# Explaining Mixtures of Sources in News Articles

arXiv: https://arxiv.org/abs/2411.05192 · HTML: https://mlsanity.com/paper/2411.05192/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 63 references that are in the map.
- First posted on arXiv 7 Nov 2024.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [Plan-And-Write: Towards Better Automatic Storytelling](https://mlsanity.com/paper/1811.05701/) (2018)
- [Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning](https://mlsanity.com/paper/2301.11916/) (2023)
- [Stay on topic with Classifier-Free Guidance](https://mlsanity.com/paper/2306.17806/) (2023)
- [Language Model Evaluation Beyond Perplexity](https://mlsanity.com/paper/2106.00085/) (2021)
- [Seeing Things from a Different Angle: Discovering Diverse Perspectives about Claims](https://mlsanity.com/paper/1906.03538/) (2019)
- [The Argument Reasoning Comprehension Task: Identification and Reconstruction of Implicit Warrants](https://mlsanity.com/paper/1708.01425/) (2017)
- [Cross-Domain Label-Adaptive Stance Detection](https://mlsanity.com/paper/2104.07467/) (2021)
- [Visconde: Multi-document QA with GPT-3 and Neural Reranking](https://mlsanity.com/paper/2212.09656/) (2022)
- [Model Criticism for Long-Form Text Generation](https://mlsanity.com/paper/2210.08444/) (2022)
- [NewsEdits: A News Article Revision Dataset and a Document-Level Reasoning Challenge](https://mlsanity.com/paper/2206.07106/) (2022)
- [LongStory: Coherent, Complete and Length Controlled Long story Generation](https://mlsanity.com/paper/2311.15208/) (2023)
- [Bayesian Example Selection Improves In-Context Learning for Speech, Text, and Visual Modalities](https://mlsanity.com/paper/2404.14716/) (2024)
- ["Don't quote me on that": Finding Mixtures of Sources in News Articles](https://mlsanity.com/paper/2104.09656/) (2021)
- [Identifying Informational Sources in News Articles](https://mlsanity.com/paper/2305.14904/) (2023)
- [Helping News Editors Write Better Headlines: A Recommender to Improve the Keyword Contents & Shareability of News Headlines](https://mlsanity.com/paper/1705.09656/) (2017)

## Built on by (most cited first, 1 of 1)

- [DiscoSum: Discourse-aware News Summarization](https://mlsanity.com/paper/2506.06930/) (2025)

## Abstract (arXiv)

Human writers plan, then write. For large language models (LLMs) to play a role in longer-form article generation, we must understand the planning steps humans make before writing. We explore one kind of planning, source-selection in news, as a case-study for evaluating plans in long-form generation. We ask: why do specific stories call for specific kinds of sources? We imagine a generative process for story writing where a source-selection schema is first selected by a journalist, and then sources are chosen based on categories in that schema. Learning the article's plan means predicting the schema initially chosen by the journalist. Working with professional journalists, we adapt five existing schemata and introduce three new ones to describe journalistic plans for the inclusion of sources in documents. Then, inspired by Bayesian latent-variable modeling, we develop metrics to select the most likely plan, or schema, underlying a story, which we use to compare schemata. We find that two schemata: stance and social affiliation best explain source plans in most documents. However, other schemata like textual entailment explain source plans in factually rich topics like "Science". Finally, we find we can predict the most suitable schema given just the article's headline with reasonable accuracy. We see this as an important case-study for human planning, and provides a framework and approach for evaluating other kinds of plans. We release a corpora, NewsSources, with annotations for 4M articles.