CARPAS: Towards Content-Aware Refinement of Provided Aspects for Summarization in Large Language Models
cs.CL
Submitted: 2025-10-08
Updated: 2026-09-02
Comments: EMNLP2026 FinNLP workshop
License: http://creativecommons.org/licenses/by/4.0/
The gist: Aspect-based summarization has attracted significant attention for its ability to generate more fine-grained and user-aligned summaries.
Terminology
Abstract
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.
Sources
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- The Llama 3 Herd of Models
- Aspect-Based Summarization with Self-Aspect Retrieval Enhanced Generation
- DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
- Large Language Models: A Survey
- GPT-4o System Card
- Leveraging the Power of LLMs: A Fine-Tuning Approach for High-Quality Aspect-Based Summarization
- Gemma 3 Technical Report
- Synthetic Data Generation Using Large Language Models: Advances in Text and Code
- Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarization
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering