# CARPAS: Towards Content-Aware Refinement of Provided Aspects for Summarization in Large Language Models

arXiv: https://arxiv.org/abs/2510.07177 · HTML: https://mlsanity.com/paper/2510.07177/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 8 Oct 2025.

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarization](https://mlsanity.com/paper/2302.08081/) (2023)
- [Summarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly Supervised](https://mlsanity.com/paper/1808.08858/) (2018)
- [Synthetic Data Generation Using Large Language Models: Advances in Text and Code](https://mlsanity.com/paper/2503.14023/) (2025)
- [WikiAsp: A Dataset for Multi-domain Aspect-based Summarization](https://mlsanity.com/paper/2011.07832/) (2020)
- [ASPECTNEWS: Aspect-Oriented Summarization of News Documents](https://mlsanity.com/paper/2110.08296/) (2021)
- [Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents](https://mlsanity.com/paper/2106.00130/) (2021)
- [OASum: Large-Scale Open Domain Aspect-based Summarization](https://mlsanity.com/paper/2212.09233/) (2022)
- [Summarizing Text on Any Aspects: A Knowledge-Informed Weakly-Supervised Approach](https://mlsanity.com/paper/2010.06792/) (2020)
- [EntSUM: A Data Set for Entity-Centric Summarization](https://mlsanity.com/paper/2204.02213/) (2022)
- [ACLSum: A New Dataset for Aspect-based Summarization of Scientific Publications](https://mlsanity.com/paper/2403.05303/) (2024)
- [OpenAsp: A Benchmark for Multi-document Open Aspect-based Summarization](https://mlsanity.com/paper/2312.04440/) (2023)
- [Template-Based Financial Report Generation in Agentic and Decomposed Information Retrieval](https://mlsanity.com/paper/2504.14233/) (2025)
- [Disordered-DABS: A Benchmark for Dynamic Aspect-Based Summarization in Disordered Texts](https://mlsanity.com/paper/2402.10554/) (2024)
- [MODABS: Multi-Objective Learning for Dynamic Aspect-Based Summarization](https://mlsanity.com/paper/2406.03479/) (2024)
- [Leveraging the Power of LLMs: A Fine-Tuning Approach for High-Quality Aspect-Based Summarization](https://mlsanity.com/paper/2408.02584/) (2024)
- [Aspect-Based Summarization with Self-Aspect Retrieval Enhanced Generation](https://mlsanity.com/paper/2504.13054/) (2025)
- [Aspect-based Meeting Transcript Summarization: A Two-Stage Approach with Weak Supervision on Sentence Classification](https://mlsanity.com/paper/2311.04292/) (2023)

## Abstract (arXiv)

Aspect-based summarization has attracted significant attention for its ability to generate more fine-grained and user-aligned summaries. While most existing approaches assume a set of predefined aspects as input, real-world scenarios often present challenges where these given aspects may be incomplete, irrelevant, or entirely missing from the document. Users frequently expect systems to adaptively refine or filter the provided aspects based on the actual content. In this paper, we initiate this novel task setting, termed Content-Aware Refinement of Provided Aspects for Summarization (CARPAS), with the aim of dynamically adjusting the provided aspects based on the document context before summarizing. We construct three new datasets and conduct pilot experiments with four representative prompting strategies. Our analysis reveals that LLMs often over-generate aspects, resulting in excessively long and misaligned summaries. Building on this observation, we introduce a two-stage framework that derives lightweight scope guidance before aspect refinement and summarization, improving focus and reducing over-generation. Our extensive experiments show that the proposed approach significantly improves performance across all datasets. Moreover, our deeper analyses uncover LLMs' compliance when the requested number of aspects differs from their own estimations, establishing a crucial insight for the deployment of LLMs in similar real-world applications.