mlsanityData to 7 Oct 2026

Considering Length Diversity in Retrieval-Augmented Summarization

arXiv 2503.09249 ↗First posted 12 Mar 2025cs.CL cs.AIcited by 2

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

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.

Key facts. Cited by 2 papers in the map (data through 7 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.

Builds on

24 of 58 references.

References · 24

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  6. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,883
  7. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  8. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  9. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  10. 2021Learning To Retrieve Prompts for In-Context Learningcited by 641
  11. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 343
  12. 2022Selective Annotation Makes Language Models Better Few-Shot Learnerscited by 242
12 more
  1. 2021Constrained Language Models Yield Few-Shot Semantic Parserscited by 162
  2. 2016Controlling Output Length in Neural Encoder-Decoderscited by 75
  3. 2022Complementary Explanations for Effective In-Context Learningcited by 71
  4. 2022Prototypical Calibration for Few-shot Learning of Language Modelscited by 58
  5. 2019Positional Encoding to Control Output Sequence Lengthcited by 56
  6. 2022Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsingcited by 50
  7. 2023Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Taskscited by 21
  8. 2024Prompt-Based Length Controlled Generation with Multiple Control Typescited by 19
  9. 2022Efficient Unsupervised Sentence Compression by Fine-tuning Transformers with Reinforcement Learningcited by 18
  10. 2023Explanation Selection Using Unlabeled Data for Chain-of-Thought Promptingcited by 12
  11. 2020Syntactically Look-Ahead Attention Network for Sentence Compressioncited by 6
  12. 2024Quantifying the Gaps Between Translation and Native Perception in Training for Multimodal, Multilingual Retrievalcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025CG-TTRL: Context-Guided Test-Time Reinforcement Learning for On-Device Large Language Modelscited by 1
  2. 2026Retrieval-Augmented Question Answering over Scientific Literature for the Electron-Ion Collidercited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Estimating Optimal Context Length for Hybrid Retrieval-augmented Multi-document Summarization
  2. 2025Diversity Enhances an LLM's Performance in RAG and Long-context Task
  3. 2025Beyond Perplexity: Let the Reader Select Retrieval Summaries via Spectrum Projection Score
  4. 2026Finding the Right Balance: Relevance and Diversity in LLM Retrieval
  5. 2024Better RAG using Relevant Information Gain
  6. 2024Vector Retrieval with Similarity and Diversity: How Hard Is It?
  7. 2025FG-RAG: Enhancing Query-Focused Summarization with Context-Aware Fine-Grained Graph RAG
  8. 2023Context-aware Decoding Reduces Hallucination in Query-focused Summarization