# Faithful Summarisation under Disagreement via Belief-Level Aggregation

arXiv: https://arxiv.org/abs/2601.04889 · HTML: https://mlsanity.com/paper/2601.04889/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 50 references that are in the map.
- First posted on arXiv 8 Jan 2026.

## Builds on (most cited first, 19 of 19)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods](https://mlsanity.com/paper/2403.02901/) (2024)
- [OpinionDigest: A Simple Framework for Opinion Summarization](https://mlsanity.com/paper/2005.01901/) (2020)
- [Belief Revision: The Adaptability of Large Language Models Reasoning](https://mlsanity.com/paper/2406.19764/) (2024)
- [Generalization Bias in Large Language Model Summarization of Scientific Research](https://mlsanity.com/paper/2504.00025/) (2025)
- [Informative and Controllable Opinion Summarization](https://mlsanity.com/paper/1909.02322/) (2019)
- [Dialect Diversity in Text Summarization on Twitter](https://mlsanity.com/paper/2007.07860/) (2020)
- [Fair Abstractive Summarization of Diverse Perspectives](https://mlsanity.com/paper/2311.07884/) (2023)
- [Examining Bias in Opinion Summarisation Through the Perspective of Opinion Diversity](https://mlsanity.com/paper/2306.04424/) (2023)
- [Bias in Opinion Summarisation from Pre-training to Adaptation: A Case Study in Political Bias](https://mlsanity.com/paper/2402.00322/) (2024)
- [Do Multi-Document Summarization Models Synthesize?](https://mlsanity.com/paper/2301.13844/) (2023)
- [Large-Scale and Multi-Perspective Opinion Summarization with Diverse Review Subsets](https://mlsanity.com/paper/2310.13340/) (2023)
- [Fairness for Whom? Understanding the Reader's Perception of Fairness in Text Summarization](https://mlsanity.com/paper/2101.12406/) (2021)
- [LLMs Do Not See Age: Assessing Demographic Bias in Automated Systematic Review Synthesis](https://mlsanity.com/paper/2511.06000/) (2025)
- [QA-prompting: Improving Summarization with Large Language Models using Question-Answering](https://mlsanity.com/paper/2505.14347/) (2025)
- [REFER: Mitigating Bias in Opinion Summarisation via Frequency Framed Prompting](https://mlsanity.com/paper/2509.15723/) (2025)

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

- [When Summaries Distort Decisions: Information Fidelity in LLM-Compressed Financial Analysis](https://mlsanity.com/paper/2606.29251/) (2026)

## Abstract (arXiv)

Opinion and multi-document summarisation often involve genuinely conflicting viewpoints, yet many existing approaches, particularly LLM-based systems, implicitly smooth disagreement and over-represent majority opinions. This limits the faithfulness of generated summaries in opinion-heavy settings. We introduce a disagreement-aware synthesis pipeline that separates belief-level aggregation from language generation. Documents are first represented as structured belief sets and aggregated using distance-based belief merging operators that explicitly model conflict. Large language models are then used only to realise the aggregated beliefs as natural language summaries. We evaluate the approach across multiple model families and scales, comparing it to methods that perform explicit aggregation during generation. Our results show that while sufficiently large models can match belief-level aggregation when aggregation is handled at generation time, this behaviour is not stable across architectures or capacities. In contrast, belief-level aggregation combined with simple prompting yields consistently strong disagreement-aware performance across models, while maintaining fluent and grounded summaries.