mlsanityData to 14 Oct 2026

Improving Document Retrieval Coherence for Semantically Equivalent Queries

arXiv 2508.07975 ↗First posted 11 Aug 2025cs.IR cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Dense Retrieval (DR) models have proven to be effective for Document Retrieval and Information Grounding tasks. Usually, these models are trained and optimized for improving the relevance of top-ranked documents for a given query. Previous work has shown that popular DR models are sensitive to the query and document lexicon: small variations of it may lead to a significant difference in the set of retrieved documents. In this paper, we propose a variation of the Multi-Negative Ranking loss for training DR that improves the coherence of models in retrieving the same documents with respect to semantically similar queries. The loss penalizes discrepancies between the top-k ranked documents retrieved for diverse but semantic equivalent queries. We conducted extensive experiments on various datasets, MS-MARCO, Natural Questions, BEIR, and TREC DL 19/20. The results show that (i) models optimizes by our loss are subject to lower sensitivity, and, (ii) interestingly, higher accuracy.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 38 of its 68 references that are in the map. First posted on arXiv 11 Aug 2025.

Builds on

38 of 68 references.

References · 38

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  3. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  4. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  5. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  6. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  7. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 981
  8. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 573
  9. 2024Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inferencecited by 554
  10. 2023State of What Art? A Call for Multi-Prompt LLM Evaluationcited by 310
  11. 2017Efficient Natural Language Response Suggestion for Smart Replycited by 229
  12. 2018WikiHow: A Large Scale Text Summarization Datasetcited by 204
26 more
  1. 2021PAQ: 65 Million Probably-Asked Questions and What You Can Do With Themcited by 200
  2. 2022Ask Me Anything: A simple strategy for prompting language modelscited by 155
  3. 2024Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessmentcited by 126
  4. 2021GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrievalcited by 119
  5. 2023How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrievalcited by 118
  6. 2020Few-Shot Generative Conversational Query Rewritingcited by 85
  7. 2024Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvementscited by 83
  8. 2024SPLADE-v3: New baselines for SPLADEcited by 72
  9. 2023Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewritingcited by 69
  10. 2024POSIX: A Prompt Sensitivity Index For Large Language Modelscited by 59
  11. 2019AmazonQA: A Review-Based Question Answering Taskcited by 43
  12. 2023How are Prompts Different in Terms of Sensitivity?cited by 35
  13. 2023Black-box Adversarial Attacks against Dense Retrieval Models: A Multi-view Contrastive Learning Methodcited by 29
  14. 2023Predicting Question-Answering Performance of Large Language Models through Semantic Consistencycited by 28
  15. 2022Conversational Question Answering on Heterogeneous Sourcescited by 26
  16. 2020Embedding-based Zero-shot Retrieval through Query Generationcited by 24
  17. 2024Enhancing Retrieval and Managing Retrieval: A Four-Module Synergy for Improved Quality and Efficiency in RAG Systemscited by 15
  18. 2024A Surprisingly Simple yet Effective Multi-Query Rewriting Method for Conversational Passage Retrievalcited by 14
  19. 2020Deep Reinforced Query Reformulation for Information Retrievalcited by 10
  20. 2023It's All Relative! -- A Synthetic Query Generation Approach for Improving Zero-Shot Relevance Predictioncited by 10
  21. 2023On the Robustness of Generative Retrieval Models: An Out-of-Distribution Perspectivecited by 8
  22. 2023QUADRo: Dataset and Models for QUestion-Answer Database Retrievalcited by 5
  23. 2023Noise-Robust Dense Retrieval via Contrastive Alignment Post Trainingcited by 5
  24. 2021Automated Query Reformulation for Efficient Search based on Query Logs From Stack Overflowcited by 4
  25. 2024Crafting the Path: Robust Query Rewriting for Information Retrievalcited by 4
  26. 2024Unsupervised dense retrieval with conterfactual contrastive learningcited by 2

Built on by

Not cited yet.