mlsanityData to 14 Oct 2026

CoNewsReader: Supporting Comprehensive Understanding and Raising Critical Thoughts on Social Media News Through Comments

arXiv 2604.27905 ↗First posted 30 Apr 2026cs.HCcited by 0

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Critical news reading (CNR), which requires grasping the holistic ideas of and raising critical thoughts on the news, is beneficial yet challenging for general people who usually get information on daily social media. Comments under the news can aid CNR by providing complementary information and other readers' diverse and critical thoughts. However, it is under-investigated how to leverage these comments to support users in CNR. In this paper, we first derive user requirements for a comment-based CNR tool from literature and a formative study (N=12). Then, we develop CoNewsReader, a comment-based interactive CNR tool powered by a large language model. CoNewsReader supports users in grasping the news idea with complementary information from comments, filtering useful comments for CNR, and getting questions generated based on the comments to conduct critical thinking. Our within-subjects study with 24 university students indicates that compared to a baseline news reading interface in social media, participants with CoNewsReader have a more engaging CNR experience and perform better on comprehending the news and raising critical thoughts. We discuss design considerations for supporting reading tasks with user- and machine-generated content.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 10 of its 125 references that are in the map. First posted on arXiv 30 Apr 2026.

Builds on

10 of 125 references.

References · 10

  1. 2023Mistral 7Bcited by 3,164
  2. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,089
  3. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 279
  4. 2021How Many Data Points is a Prompt Worth?cited by 198
  5. 2022Toward Unifying Text Segmentation and Long Document Summarizationcited by 28
  6. 2023LLM Based Multi-Document Summarization Exploiting Main-Event Biased Monotone Submodular Content Extractioncited by 7
  7. 2023Attributable and Scalable Opinion Summarizationcited by 6
  8. 2023ReadProbe: A Demo of Retrieval-Enhanced Large Language Models to Support Lateral Readingcited by 3
  9. 2024ComViewer: An Interactive Visual Tool to Help Viewers Seek Social Support in Online Mental Health Communitiescited by 2
  10. 2025Iffy-Or-Not: Extending the Web to Support the Critical Evaluation of Fallacious Textscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Think Fast, Think Slow, Think Critical: Designing an Automated Propaganda Detection Tool
  2. 2026How Human Feedback Shapes AI-generated Community Notes
  3. 2026PERCEIVE: A Benchmark for Personalized Emotion and Communication Behavior Understanding on Social Media
  4. 2025Biased by Design: Leveraging AI Biases to Enhance Critical Thinking of News Readers
  5. 2023UniPoll: A Unified Social Media Poll Generation Framework via Multi-Objective Optimization
  6. 2025Improving Multilingual Social Media Insights: Aspect-based Comment Analysis
  7. 2025Can Memory-Augmented LLM Agents Aid Journalism in Interpreting and Framing News for Diverse Audiences?
  8. 2022"I think this is the most disruptive technology": Exploring Sentiments of ChatGPT Early Adopters using Twitter Data