# Considering Length Diversity in Retrieval-Augmented Summarization

arXiv: https://arxiv.org/abs/2503.09249 · HTML: https://mlsanity.com/paper/2503.09249/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation.
- Builds on 24 of its 58 references that are in the map.
- First posted on arXiv 12 Mar 2025.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy](https://mlsanity.com/paper/2305.15294/) (2023)
- [Selective Annotation Makes Language Models Better Few-Shot Learners](https://mlsanity.com/paper/2209.01975/) (2022)
- [Constrained Language Models Yield Few-Shot Semantic Parsers](https://mlsanity.com/paper/2104.08768/) (2021)
- [Controlling Output Length in Neural Encoder-Decoders](https://mlsanity.com/paper/1609.09552/) (2016)
- [Complementary Explanations for Effective In-Context Learning](https://mlsanity.com/paper/2211.13892/) (2022)
- [Prototypical Calibration for Few-shot Learning of Language Models](https://mlsanity.com/paper/2205.10183/) (2022)
- [Positional Encoding to Control Output Sequence Length](https://mlsanity.com/paper/1904.07418/) (2019)
- [Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing](https://mlsanity.com/paper/2205.12253/) (2022)
- [Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Tasks](https://mlsanity.com/paper/2305.17653/) (2023)
- [Prompt-Based Length Controlled Generation with Multiple Control Types](https://mlsanity.com/paper/2406.10278/) (2024)
- [Efficient Unsupervised Sentence Compression by Fine-tuning Transformers with Reinforcement Learning](https://mlsanity.com/paper/2205.08221/) (2022)
- [Explanation Selection Using Unlabeled Data for Chain-of-Thought Prompting](https://mlsanity.com/paper/2302.04813/) (2023)
- [Syntactically Look-Ahead Attention Network for Sentence Compression](https://mlsanity.com/paper/2002.01145/) (2020)
- [Quantifying the Gaps Between Translation and Native Perception in Training for Multimodal, Multilingual Retrieval](https://mlsanity.com/paper/2410.02027/) (2024)

## Built on by (most cited first, 2 of 2)

- [CG-TTRL: Context-Guided Test-Time Reinforcement Learning for On-Device Large Language Models](https://mlsanity.com/paper/2511.06430/) (2025)
- [Retrieval-Augmented Question Answering over Scientific Literature for the Electron-Ion Collider](https://mlsanity.com/paper/2604.02259/) (2026)

## Abstract (arXiv)

This study investigates retrieval-augmented summarization by specifically examining the impact of exemplar summary lengths under length constraints, not covered by previous work. We propose a Diverse Length-aware Maximal Marginal Relevance (DL-MMR) algorithm to better control summary lengths. This algorithm combines the query relevance with diverse target lengths in retrieval-augmented summarization. Unlike previous methods that necessitate exhaustive exemplar exemplar relevance comparisons using MMR, DL-MMR considers the exemplar target length as well and avoids comparing exemplars to each other, thereby reducing computational cost and conserving memory during the construction of an exemplar pool. Experimental results showed the effectiveness of DL-MMR, which considers length diversity, compared to the original MMR algorithm. DL-MMR additionally showed the effectiveness in memory saving of 781,513 times and computational cost reduction of 500,092 times, while maintaining the same level of informativeness.