Cover Image

LLM as Attention-Informed NTM and Topic Modeling as long-input Generation: Interpretability and long-Context Capability

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Xuan, Yang, Zhongliang, Li, Haolun, Chu, Beilin, Tian, Rui, Li, Yu, Tan, Shaolin, Zhou, Linna
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Reduced Spatial Dependency for More General Video-level Deepfake Detection
by: Chu, Beilin, et al.
Published: (2025)

FinCPRG: A Bidirectional Generation Pipeline for Hierarchical Queries and Rich Relevance in Financial Chinese Passage Retrieval
by: Xu, Xuan, et al.
Published: (2025)

FIRE: Robust Detection of Diffusion-Generated Images via Frequency-Guided Reconstruction Error
by: Chu, Beilin, et al.
Published: (2024)

FinBERT2: A Specialized Bidirectional Encoder for Bridging the Gap in Finance-Specific Deployment of Large Language Models
by: Xu, Xuan, et al.
Published: (2025)

S2vNTM: Semi-supervised vMF Neural Topic Modeling
by: Xu, Weijie, et al.
Published: (2023)

Robust Uncertainty Quantification for Factual Generation of Large Language Models
by: Zhang, Yuhao, et al.
Published: (2026)

When Semantics Regulate: Rethinking Patch Shuffle and Internal Bias for Generated Image Detection with CLIP
by: Chu, Beilin, et al.
Published: (2025)

EvoCorps: An Evolutionary Multi-Agent Framework for Depolarizing Online Discourse
by: Lin, Ning, et al.
Published: (2026)

Label-Confidence-Aware Uncertainty Estimation in Natural Language Generation
by: Lin, Qinhong, et al.
Published: (2024)

Enhancing Topic Interpretability for Neural Topic Modeling through Topic-wise Contrastive Learning
by: Gao, Xin, et al.
Published: (2024)

OracleProto: A Reproducible Framework for Benchmarking LLM Native Forecasting via Knowledge Cutoff and Temporal Masking
by: Ma, Yiding, et al.
Published: (2026)

CreditXAI: A Multi-Agent System for Explainable Corporate Credit Rating
by: Shi, Yumeng, et al.
Published: (2025)

Agent Guide: A Simple Agent Behavioral Watermarking Framework
by: Huang, Kaibo, et al.
Published: (2025)

AgentMark: Utility-Preserving Behavioral Watermarking for Agents
by: Huang, Kaibo, et al.
Published: (2026)

Efficient Streaming Voice Steganalysis in Challenging Detection Scenarios
by: Zhou, Pengcheng, et al.
Published: (2024)

Challenges for Generative AI in Legal Reasoning
by: Linna, Eljas, et al.
Published: (2025)

ACF: A Collaborative Framework for Agent Covert Communication under Cognitive Asymmetry
by: Wu, Wansheng, et al.
Published: (2026)

GSDFuse: Capturing Cognitive Inconsistencies from Multi-Dimensional Weak Signals in Social Media Steganalysis
by: Huang, Kaibo, et al.
Published: (2025)

Can LLM Agents Really Debate? A Controlled Study of Multi-Agent Debate in Logical Reasoning
by: Wu, Haolun, et al.
Published: (2025)

MEMO: Fine-grained Tensor Management For Ultra-long Context LLM Training
by: Zhao, Pinxue, et al.
Published: (2024)

Fast‐Charging Capabilities of Hard Carbon Anodes in Sodium‐Ion Batteries: Mechanisms, Strategies, and Prospects
by: Shunyuan Tan, et al.
Published: (2025)

SUS backprop: linear backpropagation algorithm for long inputs in transformers
by: Pankov, Sergey, et al.
Published: (2025)

DASM: Domain-Aware Sharpness Minimization for Multi-Domain Voice Stream Steganalysis
by: Zhou, Pengcheng, et al.
Published: (2026)

Erythromycin Shortage in an NTM ‐Endemic Country: Implications for Bronchiectasis Care and Antimicrobial Stewardship
by: Takanori Asakura, et al.
Published: (2025)

Tree of Agents: Improving Long-Context Capabilities of Large Language Models through Multi-Perspective Reasoning
by: Yu, Song, et al.
Published: (2025)

Creating Targeted, Interpretable Topic Models with LLM-Generated Text Augmentation
by: Lieb, Anna, et al.
Published: (2025)

Generative Modeling and Data Augmentation for Power System Production Simulation
by: Xu, Linna, et al.
Published: (2024)

Role of the Public Library in the 21st Century.
by: Yu, Linna
Published: (2000)

CreditARF: A Framework for Corporate Credit Rating with Annual Report and Financial Feature Integration
by: Shi, Yumeng, et al.
Published: (2025)

Whispering Agents: An Event-driven Covert Communication Protocol For the Internet of Agents
by: Huang, Kaibo, et al.
Published: (2025)

Intelligent DoS and DDoS Detection: A Hybrid GRU-NTM Approach to Network Security
by: Panggabean, Caroline, et al.
Published: (2025)

Topical review: Challenges and solutions for eye care in long‐term care
by: Divya Anantharaman, et al.
Published: (2025)

Constant‐force photonic projectile for long‐distance targeting delivery
by: Chun Meng, et al.
Published: (2024)

Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding
by: Zhang, Weixu, et al.
Published: (2026)

Applying LLM and Topic Modelling in Psychotherapeutic Contexts
by: Vanin, Alexander, et al.
Published: (2024)

Koala: Key frame-conditioned long video-LLM
by: Tan, Reuben, et al.
Published: (2024)

Interpretable PROTAC Degradation Prediction With Structure‐Informed Deep Ternary Attention Framework
by: Zhenglu Chen, et al.
Published: (2025)

Advancing Topic Segmentation and Outline Generation in Chinese Texts: The Paragraph-level Topic Representation, Corpus, and Benchmark
by: Jiang, Feng, et al.
Published: (2023)

NSI-IBP: A General Numerical Singular Integral Method via Integration by Parts
by: Liao, Shaolin
Published: (2024)

Context-Alignment: Activating and Enhancing LLM Capabilities in Time Series
by: Hu, Yuxiao, et al.
Published: (2025)