Imagen de Portada

Input Order Shapes LLM Semantic Alignment in Multi-Document Summarization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Ma, Jing
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

OrderSum: Semantic Sentence Ordering for Extractive Summarization
por: Kwon, Taewan, et al.
Publicado: (2025)

Multi-LLM Text Summarization
por: Fang, Jiangnan, et al.
Publicado: (2024)

Do Multi-Document Summarization Models Synthesize?
por: DeYoung, Jay, et al.
Publicado: (2023)

Fine-grained Analysis of Brain-LLM Alignment through Input Attribution
por: Proietti, Michela, et al.
Publicado: (2025)

From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization
por: Belem, Catarina G., et al.
Publicado: (2024)

GLIMPSE: Pragmatically Informative Multi-Document Summarization for Scholarly Reviews
por: Darrin, Maxime, et al.
Publicado: (2024)

AlphaPO: Reward Shape Matters for LLM Alignment
por: Gupta, Aman, et al.
Publicado: (2025)

Key-Element-Informed sLLM Tuning for Document Summarization
por: Ryu, Sangwon, et al.
Publicado: (2024)

Topic-Guided Reinforcement Learning with LLMs for Enhancing Multi-Document Summarization
por: Li, Chuyuan, et al.
Publicado: (2025)

GLIMMER: Incorporating Graph and Lexical Features in Unsupervised Multi-Document Summarization
por: Liu, Ran, et al.
Publicado: (2024)

BERT-VBD: Vietnamese Multi-Document Summarization Framework
por: Vuong, Tuan-Cuong, et al.
Publicado: (2024)

The Effect of Document Summarization on LLM-Based Relevance Judgments
por: Mohtadi, Samaneh, et al.
Publicado: (2025)

Learning to Summarize by Learning to Quiz: Adversarial Agentic Collaboration for Long Document Summarization
por: Wang, Weixuan, et al.
Publicado: (2025)

LightPAL: Lightweight Passage Retrieval for Open Domain Multi-Document Summarization
por: Enomoto, Masafumi, et al.
Publicado: (2024)

Cross-Document Event-Keyed Summarization
por: Walden, William, et al.
Publicado: (2024)

The Order Effect: Investigating Prompt Sensitivity to Input Order in LLMs
por: Guan, Bryan, et al.
Publicado: (2025)

Enriching and Controlling Global Semantics for Text Summarization
por: Nguyen, Thong, et al.
Publicado: (2021)

Benchmarking LLMs on the Semantic Overlap Summarization Task
por: Salvador, John, et al.
Publicado: (2024)

GraphLSS: Integrating Lexical, Structural, and Semantic Features for Long Document Extractive Summarization
por: Bugueño, Margarita, et al.
Publicado: (2024)

Understanding LLM Reasoning for Abstractive Summarization
por: Yuan, Haohan, et al.
Publicado: (2025)

Understanding LLM Behavior in Multi-Target Cross-Lingual Summarization
por: Ryu, Sangwon, et al.
Publicado: (2026)

Scaling Multi-Document Event Summarization: Evaluating Compression vs. Full-Text Approaches
por: Pratapa, Adithya, et al.
Publicado: (2025)

Automatic Summarization of Long Documents
por: Chhibbar, Naman, et al.
Publicado: (2024)

Summarization of Opinionated Political Documents with Varied Perspectives
por: Deas, Nicholas, et al.
Publicado: (2024)

BRIDO: Bringing Democratic Order to Abstractive Summarization
por: Lee, Junhyun, et al.
Publicado: (2025)

Understanding Position Bias Effects on Fairness in Social Multi-Document Summarization
por: Olabisi, Olubusayo, et al.
Publicado: (2024)

SKT5SciSumm -- Revisiting Extractive-Generative Approach for Multi-Document Scientific Summarization
por: To, Huy Quoc, et al.
Publicado: (2024)

Towards Multi-dimensional Evaluation of LLM Summarization across Domains and Languages
por: Min, Hyangsuk, et al.
Publicado: (2025)

Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack
por: Fu, Yu, et al.
Publicado: (2023)

Context-Aware Hierarchical Merging for Long Document Summarization
por: Ou, Litu, et al.
Publicado: (2025)

Document Summarization with Conformal Importance Guarantees
por: Kuwahara, Bruce, et al.
Publicado: (2025)

MetaSumPerceiver: Multimodal Multi-Document Evidence Summarization for Fact-Checking
por: Chen, Ting-Chih, et al.
Publicado: (2024)

EventSum: A Large-Scale Event-Centric Summarization Dataset for Chinese Multi-News Documents
por: Zhu, Mengna, et al.
Publicado: (2024)

Comparative Personalization for Multi-document Summarization
por: Li, Haoyuan, et al.
Publicado: (2025)

ArgCMV: An Argument Summarization Benchmark for the LLM-era
por: Gurjar, Omkar, et al.
Publicado: (2025)

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
por: Yang, Junxiao, et al.
Publicado: (2026)

Automatic Text Summarization (ATS) for Research Documents in Sorani Kurdish
por: Abdulrahman, Rondik Hadi, et al.
Publicado: (2025)

Large Language Models for Summarizing Czech Historical Documents and Beyond
por: Tran, Václav, et al.
Publicado: (2025)

Same Input, Different Scores: A Multi Model Study on the Inconsistency of LLM Judge
por: Lau, Fiona
Publicado: (2026)

CCSBench: Evaluating Compositional Controllability in LLMs for Scientific Document Summarization
por: Ding, Yixi, et al.
Publicado: (2024)