# Towards Consistency Filtering-Free Unsupervised Learning for Dense Retrieval

arXiv: https://arxiv.org/abs/2308.02926 · HTML: https://mlsanity.com/paper/2308.02926/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 38 references that are in the map.
- First posted on arXiv 5 Aug 2023.

## Builds on (most cited first, 19 of 19)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [Is ChatGPT a Good NLG Evaluator? A Preliminary Study](https://mlsanity.com/paper/2303.04048/) (2023)
- [Pretrained Transformers for Text Ranking: BERT and Beyond](https://mlsanity.com/paper/2010.06467/) (2020)
- [Promptagator: Few-shot Dense Retrieval From 8 Examples](https://mlsanity.com/paper/2209.11755/) (2022)
- [Document Expansion by Query Prediction](https://mlsanity.com/paper/1904.08375/) (2019)
- [PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them](https://mlsanity.com/paper/2102.07033/) (2021)
- [Synthetic QA Corpora Generation with Roundtrip Consistency](https://mlsanity.com/paper/1906.05416/) (2019)
- [COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List](https://mlsanity.com/paper/2104.07186/) (2021)
- [A Survey on Cross-Lingual Summarization](https://mlsanity.com/paper/2203.12515/) (2022)
- [MS MARCO: Benchmarking Ranking Models in the Large-Data Regime](https://mlsanity.com/paper/2105.04021/) (2021)
- [ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarization](https://mlsanity.com/paper/2202.05599/) (2022)
- [MultiReQA: A Cross-Domain Evaluation for Retrieval Question Answering Models](https://mlsanity.com/paper/2005.02507/) (2020)
- [Towards Unifying Multi-Lingual and Cross-Lingual Summarization](https://mlsanity.com/paper/2305.09220/) (2023)
- [Summary-Oriented Vision Modeling for Multimodal Abstractive Summarization](https://mlsanity.com/paper/2212.07672/) (2022)
- [To Interpolate or not to Interpolate: PRF, Dense and Sparse Retrievers](https://mlsanity.com/paper/2205.00235/) (2022)
- [Knowledge Enhanced Sports Game Summarization](https://mlsanity.com/paper/2111.12535/) (2021)
- [Self-supervised Document Clustering Based on BERT with Data Augment](https://mlsanity.com/paper/2011.08523/) (2020)

## Abstract (arXiv)

Domain transfer is a prevalent challenge in modern neural Information Retrieval (IR). To overcome this problem, previous research has utilized domain-specific manual annotations and synthetic data produced by consistency filtering to finetune a general ranker and produce a domain-specific ranker. However, training such consistency filters are computationally expensive, which significantly reduces the model efficiency. In addition, consistency filtering often struggles to identify retrieval intentions and recognize query and corpus distributions in a target domain. In this study, we evaluate a more efficient solution: replacing the consistency filter with either direct pseudo-labeling, pseudo-relevance feedback, or unsupervised keyword generation methods for achieving consistent filtering-free unsupervised dense retrieval. Our extensive experimental evaluations demonstrate that, on average, TextRank-based pseudo relevance feedback outperforms other methods. Furthermore, we analyzed the training and inference efficiency of the proposed paradigm. The results indicate that filtering-free unsupervised learning can continuously improve training and inference efficiency while maintaining retrieval performance. In some cases, it can even improve performance based on particular datasets.