Aspect-Based Summarization with Self-Aspect Retrieval Enhanced Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910913526759424 |
|---|---|
| author | Feng, Yichao Zhao, Shuai Li, Yueqiu Xiao, Luwei Wu, Xiaobao Luu, Anh Tuan |
| author_facet | Feng, Yichao Zhao, Shuai Li, Yueqiu Xiao, Luwei Wu, Xiaobao Luu, Anh Tuan |
| contents | Aspect-based summarization aims to generate summaries tailored to specific aspects, addressing the resource constraints and limited generalizability of traditional summarization approaches. Recently, large language models have shown promise in this task without the need for training. However, they rely excessively on prompt engineering and face token limits and hallucination challenges, especially with in-context learning. To address these challenges, in this paper, we propose a novel framework for aspect-based summarization: Self-Aspect Retrieval Enhanced Summary Generation. Rather than relying solely on in-context learning, given an aspect, we employ an embedding-driven retrieval mechanism to identify its relevant text segments. This approach extracts the pertinent content while avoiding unnecessary details, thereby mitigating the challenge of token limits. Moreover, our framework optimizes token usage by deleting unrelated parts of the text and ensuring that the model generates output strictly based on the given aspect. With extensive experiments on benchmark datasets, we demonstrate that our framework not only achieves superior performance but also effectively mitigates the token limitation problem. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_13054 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Aspect-Based Summarization with Self-Aspect Retrieval Enhanced Generation Feng, Yichao Zhao, Shuai Li, Yueqiu Xiao, Luwei Wu, Xiaobao Luu, Anh Tuan Computation and Language Artificial Intelligence Aspect-based summarization aims to generate summaries tailored to specific aspects, addressing the resource constraints and limited generalizability of traditional summarization approaches. Recently, large language models have shown promise in this task without the need for training. However, they rely excessively on prompt engineering and face token limits and hallucination challenges, especially with in-context learning. To address these challenges, in this paper, we propose a novel framework for aspect-based summarization: Self-Aspect Retrieval Enhanced Summary Generation. Rather than relying solely on in-context learning, given an aspect, we employ an embedding-driven retrieval mechanism to identify its relevant text segments. This approach extracts the pertinent content while avoiding unnecessary details, thereby mitigating the challenge of token limits. Moreover, our framework optimizes token usage by deleting unrelated parts of the text and ensuring that the model generates output strictly based on the given aspect. With extensive experiments on benchmark datasets, we demonstrate that our framework not only achieves superior performance but also effectively mitigates the token limitation problem. |
| title | Aspect-Based Summarization with Self-Aspect Retrieval Enhanced Generation |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2504.13054 |