Multi-document Summarization through Multi-document Event Relation Graph Reasoning in LLMs: a case study in Framing Bias Mitigation

• URL: http://arxiv.org/abs/2506.12978v1
• Date: Sun, 15 Jun 2025 22:14:59 GMT
• Title: Multi-document Summarization through Multi-document Event Relation Graph Reasoning in LLMs: a case study in Framing Bias Mitigation
• Authors: Yuanyuan Lei, Ruihong Huang,
• Abstract summary: We aim to mitigate media bias by generating a neutralized summary given multiple articles presenting different ideological views.<n>Motivated by the critical role of events and event relations in media bias detection, we propose to increase awareness of bias in LLMs.
• Score: 18.351777831207965
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Media outlets are becoming more partisan and polarized nowadays. Most previous work focused on detecting media bias. In this paper, we aim to mitigate media bias by generating a neutralized summary given multiple articles presenting different ideological views. Motivated by the critical role of events and event relations in media bias detection, we propose to increase awareness of bias in LLMs via multi-document events reasoning and use a multi-document event relation graph to guide the summarization process. This graph contains rich event information useful to reveal bias: four common types of in-doc event relations to reflect content framing bias, cross-doc event coreference relation to reveal content selection bias, and event-level moral opinions to highlight opinionated framing bias. We further develop two strategies to incorporate the multi-document event relation graph for neutralized summarization. Firstly, we convert a graph into natural language descriptions and feed the textualized graph into LLMs as a part of a hard text prompt. Secondly, we encode the graph with graph attention network and insert the graph embedding into LLMs as a soft prompt. Both automatic evaluation and human evaluation confirm that our approach effectively mitigates both lexical and informational media bias, and meanwhile improves content preservation.

Related papers

• On Positional Bias of Faithfulness for Long-form Summarization [83.63283027830657]
  Large Language Models (LLMs) often exhibit positional bias in long-context settings, under-attending to information in the middle of inputs. We investigate the presence of this bias in long-form summarization, its impact on faithfulness, and various techniques to mitigate this bias.
  arXiv  Detail & Related papers  (2024-10-31T03:50:15Z)
• Mapping the Media Landscape: Predicting Factual Reporting and Political Bias Through Web Interactions [0.7249731529275342]
  We propose an extension to a recently presented news media reliability estimation method. We assess the classification performance of four reinforcement learning strategies on a large news media hyperlink graph. Our experiments, targeting two challenging bias descriptors, factual reporting and political bias, showed a significant performance improvement at the source media level.
  arXiv  Detail & Related papers  (2024-10-23T08:18:26Z)
• Sentence-level Media Bias Analysis with Event Relation Graph [18.351777831207965]
  We identify media bias at the sentence level, and pinpoint bias sentences that intend to sway readers' opinions. In particular, we observe that events in a bias sentence need to be understood in associations with other events in the document. We propose to construct an event relation graph to explicitly reason about event-event relations for sentence-level bias identification.
  arXiv  Detail & Related papers  (2024-04-02T08:16:03Z)
• Fair Abstractive Summarization of Diverse Perspectives [103.08300574459783]
  A fair summary should provide a comprehensive coverage of diverse perspectives without underrepresenting certain groups. We first formally define fairness in abstractive summarization as not underrepresenting perspectives of any groups of people. We propose four reference-free automatic metrics by measuring the differences between target and source perspectives.
  arXiv  Detail & Related papers  (2023-11-14T03:38:55Z)
• Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articles [136.84278943588652]
  We propose a new task of summarizing diverse information encountered in multiple news articles encompassing the same event. To facilitate this task, we outlined a data collection schema for identifying diverse information and curated a dataset named DiverseSumm. The dataset includes 245 news stories, with each story comprising 10 news articles and paired with a human-validated reference.
  arXiv  Detail & Related papers  (2023-09-17T20:28:17Z)
• Bias in News Summarization: Measures, Pitfalls and Corpora [4.917075909999548]
  We introduce definitions for biased behaviours in summarization models, along with practical operationalizations. We measure gender bias in English summaries generated by both purpose-built summarization models and general purpose chat models. We find content selection in single document summarization to be largely unaffected by gender bias, while hallucinations exhibit evidence of bias.
  arXiv  Detail & Related papers  (2023-09-14T22:20:27Z)
• Open-Domain Event Graph Induction for Mitigating Framing Bias [89.46744219887005]
  We argue that studying and identifying framing bias is a crucial step towards trustworthy event understanding. We propose a novel task, neutral event graph induction, to address this problem. Our task aims to induce such structural knowledge with minimal framing bias in an open domain.
  arXiv  Detail & Related papers  (2023-05-22T08:57:42Z)
• Scientific Paper Extractive Summarization Enhanced by Citation Graphs [50.19266650000948]
  We focus on leveraging citation graphs to improve scientific paper extractive summarization under different settings. Preliminary results demonstrate that citation graph is helpful even in a simple unsupervised framework. Motivated by this, we propose a Graph-based Supervised Summarization model (GSS) to achieve more accurate results on the task when large-scale labeled data are available.
  arXiv  Detail & Related papers  (2022-12-08T11:53:12Z)
• NeuS: Neutral Multi-News Summarization for Mitigating Framing Bias [54.89737992911079]
  We propose a new task, a neutral summary generation from multiple news headlines of the varying political spectrum. One of the most interesting observations is that generation models can hallucinate not only factually inaccurate or unverifiable content, but also politically biased content.
  arXiv  Detail & Related papers  (2022-04-11T07:06:01Z)
• Modeling Multi-level Context for Informational Bias Detection by Contrastive Learning and Sentential Graph Network [13.905580921329717]
  Informational bias can only be detected together with the context. In this paper, we integrate three levels of context to detect the sentence-level informational bias in English news articles. Our model, MultiCTX, uses contrastive learning and sentence graphs together with Graph Attention Network (GAT) to encode these three degrees of context.
  arXiv  Detail & Related papers  (2022-01-25T15:07:09Z)

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.