PerSphere: A Comprehensive Framework for Multi-Faceted Perspective Retrieval and Summarization
Not on the map. Why?
Abstract (arXiv)
As online platforms and recommendation algorithms evolve, people are increasingly trapped in echo chambers, leading to biased understandings of various issues. To combat this issue, we have introduced PerSphere, a benchmark designed to facilitate multi-faceted perspective retrieval and summarization, thus breaking free from these information silos. For each query within PerSphere, there are two opposing claims, each supported by distinct, non-overlapping perspectives drawn from one or more documents. Our goal is to accurately summarize these documents, aligning the summaries with the respective claims and their underlying perspectives. This task is structured as a two-step end-to-end pipeline that includes comprehensive document retrieval and multi-faceted summarization. Furthermore, we propose a set of metrics to evaluate the comprehensiveness of the retrieval and summarization content. Experimental results on various counterparts for the pipeline show that recent models struggle with such a complex task. Analysis shows that the main challenge lies in long context and perspective extraction, and we propose a simple but effective multi-agent summarization system, offering a promising solution to enhance performance on PerSphere.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 24 of its 50 references that are in the map. First posted on arXiv 17 Dec 2024.
Builds on
24 of 50 references.
References · 24
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
- 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
- 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
- 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
- 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
- 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
- 2023An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuningcited by 622
- 2023Enabling Large Language Models to Generate Text with Citationscited by 584
- 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 519
- 2021Large Dual Encoders Are Generalizable Retrieverscited by 454
- 2024Generative Representational Instruction Tuningcited by 227
12 more
- 2019Seeing Things from a Different Angle: Discovering Diverse Perspectives about Claimscited by 73
- 2018Cross-topic Argument Mining from Heterogeneous Sources Using Attention-based Neural Networkscited by 58
- 2016Neural Network-Based Abstract Generation for Opinions and Argumentscited by 46
- 2019Corpus Wide Argument Mining -- a Working Solutioncited by 36
- 2020DebateSum: A large-scale argument mining and summarization datasetcited by 34
- 2016Echo Chambers: Emotional Contagion and Group Polarization on Facebookcited by 27
- 2022ArgLegalSumm: Improving Abstractive Summarization of Legal Documents with Argument Miningcited by 25
- 2021Overview of the 2021 Key Point Analysis Shared Taskcited by 23
- 2022Exploiting Sentiment and Common Sense for Zero-shot Stance Detectioncited by 16
- 2024Which Side Are You On? A Multi-task Dataset for End-to-End Argument Summarisation and Evaluationcited by 13
- 2023Towards Argument-Aware Abstractive Summarization of Long Legal Opinions with Summary Rerankingcited by 9
- 2023Enhancing Argument Structure Extraction with Efficient Leverage of Contextual Informationcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.