening the AI black box: program synthesis via mechanistic interpretability

Eric J. Michaud, Isaac Liao, Vedang Lad, Ziming Liu, Anish Mudide, Chloe Loughridge, Zifan Carl Guo, Tara Rezaei Kheirkhah, Mateja Vukelić, Max Tegmark

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

Comments 24 pages

2305.08809 2024-02-08 cs.CL 70%

Interpretability at Scale: Identifying Causal Mechanisms in Alpaca

Zhengxuan Wu, Atticus Geiger, Thomas Icard, Christopher Potts, Noah D. Goodman

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

Comments NeurIPS 2023 with Author Corrections

2402.01935 2024-02-06 cs.CL 70%

Code Representation Learning At Scale

Dejiao Zhang, Wasi Ahmad, Ming Tan, Hantian Ding, Ramesh Nallapati, Dan Roth, Xiaofei Ma, Bing Xiang

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

Comments 10 pages

Journal ref ICLR 2024

2212.00281 2024-01-31 cs.CV cs.CL 70%

Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models

Zhuowan Li, Cihang Xie, Benjamin Van Durme, Alan Yuille

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

Comments Accepted to EACL 2024. Code is released at https://github.com/Lizw14/visual_probing

2401.15449 2024-01-30 cs.CL 70%

Learning to Trust Your Feelings: Leveraging Self-awareness in LLMs for Hallucination Mitigation

Yuxin Liang, Zhuoyang Song, Hao Wang, Jiaxing Zhang

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

2306.00788 2024-01-19 cs.LG stat.ML 70%

Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression

Runtian Zhai, Bingbin Liu, Andrej Risteski, Zico Kolter, Pradeep Ravikumar

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

Comments ICLR 2024 spotlight. 34 pages

2401.07897 2024-01-17 cs.CL 70%

The Pitfalls of Defining Hallucination

Kees van Deemter

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

Comments Accepted for publication in Computational Linguistics on 30 Dec. 2023. (9 Pages.)

2312.04333 2024-01-10 cs.CL 70%

Is Bigger and Deeper Always Better? Probing LLaMA Across Scales and Layers

Nuo Chen, Ning Wu, Shining Liang, Ming Gong, Linjun Shou, Dongmei Zhang, Jia Li

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

Comments 15 pages

2401.03646 2024-01-09 cs.LG cs.NE 70%

Evaluating Brain-Inspired Modular Training in Automated Circuit Discovery for Mechanistic Interpretability

Jatin Nainani

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

Comments 15 pages, 7 figures

2312.15184 2023-12-27 cs.LG 70%

ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-order Optimization

Shuoran Jiang, Qingcai Chen, Youchen Pan, Yang Xiang, Yukang Lin, Xiangping Wu, Chuanyi Liu, Xiaobao Song

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

2311.18034 2023-12-19 cs.CL 70%

Hyperpolyglot LLMs: Cross-Lingual Interpretability in Token Embeddings

Andrea W Wen-Yi, David Mimno

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

Journal ref Published in EMNLP 2023

2312.09532 2023-12-18 cs.AI 70%

Grounding for Artificial Intelligence

Bing Liu

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

2311.11334 2023-11-21 cs.DL cs.AI 70%

Using Causal Threads to Explain Changes in a Dynamic System

Robert B. Allen

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

Comments 2023 ICADL

2310.12860 2023-10-31 cs.CL cs.CY 70%

Probing LLMs for hate speech detection: strengths and vulnerabilities

Sarthak Roy, Ashish Harshavardhan, Animesh Mukherjee, Punyajoy Saha

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

Comments 13 pages, 9 figures, 7 tables, accepted to findings of EMNLP 2023

2308.02122 2023-10-30 cs.CR cs.CL 70%

ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP

Lu Yan, Zhuo Zhang, Guanhong Tao, Kaiyuan Zhang, Xuan Chen, Guangyu Shen, Xiangyu Zhang

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

2310.15455 2023-10-25 cs.HC cs.AI 70%

UI Layout Generation with LLMs Guided by UI Grammar

Yuwen Lu, Ziang Tong, Qinyi Zhao, Chengzhi Zhang, Toby Jia-Jun Li

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

Comments ICML 2023 Workshop on AI and HCI

2310.07155 2023-10-24 cs.CL 70%

"A Tale of Two Movements": Identifying and Comparing Perspectives in #BlackLivesMatter and #BlueLivesMatter Movements-related Tweets using Weakly Supervised Graph-based Structured Prediction

Shamik Roy, Dan Goldwasser

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

Comments Findings of EMNLP 2023 (Camera Ready)

1. 知识编辑与模型理解 7565 篇

LLMs are Good Sign Language Translators

Visual Hallucination: Definition, Quantification, and Prescriptive Remediations

New Intent Discovery with Attracting and Dispersing Prototype

Zero-Shot Multi-task Hallucination Detection

Sentiment-driven prediction of financial returns: a Bayesian-enhanced FinBERT approach

$\textit{Dial BeInfo for Faithfulness}$: Improving Factuality of Information-Seeking Dialogue via Behavioural Fine-Tuning

ColBERT-XM: A Modular Multi-Vector Representation Model for Zero-Shot Multilingual Information Retrieval

WinoViz: Probing Visual Properties of Objects Under Different States

EVEDIT: Event-based Knowledge Editing with Deductive Editing Boundaries

Disclosure and Mitigation of Gender Bias in LLMs

Answer is All You Need: Instruction-following Text Embedding via Answering the Question

PresAIse, A Prescriptive AI Solution for Enterprises

"Filling the Blanks'': Identifying Micro-activities that Compose Complex Human Activities of Daily Living

Opening the AI black box: program synthesis via mechanistic interpretability

Interpretability at Scale: Identifying Causal Mechanisms in Alpaca

Code Representation Learning At Scale

Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models

Learning to Trust Your Feelings: Leveraging Self-awareness in LLMs for Hallucination Mitigation

Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression

The Pitfalls of Defining Hallucination

Is Bigger and Deeper Always Better? Probing LLaMA Across Scales and Layers

Evaluating Brain-Inspired Modular Training in Automated Circuit Discovery for Mechanistic Interpretability

ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-order Optimization

Hyperpolyglot LLMs: Cross-Lingual Interpretability in Token Embeddings

Grounding for Artificial Intelligence

Using Causal Threads to Explain Changes in a Dynamic System

Probing LLMs for hate speech detection: strengths and vulnerabilities

ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP

UI Layout Generation with LLMs Guided by UI Grammar

"A Tale of Two Movements": Identifying and Comparing Perspectives in #BlackLivesMatter and #BlueLivesMatter Movements-related Tweets using Weakly Supervised Graph-based Structured Prediction