# Finding Memo: Extractive Memorization in Constrained Sequence Generation Tasks arXiv: https://arxiv.org/abs/2210.12929 ยท HTML: https://mlsanity.com/paper/2210.12929/ ## Key facts - Cited by 12 papers in the map (data through 14 Oct 2026). - Builds on 27 of its 43 references that are in the map. - First posted on arXiv 24 Oct 2022. ## Builds on (most cited first, 27 of 27) - [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017) - [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018) - [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022) - [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020) - [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018) - [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018) - [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020) - [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017) - [Quantifying Memorization Across Neural Language Models](https://mlsanity.com/paper/2202.07646/) (2022) - [What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation](https://mlsanity.com/paper/2008.03703/) (2020) - [Does Learning Require Memorization? A Short Tale about a Long Tail](https://mlsanity.com/paper/1906.05271/) (2019) - [Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models](https://mlsanity.com/paper/2205.10770/) (2022) - [Marian: Fast Neural Machine Translation in C++](https://mlsanity.com/paper/1804.00344/) (2018) - [The Curious Case of Hallucinations in Neural Machine Translation](https://mlsanity.com/paper/2104.06683/) (2021) - [Counterfactual Memorization in Neural Language Models](https://mlsanity.com/paper/2112.12938/) (2021) - [When and Why are Pre-trained Word Embeddings Useful for Neural Machine Translation?](https://mlsanity.com/paper/1804.06323/) (2018) - [Machine Translationese: Effects of Algorithmic Bias on Linguistic Complexity in Machine Translation](https://mlsanity.com/paper/2102.00287/) (2021) - [Understanding Transformer Memorization Recall Through Idioms](https://mlsanity.com/paper/2210.03588/) (2022) - [Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations](https://mlsanity.com/paper/1906.01181/) (2019) - [The paradox of the compositionality of natural language: a neural machine translation case study](https://mlsanity.com/paper/2108.05885/) (2021) - [GEMv2: Multilingual NLG Benchmarking in a Single Line of Code](https://mlsanity.com/paper/2206.11249/) (2022) - [Memorisation versus Generalisation in Pre-trained Language Models](https://mlsanity.com/paper/2105.00828/) (2021) - [How BPE Affects Memorization in Transformers](https://mlsanity.com/paper/2110.02782/) (2021) - [Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine Translation](https://mlsanity.com/paper/2205.15301/) (2022) - [SALTED: A Framework for SAlient Long-Tail Translation Error Detection](https://mlsanity.com/paper/2205.09988/) (2022) - [An Empirical Study of Memorization in NLP](https://mlsanity.com/paper/2203.12171/) (2022) - [On Compositionality in Neural Machine Translation](https://mlsanity.com/paper/1911.01497/) (2019) ## Built on by (most cited first, 12 of 12) - [How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation](https://mlsanity.com/paper/2302.09210/) (2023) - [The unreasonable effectiveness of few-shot learning for machine translation](https://mlsanity.com/paper/2302.01398/) (2023) - [AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ](https://mlsanity.com/paper/2310.00367/) (2023) - [Leveraging GPT-4 for Automatic Translation Post-Editing](https://mlsanity.com/paper/2305.14878/) (2023) - [ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language Models](https://mlsanity.com/paper/2212.10474/) (2022) - [An Evaluation on Large Language Model Outputs: Discourse and Memorization](https://mlsanity.com/paper/2304.08637/) (2023) - [Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Ability](https://mlsanity.com/paper/2506.15629/) (2025) - [Rank-One Editing of Encoder-Decoder Models](https://mlsanity.com/paper/2211.13317/) (2022) - [Memorisation Cartography: Mapping out the Memorisation-Generalisation Continuum in Neural Machine Translation](https://mlsanity.com/paper/2311.05379/) (2023) - [When Flores Bloomz Wrong: Cross-Direction Contamination in Machine Translation Evaluation](https://mlsanity.com/paper/2601.20858/) (2026) - [Memorization Inheritance in Sequence-Level Knowledge Distillation for Neural Machine Translation](https://mlsanity.com/paper/2502.01491/) (2025) - [Operationalizing Specifications, In Addition to Test Sets for Evaluating Constrained Generative Models](https://mlsanity.com/paper/2212.00006/) (2022) ## Abstract (arXiv) Memorization presents a challenge for several constrained Natural Language Generation (NLG) tasks such as Neural Machine Translation (NMT), wherein the proclivity of neural models to memorize noisy and atypical samples reacts adversely with the noisy (web crawled) datasets. However, previous studies of memorization in constrained NLG tasks have only focused on counterfactual memorization, linking it to the problem of hallucinations. In this work, we propose a new, inexpensive algorithm for extractive memorization (exact training data generation under insufficient context) in constrained sequence generation tasks and use it to study extractive memorization and its effects in NMT. We demonstrate that extractive memorization poses a serious threat to NMT reliability by qualitatively and quantitatively characterizing the memorized samples as well as the model behavior in their vicinity. Based on empirical observations, we develop a simple algorithm which elicits non-memorized translations of memorized samples from the same model, for a large fraction of such samples. Finally, we show that the proposed algorithm could also be leveraged to mitigate memorization in the model through finetuning. We have released the code to reproduce our results at https://github.com/vyraun/Finding-Memo.