CWF: A Collaborative Writing Framework for Personalized and Reliable Popular Science Writing

• URL: http://arxiv.org/abs/2609.06126v1
• Date: Sat, 05 Sep 2026 14:51:22 GMT
• Title: CWF: A Collaborative Writing Framework for Personalized and Reliable Popular Science Writing
• Abstract summary: We introduce Personalized and Reliable Popular Science Writing, a novel task that requires adapting scientific explanations to audiences with different cognitive levels.<n>To address these challenges, we first construct a dataset of 39,134 entries and a reader-centric Personalized Science Communication Benchmark (PSCB) that jointly evaluates audience adaptation and factual accuracy.
• Score: 7.365498362292651
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce Personalized and Reliable Popular Science Writing, a novel task that requires adapting scientific explanations to audiences with different cognitive levels while preserving factual accuracy. However, improving personalization often introduces simplifications that increase the risk of hallucination and factual distortion. To address these challenges, we first construct a dataset of 39,134 entries and a reader-centric Personalized Science Communication Benchmark (PSCB) that jointly evaluates audience adaptation and factual accuracy. To reduce data and computational requirements while improving generalization across domains and audiences, we introduce DA-MoE, which explicitly decouples audience adaptation from domain knowledge through separate modeling. To enable robust verification and revision in evidence-scarce scenarios, a multi-agent fact-checking mechanism that augments limited evidence with role-specific agent debate and propagates confidence over a graph is proposed. Experiments on PSCB show that our approach achieves state-of-the-art performance. Our code is open-sourced at https://github.com/DPInnovationWorks/CWF.

Related papers

• FedAvg for HAR: Exploring the Tradeoff Between Personalized and Generalization Accuracy [39.58793931604357]
  In this paper, we design and implement several testing scenarios devoted to evaluating and comparing the centralized, local, and federated paradigm performances.<n>We present experimental results of the FedAvg algorithm applied to the Human Activity Recognition (HAR) domain to understand the trade-off between personalized and generalized accuracy.<n>Results show that, although FedAvg confirms a higher degree of personalization capabilities while keeping a high degree of generalization with respect to the traditional centralized learning, this result is not so obvious under stressful conditions.
  arXiv  Detail & Related papers  (2026-07-03T13:51:53Z)
• Towards Automated Community Notes Generation with Large Vision Language Models for Combating Contextual Deception [8.79051023144961]
  We study the automated Community Notes generation method for image-based contextual deception.<n>Unlike prior work that primarily focuses on deception detection, Community Notes-style systems need to generate concise and grounded notes.<n>We propose ACCNote, a retrieval-augmented, multi-agent collaboration framework built on large vision-language models.
  arXiv  Detail & Related papers  (2026-03-23T18:21:23Z)
• Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval [60.25608870901428]
  Trustworthiness is a core research challenge for agentic AI systems built on Large Language Models (LLMs)<n>We propose the task of fact-checking without retrieval, focusing on the verification of arbitrary natural language claims, independent of their source robustness.
  arXiv  Detail & Related papers  (2026-03-05T18:42:51Z)
• FedUTR: Federated Recommendation with Augmented Universal Textual Representation for Sparse Interaction Scenarios [58.33672784127872]
  Federated recommendations (FRs) have emerged as an on-device privacy-preserving paradigm.<n>We propose a novel method named FedUTR, which incorporates item textual representations as a complement to interaction behaviors.<n>Our method achieves superior performance, with improvements of up to 59% across all datasets compared to the SOTA baselines.
  arXiv  Detail & Related papers  (2026-01-29T08:55:19Z)
• Graphing the Truth: Structured Visualizations for Automated Hallucination Detection in LLMs [0.0]
  This paper introduces a framework that organizes proprietary knowledge and model-generated content into interactive visual knowledge graphs.<n>Users can diagnose inconsistencies, identify weak reasoning chains, and supply corrective feedback.
  arXiv  Detail & Related papers  (2025-11-29T23:09:15Z)
• What Drives Paper Acceptance? A Process-Centric Analysis of Modern Peer Review [2.9282248958475345]
  We present a large-scale empirical study of ICLR 2017-2025, encompassing over 28,000 submissions.<n>Our results show that factors beyond scientific novelty significantly shape acceptance outcomes.<n>We propose data-driven guidelines for authors, reviewers, and meta-reviewers to enhance transparency and fairness in peer review.
  arXiv  Detail & Related papers  (2025-09-30T03:00:10Z)
• FedSC: Federated Learning with Semantic-Aware Collaboration [12.366529890744822]
  Federated learning (FL) aims to train models collaboratively across clients without sharing data for privacy-preserving.<n>We propose Federated Learning with Semantic-Aware Collaboration (FedSC) to capture client-specific and class-relevant knowledge across heterogeneous clients.
  arXiv  Detail & Related papers  (2025-06-26T05:04:55Z)
• RELIC: Investigating Large Language Model Responses using Self-Consistency [58.63436505595177]
  Large Language Models (LLMs) are notorious for blending fact with fiction and generating non-factual content, known as hallucinations. We propose an interactive system that helps users gain insight into the reliability of the generated text.
  arXiv  Detail & Related papers  (2023-11-28T14:55:52Z)
• From Chaos to Clarity: Claim Normalization to Empower Fact-Checking [57.024192702939736]
  Claim Normalization (aka ClaimNorm) aims to decompose complex and noisy social media posts into more straightforward and understandable forms. We propose CACN, a pioneering approach that leverages chain-of-thought and claim check-worthiness estimation. Our experiments demonstrate that CACN outperforms several baselines across various evaluation measures.
  arXiv  Detail & Related papers  (2023-10-22T16:07:06Z)
• CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation [91.16551253297588]
  COunterfactual Generation via Retrieval and Editing (CORE) is a retrieval-augmented generation framework for creating diverse counterfactual perturbations for training. CORE first performs a dense retrieval over a task-related unlabeled text corpus using a learned bi-encoder. CORE then incorporates these into prompts to a large language model with few-shot learning capabilities, for counterfactual editing.
  arXiv  Detail & Related papers  (2022-10-10T17:45:38Z)
• Exploring the Trade-off between Plausibility, Change Intensity and Adversarial Power in Counterfactual Explanations using Multi-objective Optimization [73.89239820192894]
  We argue that automated counterfactual generation should regard several aspects of the produced adversarial instances. We present a novel framework for the generation of counterfactual examples.
  arXiv  Detail & Related papers  (2022-05-20T15:02:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.