Salvato in:
Dettagli Bibliografici
Autori principali: Aghaebe, Favour Yahdii, Apekey, Tanefa, Williams, Elizabeth, Moosavi, Nafise Sadat
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2601.04889
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909984822919168
author Aghaebe, Favour Yahdii
Apekey, Tanefa
Williams, Elizabeth
Moosavi, Nafise Sadat
author_facet Aghaebe, Favour Yahdii
Apekey, Tanefa
Williams, Elizabeth
Moosavi, Nafise Sadat
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_04889
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Faithful Summarisation under Disagreement via Belief-Level Aggregation
Aghaebe, Favour Yahdii
Apekey, Tanefa
Williams, Elizabeth
Moosavi, Nafise Sadat
Computation and Language
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.
title Faithful Summarisation under Disagreement via Belief-Level Aggregation
topic Computation and Language
url https://arxiv.org/abs/2601.04889