# What Knowledge Is Needed? Towards Explainable Memory for kNN-MT Domain Adaptation

arXiv: https://arxiv.org/abs/2211.04052 · HTML: https://mlsanity.com/paper/2211.04052/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 25 references that are in the map.
- First posted on arXiv 8 Nov 2022.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Nearest Neighbor Machine Translation](https://mlsanity.com/paper/2010.00710/) (2020)
- [Facebook FAIR's WMT19 News Translation Task Submission](https://mlsanity.com/paper/1907.06616/) (2019)
- [Unsupervised Domain Clusters in Pretrained Language Models](https://mlsanity.com/paper/2004.02105/) (2020)
- [Adaptive Nearest Neighbor Machine Translation](https://mlsanity.com/paper/2105.13022/) (2021)
- [Domain Adaptation of Neural Machine Translation by Lexicon Induction](https://mlsanity.com/paper/1906.00376/) (2019)
- [Learning Kernel-Smoothed Machine Translation with Retrieved Examples](https://mlsanity.com/paper/2109.09991/) (2021)
- [Efficient Cluster-Based k-Nearest-Neighbor Machine Translation](https://mlsanity.com/paper/2204.06175/) (2022)
- [Efficient Machine Translation Domain Adaptation](https://mlsanity.com/paper/2204.12608/) (2022)

## Built on by (most cited first, 7 of 7)

- [A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning](https://mlsanity.com/paper/2501.02497/) (2025)
- [NNOSE: Nearest Neighbor Occupational Skill Extraction](https://mlsanity.com/paper/2401.17092/) (2024)
- [kNN-BOX: A Unified Framework for Nearest Neighbor Generation](https://mlsanity.com/paper/2302.13574/) (2023)
- [Efficient k-Nearest-Neighbor Machine Translation with Dynamic Retrieval](https://mlsanity.com/paper/2406.06073/) (2024)
- [Nearest Neighbor Machine Translation is Meta-Optimizer on Output Projection Layer](https://mlsanity.com/paper/2305.13034/) (2023)
- [Rethinking Translation Memory Augmented Neural Machine Translation](https://mlsanity.com/paper/2306.06948/) (2023)
- [Angular Dispersion Accelerates k-Nearest Neighbors Machine Translation](https://mlsanity.com/paper/2509.16729/) (2025)

## Abstract (arXiv)

kNN-MT presents a new paradigm for domain adaptation by building an external datastore, which usually saves all target language token occurrences in the parallel corpus. As a result, the constructed datastore is usually large and possibly redundant. In this paper, we investigate the interpretability issue of this approach: what knowledge does the NMT model need? We propose the notion of local correctness (LAC) as a new angle, which describes the potential translation correctness for a single entry and for a given neighborhood. Empirical study shows that our investigation successfully finds the conditions where the NMT model could easily fail and need related knowledge. Experiments on six diverse target domains and two language-pairs show that pruning according to local correctness brings a light and more explainable memory for kNN-MT domain adaptation.