# Improving Document Retrieval Coherence for Semantically Equivalent Queries

arXiv: https://arxiv.org/abs/2508.07975 · HTML: https://mlsanity.com/paper/2508.07975/

## 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 (most cited first, 30 of 38)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [KILT: a Benchmark for Knowledge Intensive Language Tasks](https://mlsanity.com/paper/2009.02252/) (2020)
- [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://mlsanity.com/paper/2412.13663/) (2024)
- [State of What Art? A Call for Multi-Prompt LLM Evaluation](https://mlsanity.com/paper/2401.00595/) (2023)
- [Efficient Natural Language Response Suggestion for Smart Reply](https://mlsanity.com/paper/1705.00652/) (2017)
- [WikiHow: A Large Scale Text Summarization Dataset](https://mlsanity.com/paper/1810.09305/) (2018)
- [PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them](https://mlsanity.com/paper/2102.07033/) (2021)
- [Ask Me Anything: A simple strategy for prompting language models](https://mlsanity.com/paper/2210.02441/) (2022)
- [Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment](https://mlsanity.com/paper/2402.14016/) (2024)
- [GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval](https://mlsanity.com/paper/2112.07577/) (2021)
- [How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval](https://mlsanity.com/paper/2302.07452/) (2023)
- [Few-Shot Generative Conversational Query Rewriting](https://mlsanity.com/paper/2006.05009/) (2020)
- [Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvements](https://mlsanity.com/paper/2401.06766/) (2024)
- [SPLADE-v3: New baselines for SPLADE](https://mlsanity.com/paper/2403.06789/) (2024)
- [Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewriting](https://mlsanity.com/paper/2310.09716/) (2023)
- [POSIX: A Prompt Sensitivity Index For Large Language Models](https://mlsanity.com/paper/2410.02185/) (2024)
- [AmazonQA: A Review-Based Question Answering Task](https://mlsanity.com/paper/1908.04364/) (2019)
- [How are Prompts Different in Terms of Sensitivity?](https://mlsanity.com/paper/2311.07230/) (2023)
- [Black-box Adversarial Attacks against Dense Retrieval Models: A Multi-view Contrastive Learning Method](https://mlsanity.com/paper/2308.09861/) (2023)
- [Predicting Question-Answering Performance of Large Language Models through Semantic Consistency](https://mlsanity.com/paper/2311.01152/) (2023)
- [Conversational Question Answering on Heterogeneous Sources](https://mlsanity.com/paper/2204.11677/) (2022)
- [Embedding-based Zero-shot Retrieval through Query Generation](https://mlsanity.com/paper/2009.10270/) (2020)
- [Enhancing Retrieval and Managing Retrieval: A Four-Module Synergy for Improved Quality and Efficiency in RAG Systems](https://mlsanity.com/paper/2407.10670/) (2024)
- [A Surprisingly Simple yet Effective Multi-Query Rewriting Method for Conversational Passage Retrieval](https://mlsanity.com/paper/2406.18960/) (2024)

## 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.