# It's All Relative! -- A Synthetic Query Generation Approach for Improving Zero-Shot Relevance Prediction

arXiv: https://arxiv.org/abs/2311.07930 · HTML: https://mlsanity.com/paper/2311.07930/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 42 references that are in the map.
- First posted on arXiv 14 Nov 2023.

## Builds on (most cited first, 29 of 29)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models](https://mlsanity.com/paper/2108.08877/) (2021)
- [Large Dual Encoders Are Generalizable Retrievers](https://mlsanity.com/paper/2112.07899/) (2021)
- [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://mlsanity.com/paper/2004.07180/) (2020)
- [Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting](https://mlsanity.com/paper/2306.17563/) (2023)
- [Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias](https://mlsanity.com/paper/2306.15895/) (2023)
- [Generating Training Data with Language Models: Towards Zero-Shot Language Understanding](https://mlsanity.com/paper/2202.04538/) (2022)
- [CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims](https://mlsanity.com/paper/2012.00614/) (2020)
- [CORD-19: The COVID-19 Open Research Dataset](https://mlsanity.com/paper/2004.10706/) (2020)
- [Synthetic QA Corpora Generation with Roundtrip Consistency](https://mlsanity.com/paper/1906.05416/) (2019)
- [Large language models can accurately predict searcher preferences](https://mlsanity.com/paper/2309.10621/) (2023)
- [RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses](https://mlsanity.com/paper/2210.10634/) (2022)
- [Beyond Yes and No: Improving Zero-Shot LLM Rankers via Scoring Fine-Grained Relevance Labels](https://mlsanity.com/paper/2310.14122/) (2023)
- [Perspectives on Large Language Models for Relevance Judgment](https://mlsanity.com/paper/2304.09161/) (2023)
- [Shopping Queries Dataset: A Large-Scale ESCI Benchmark for Improving Product Search](https://mlsanity.com/paper/2206.06588/) (2022)
- [ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval](https://mlsanity.com/paper/2305.10703/) (2023)
- [Mixture of Soft Prompts for Controllable Data Generation](https://mlsanity.com/paper/2303.01580/) (2023)
- [Exploring the Viability of Synthetic Query Generation for Relevance Prediction](https://mlsanity.com/paper/2305.11944/) (2023)

## Built on by (most cited first, 10 of 10)

- [ReasonIR: Training Retrievers for Reasoning Tasks](https://mlsanity.com/paper/2504.20595/) (2025)
- [Understanding Synthetic Context Extension via Retrieval Heads](https://mlsanity.com/paper/2410.22316/) (2024)
- [Improving Scientific Document Retrieval with Concept Coverage-based Query Set Generation](https://mlsanity.com/paper/2502.11181/) (2025)
- [GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time](https://mlsanity.com/paper/2510.03777/) (2025)
- [Empowering Meta-Analysis: Leveraging Large Language Models for Scientific Synthesis](https://mlsanity.com/paper/2411.10878/) (2024)
- [HotelMatch-LLM: Joint Multi-Task Training of Small and Large Language Models for Efficient Multimodal Hotel Retrieval](https://mlsanity.com/paper/2506.07296/) (2025)
- [Improving Document Retrieval Coherence for Semantically Equivalent Queries](https://mlsanity.com/paper/2508.07975/) (2025)
- [Improving Scientific Document Retrieval with Academic Concept Index](https://mlsanity.com/paper/2601.00567/) (2026)
- [STELLA: Self-Reflective Terminology-Aware Framework for Building an Aerospace Information Retrieval Benchmark](https://mlsanity.com/paper/2601.03496/) (2026)
- [CoverSynth: Coverage-Guided Generation of Retrieval Evaluation Sets](https://mlsanity.com/paper/2610.15409/) (2026)

## Abstract (arXiv)

Recent developments in large language models (LLMs) have shown promise in their ability to generate synthetic query-document pairs by prompting with as few as 8 demonstrations. This has enabled building better IR models, especially for tasks with no training data readily available. Typically, such synthetic query generation (QGen) approaches condition on an input context (e.g. a text document) and generate a query relevant to that context, or condition the QGen model additionally on the relevance label (e.g. relevant vs irrelevant) to generate queries across relevance buckets. However, we find that such QGen approaches are sub-optimal as they require the model to reason about the desired label and the input from a handful of examples. In this work, we propose to reduce this burden of LLMs by generating queries simultaneously for different labels. We hypothesize that instead of asking the model to generate, say, an irrelevant query given an input context, asking the model to generate an irrelevant query relative to a relevant query is a much simpler task setup for the model to reason about. Extensive experimentation across seven IR datasets shows that synthetic queries generated in such a fashion translates to a better downstream performance, suggesting that the generated queries are indeed of higher quality.