Lune

EMNLP Findings2025

CtrlNews: LLM-based Multi-Agent Controllable News Writing via Knowledge Gravitational Field

Yifei Xu, Yingjie Zong, Wang Zhonghua, Sirui Wu, Yuan Rao, Dan Zhang, Shuiguang Deng

Abstract

News writing empowered by large language models (LLMs) has emerged as a prevalent trend due to their efficiency and scalability. This paradigm necessitates dynamic information acquisition, knowledge structuring, and precise viewpoint articulation. However, current approaches often rely on superficially retrieved information and oversimplified knowledge enumeration, resulting in shallow, repetitive, and unordered outputs. Additionally, the lack of controllability over narrative viewpoints fails to align with user-defined preferences. To address these limitations, we propose an LLM-based multi-agent controllable news writing framework termed CtrlNews. The framework simulates expert questioning through automated role assignment and question generation followed by a three-layer hierarchical gravitational graph iteratively refined via expansionreflection cycles. Besides, we elaborate a finegrained viewpoint control mechanism to precisely regulate bias, emotion, and exaggeration attributes. When composing long-form news articles, the controlled viewpoints are extended via emotion-preserving composition and selfreflection refinement to ensure the consistency of viewpoint control and prevent the dilution of the control effect. Experiments on quality and control effect evaluation, news dissemination effect assessment, and human evaluation demonstrate significant improvements across multiple metrics compared to existing methods.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society cites Language Models are Few-Shot Learners
  • Scaling Data-Constrained Language Models cites Language Models are Few-Shot Learners
  • AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors cites CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on20

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained TransformersWenhui Wang, Furu Wei, Li Dong, Hangbo Bao et al.NeurIPS 2020 · 2,727 citations
  3. CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model SocietyGuohao Li, Hasan Hammoud, Hani Itani, Dmitrii Khizbullin et al.NeurIPS 2023 · 1,975 citations
  4. AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent BehaviorsWeize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang et al.ICLR 2024 · 594 citations
  5. Scaling Data-Constrained Language ModelsNiklas Muennighoff, Alexander M. Rush, Boaz Barak, Teven Le Scao et al.NeurIPS 2023 · 475 citations

Related papers

  1. Towards Designing a Question-Answering Chatbot for Online News: Understanding Questions and PerspectivesMd. Naimul Hoque, Ayman A. Mahfuz, Mayukha Sridhatri Kindi, Naeemul HassanCHI 2024 · 8 citations
  2. DataNarrative: Automated Data-Driven Storytelling with Visualizations and TextsMohammed Saidul Islam, Md. Tahmid Rahman Laskar, Md. Rizwan Parvez, Enamul Hoque et al.EMNLP 2024 · 11 citations
  3. Controllable Protein Sequence Generation with LLM Preference OptimizationXiangyu Liu, Yi Liu, Silei Chen, Wei HuAAAI 2025 · 8 citations
  4. WRitEer: A Multi-Objective, Preference-Driven Multi-Agent Framework for Human-Like Advanced Text GenerationJunchuan Yu, Yuyang SunAAAI 2026
  5. KARMA: Leveraging Multi-Agent LLMs for Automated Knowledge Graph EnrichmentYuxing Lu, Wei Wu, Xukai Zhao, Rui Peng et al.NeurIPS 2025 · 41 citations
Dusk over the sea between two cliffs drawn in fine vertical lines