Aspect-Based Summarization with Self-Aspect Retrieval Enhanced Generation

• URL: http://arxiv.org/abs/2504.13054v1
• Date: Thu, 17 Apr 2025 16:09:57 GMT
• Title: Aspect-Based Summarization with Self-Aspect Retrieval Enhanced Generation
• Authors: Yichao Feng, Shuai Zhao, Yueqiu Li, Luwei Xiao, Xiaobao Wu, Anh Tuan Luu,
• Abstract summary: Aspect-based summarization aims to generate summaries tailored to specific aspects.<n>We propose a novel framework for aspect-based summarization: Self-Aspect Retrieval Enhanced Summary Generation.
• Score: 23.801244006016972
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: 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.

Related papers

• Learning Task Representations from In-Context Learning [73.72066284711462]
  Large language models (LLMs) have demonstrated remarkable proficiency in in-context learning. We introduce an automated formulation for encoding task information in ICL prompts as a function of attention heads. We show that our method's effectiveness stems from aligning the distribution of the last hidden state with that of an optimally performing in-context-learned model.
  arXiv  Detail & Related papers  (2025-02-08T00:16:44Z)
• ChallengeMe: An Adversarial Learning-enabled Text Summarization Framework [7.34943328546274]
  This paper constructs an adversarial learning-based prompt framework named ChallengeMe.<n>It includes three cascaded solutions: generation prompts, evaluation prompts, and feedback optimization.<n>The results of mixed case studies on the text summarization task show that the proposed framework can generate more accurate and fluent text summaries.
  arXiv  Detail & Related papers  (2025-02-07T16:59:34Z)
• SUMI-IFL: An Information-Theoretic Framework for Image Forgery Localization with Sufficiency and Minimality Constraints [66.85363924364628]
  Image forgery localization (IFL) is a crucial technique for preventing tampered image misuse and protecting social safety.<n>We introduce a novel information-theoretic IFL framework named SUMI-IFL that imposes sufficiency-view and minimality-view constraints on forgery feature representation.
  arXiv  Detail & Related papers  (2024-12-13T09:08:02Z)
• SpeciaLex: A Benchmark for In-Context Specialized Lexicon Learning [4.1205832766381985]
  SpeciaLex is a benchmark for evaluating a language model's ability to follow specialized lexicon-based constraints. We present an empirical evaluation of 15 open and closed-source LLMs and discuss insights on how factors such as model scale, openness, setup, and recency affect performance upon evaluating with the benchmark.
  arXiv  Detail & Related papers  (2024-07-18T08:56:02Z)
• FENICE: Factuality Evaluation of summarization based on Natural language Inference and Claim Extraction [85.26780391682894]
  We propose Factuality Evaluation of summarization based on Natural language Inference and Claim Extraction (FENICE) FENICE leverages an NLI-based alignment between information in the source document and a set of atomic facts, referred to as claims, extracted from the summary. Our metric sets a new state of the art on AGGREFACT, the de-facto benchmark for factuality evaluation.
  arXiv  Detail & Related papers  (2024-03-04T17:57:18Z)
• Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model [86.9619638550683]
  Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired data.<n>However, these models display significant limitations when applied to downstream tasks, such as fine-grained image classification, as a result of decision shortcuts''
  arXiv  Detail & Related papers  (2024-03-01T09:01:53Z)
• ConstraintMatch for Semi-constrained Clustering [32.92933231199262]
  Constrained clustering allows the training of classification models using pairwise constraints only, which are weak and relatively easy to mine. We propose a semi-supervised context whereby a large amount of textitunconstrained data is available alongside a smaller set of constraints, and propose textitConstraintMatch to leverage such unconstrained data.
  arXiv  Detail & Related papers  (2023-11-26T19:31:52Z)
• How Well Do Text Embedding Models Understand Syntax? [50.440590035493074]
  The ability of text embedding models to generalize across a wide range of syntactic contexts remains under-explored. Our findings reveal that existing text embedding models have not sufficiently addressed these syntactic understanding challenges. We propose strategies to augment the generalization ability of text embedding models in diverse syntactic scenarios.
  arXiv  Detail & Related papers  (2023-11-14T08:51:00Z)
• SummIt: Iterative Text Summarization via ChatGPT [12.966825834765814]
  We propose SummIt, an iterative text summarization framework based on large language models like ChatGPT. Our framework enables the model to refine the generated summary iteratively through self-evaluation and feedback. We also conduct a human evaluation to validate the effectiveness of the iterative refinements and identify a potential issue of over-correction.
  arXiv  Detail & Related papers  (2023-05-24T07:40:06Z)
• Controllable Summarization with Constrained Markov Decision Process [50.04321779376415]
  We study controllable text summarization which allows users to gain control on a particular attribute. We propose a novel training framework based on Constrained Markov Decision Process (CMDP) Our framework can be applied to control important attributes of summarization, including length, covered entities, and abstractiveness.
  arXiv  Detail & Related papers  (2021-08-07T09:12:53Z)
• Lexically-constrained Text Generation through Commonsense Knowledge Extraction and Injection [62.071938098215085]
  We focus on the Commongen benchmark, wherein the aim is to generate a plausible sentence for a given set of input concepts. We propose strategies for enhancing the semantic correctness of the generated text.
  arXiv  Detail & Related papers  (2020-12-19T23:23:40Z)

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.