{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/memorization/papers/9","list_of":"/task/memorization","task":"Memorization","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":9,"pages_in_order":11,"rows_per_page":100,"rows":[801,900],"of":1088,"counts":{"archive_papers_tagged":1088,"with_a_code_link":438,"where_syntology_ran_a_sample":177,"not_listed_spam_title":0,"listed":1088,"listed_where_code_ran":177,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":148,"every_run_a_failure_of_syntologys_instrument":29,"listed_with_a_run_with_no_instrument_failure":148,"listed_every_run_a_failure_of_syntologys_instrument":29,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/memorization","prev":"/task/memorization/papers/8","next":"/task/memorization/papers/10","papers":[{"url":null,"slug":"investigating-data-memorization-in-3d-latent","title":"Investigating Data Memorization in 3D Latent Diffusion Models for Medical Image Synthesis","date":"2023-07-03","arxiv_id":"2307.01148","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-neural-networks-provably-benefit-from","title":"Graph Neural Networks Provably Benefit from Structural Information: A Feature Learning Perspective","date":"2023-06-24","arxiv_id":"2306.13926","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-grokking-long-before-it-happens-a","title":"Predicting Grokking Long Before it Happens: A look into the loss landscape of models which grok","date":"2023-06-23","arxiv_id":"2306.13253","repositories_listed":0,"syntology":null},{"url":null,"slug":"why-are-state-space-models-more-expressive","title":"Why are state-space models more expressive than $n$-gram models?","date":"2023-06-20","arxiv_id":"2306.17184","repositories_listed":0,"syntology":null},{"url":null,"slug":"better-generalization-with-semantic-ids-a","title":"Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendations","date":"2023-06-13","arxiv_id":"2306.08121","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-the-effect-of-the-long-tail-on","title":"Understanding the Effect of the Long Tail on Neural Network Compression","date":"2023-06-09","arxiv_id":"2306.06238","repositories_listed":0,"syntology":null},{"url":null,"slug":"computation-with-sequences-in-the-brain","title":"Computation with Sequences in a Model of the Brain","date":"2023-06-06","arxiv_id":"2306.03812","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-creative-frontier-of-generative-ai","title":"The Creative Frontier of Generative AI: Managing the Novelty-Usefulness Tradeoff","date":"2023-06-06","arxiv_id":"2306.03601","repositories_listed":0,"syntology":null},{"url":null,"slug":"why-clean-generalization-and-robust","title":"Towards Understanding Clean Generalization and Robust Overfitting in Adversarial Training","date":"2023-06-02","arxiv_id":"2306.01271","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-influence-functions-classification","title":"On Influence Functions, Classification Influence, Relative Influence, Memorization and Generalization","date":"2023-05-25","arxiv_id":"2305.16094","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-data-extraction-from-pre-trained","title":"Training Data Extraction From Pre-trained Language Models: A Survey","date":"2023-05-25","arxiv_id":"2305.16157","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-enhanced-differentiable-search-index","title":"Semantic-Enhanced Differentiable Search Index Inspired by Learning Strategies","date":"2023-05-24","arxiv_id":"2305.15115","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-chatgpt-defend-the-truth-automatic","title":"Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debate","date":"2023-05-22","arxiv_id":"2305.13160","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-memory-model-for-question-answering-from","title":"A Memory Model for Question Answering from Streaming Data Supported by Rehearsal and Anticipation of Coreference Information","date":"2023-05-12","arxiv_id":"2305.07565","repositories_listed":0,"syntology":null},{"url":null,"slug":"precog-exploring-the-relation-between","title":"PreCog: Exploring the Relation between Memorization and Performance in Pre-trained Language Models","date":"2023-05-08","arxiv_id":"2305.04673","repositories_listed":0,"syntology":null},{"url":null,"slug":"surveying-generative-ai-s-economic","title":"Surveying Generative AI's Economic Expectations","date":"2023-05-04","arxiv_id":"2305.02823","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-approximate-memorization-in","title":"Mitigating Approximate Memorization in Language Models via Dissimilarity Learned Policy","date":"2023-05-02","arxiv_id":"2305.01550","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-newer-is-not-better-does-deep-learning","title":"When Newer is Not Better: Does Deep Learning Really Benefit Recommendation From Implicit Feedback?","date":"2023-05-02","arxiv_id":"2305.01801","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpreting-pretrained-source-code-models","title":"Redundancy and Concept Analysis for Code-trained Language Models","date":"2023-05-01","arxiv_id":"2305.00875","repositories_listed":0,"syntology":null},{"url":null,"slug":"hopfield-model-with-planted-patterns-a","title":"Hopfield model with planted patterns: a teacher-student self-supervised learning model","date":"2023-04-26","arxiv_id":"2304.13710","repositories_listed":0,"syntology":null},{"url":null,"slug":"why-does-chatgpt-fall-short-in-answering","title":"Why Does ChatGPT Fall Short in Providing Truthful Answers?","date":"2023-04-20","arxiv_id":"2304.10513","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-evaluation-on-large-language-model-outputs","title":"An Evaluation on Large Language Model Outputs: Discourse and Memorization","date":"2023-04-17","arxiv_id":"2304.08637","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-do-you-need-chain-of-thought-prompting","title":"When do you need Chain-of-Thought Prompting for ChatGPT?","date":"2023-04-06","arxiv_id":"2304.03262","repositories_listed":0,"syntology":null},{"url":null,"slug":"per-example-gradient-regularization-improves","title":"Per-Example Gradient Regularization Improves Learning Signals from Noisy Data","date":"2023-03-31","arxiv_id":"2303.17940","repositories_listed":0,"syntology":null},{"url":"/paper/koala-an-index-for-quantifying-overlaps-with","slug":"koala-an-index-for-quantifying-overlaps-with","title":"Koala: An Index for Quantifying Overlaps with Pre-training Corpora","date":"2023-03-26","arxiv_id":"2303.14770","repositories_listed":0,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/koala-an-index-for-quantifying-overlaps-with#ran","syntology_url":"https://syntology.ai/paper/2303.14770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14770"}},"official":null}},{"url":null,"slug":"memorization-capacity-of-neural-networks-with","title":"Memorization Capacity of Neural Networks with Conditional Computation","date":"2023-03-20","arxiv_id":"2303.11247","repositories_listed":0,"syntology":null},{"url":null,"slug":"query2doc-query-expansion-with-large-language","title":"Query2doc: Query Expansion with Large Language Models","date":"2023-03-14","arxiv_id":"2303.07678","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-the-finer-things-bayesian-structure","title":"Learning the Finer Things: Bayesian Structure Learning at the Instantiation Level","date":"2023-03-08","arxiv_id":"2303.04339","repositories_listed":0,"syntology":null},{"url":"/paper/where-we-are-and-what-we-re-looking-at-query","slug":"where-we-are-and-what-we-re-looking-at-query","title":"Where We Are and What We're Looking At: Query Based Worldwide Image Geo-localization Using Hierarchies and Scenes","date":"2023-03-07","arxiv_id":"2303.04249","repositories_listed":0,"syntology":{"n":23,"n_ran":17,"n_constructed":11,"n_ran_checked":15,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":23,"phrase":"17 ran (of which 11 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/where-we-are-and-what-we-re-looking-at-query#ran","syntology_url":"https://syntology.ai/paper/2303.04249","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.04249"}},"official":null}},{"url":null,"slug":"semiparametric-language-models-are-scalable","title":"Semiparametric Language Models Are Scalable Continual Learners","date":"2023-03-02","arxiv_id":"2303.01421","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-copying-in-generative-models-a-formal","title":"Data-Copying in Generative Models: A Formal Framework","date":"2023-02-25","arxiv_id":"2302.13181","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-nearest-neighbor-machine","title":"Federated Nearest Neighbor Machine Translation","date":"2023-02-23","arxiv_id":"2302.12211","repositories_listed":0,"syntology":null},{"url":null,"slug":"targeted-attack-on-gpt-neo-for-the-satml","title":"Targeted Attack on GPT-Neo for the SATML Language Model Data Extraction Challenge","date":"2023-02-13","arxiv_id":"2302.07735","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-table-to-text-generation-with-prompt","title":"Few-Shot Table-to-Text Generation with Prompt Planning and Knowledge Memorization","date":"2023-02-09","arxiv_id":"2302.04415","repositories_listed":0,"syntology":null},{"url":null,"slug":"coherence-and-diversity-through-noise-self","title":"Coherence and Diversity through Noise: Self-Supervised Paraphrase Generation via Structure-Aware Denoising","date":"2023-02-06","arxiv_id":"2302.02780","repositories_listed":0,"syntology":null},{"url":null,"slug":"resmem-learn-what-you-can-and-memorize-the","title":"ResMem: Learn what you can and memorize the rest","date":"2023-02-03","arxiv_id":"2302.01576","repositories_listed":0,"syntology":null},{"url":null,"slug":"sharp-lower-bounds-on-interpolation-by-deep","title":"Sharp Lower Bounds on Interpolation by Deep ReLU Neural Networks at Irregularly Spaced Data","date":"2023-02-02","arxiv_id":"2302.00834","repositories_listed":0,"syntology":null},{"url":null,"slug":"validation-of-machine-learning-based-scenario","title":"Validation of machine learning based scenario generators","date":"2023-01-30","arxiv_id":"2301.12719","repositories_listed":0,"syntology":null},{"url":null,"slug":"ot-filter-an-optimal-transport-filter-for","title":"OT-Filter: An Optimal Transport Filter for Learning With Noisy Labels","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-mathematical-framework-for-learning","title":"A Mathematical Framework for Learning Probability Distributions","date":"2022-12-22","arxiv_id":"2212.11481","repositories_listed":0,"syntology":null},{"url":null,"slug":"nlip-noise-robust-language-image-pre-training","title":"NLIP: Noise-robust Language-Image Pre-training","date":"2022-12-14","arxiv_id":"2212.07086","repositories_listed":0,"syntology":null},{"url":null,"slug":"state-regularized-recurrent-neural-networks-1","title":"State-Regularized Recurrent Neural Networks to Extract Automata and Explain Predictions","date":"2022-12-10","arxiv_id":"2212.05178","repositories_listed":0,"syntology":null},{"url":null,"slug":"logit-clipping-for-robust-learning-against","title":"Mitigating Memorization of Noisy Labels by Clipping the Model Prediction","date":"2022-12-08","arxiv_id":"2212.04055","repositories_listed":0,"syntology":null},{"url":null,"slug":"codex-hacks-hackerrank-memorization-issues","title":"Codex Hacks HackerRank: Memorization Issues and a Framework for Code Synthesis Evaluation","date":"2022-12-06","arxiv_id":"2212.02684","repositories_listed":0,"syntology":null},{"url":null,"slug":"crosssplit-mitigating-label-noise","title":"CrossSplit: Mitigating Label Noise Memorization through Data Splitting","date":"2022-12-03","arxiv_id":"2212.01674","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-myth-of-culturally-agnostic-ai-models","title":"The Myth of Culturally Agnostic AI Models","date":"2022-11-28","arxiv_id":"2211.15271","repositories_listed":0,"syntology":null},{"url":null,"slug":"boundary-adversarial-examples-against","title":"Boundary Adversarial Examples Against Adversarial Overfitting","date":"2022-11-25","arxiv_id":"2211.14088","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompting-language-models-for-linguistic","title":"Prompting Language Models for Linguistic Structure","date":"2022-11-15","arxiv_id":"2211.07830","repositories_listed":0,"syntology":null},{"url":null,"slug":"selective-memory-recursive-least-squares","title":"Selective Memory Recursive Least Squares: Recast Forgetting into Memory in RBF Neural Network Based Real-Time Learning","date":"2022-11-15","arxiv_id":"2211.07909","repositories_listed":0,"syntology":null},{"url":null,"slug":"unintended-memorization-and-timing-attacks-in","title":"Unintended Memorization and Timing Attacks in Named Entity Recognition Models","date":"2022-11-04","arxiv_id":"2211.02245","repositories_listed":0,"syntology":null},{"url":null,"slug":"plato-k-internal-and-external-knowledge","title":"PLATO-K: Internal and External Knowledge Enhanced Dialogue Generation","date":"2022-11-02","arxiv_id":"2211.00910","repositories_listed":0,"syntology":null},{"url":null,"slug":"preventing-verbatim-memorization-in-language","title":"Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy","date":"2022-10-31","arxiv_id":"2210.17546","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-is-provably-robust-to-symmetric","title":"Deep Learning is Provably Robust to Symmetric Label Noise","date":"2022-10-26","arxiv_id":"2210.15083","repositories_listed":0,"syntology":null},{"url":null,"slug":"empowering-long-tail-item-recommendation","title":"Empowering Long-tail Item Recommendation through Cross Decoupling Network (CDN)","date":"2022-10-25","arxiv_id":"2210.14309","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-curious-case-of-benign-memorization","title":"The Curious Case of Benign Memorization","date":"2022-10-25","arxiv_id":"2210.14019","repositories_listed":0,"syntology":null},{"url":null,"slug":"measures-of-information-reflect-memorization","title":"Measures of Information Reflect Memorization Patterns","date":"2022-10-17","arxiv_id":"2210.09404","repositories_listed":0,"syntology":null},{"url":null,"slug":"cntn-cyclic-noise-tolerant-network-for-gait","title":"CNTN: Cyclic Noise-tolerant Network for Gait Recognition","date":"2022-10-13","arxiv_id":"2210.06910","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-unintended-memorization-in","title":"Mitigating Unintended Memorization in Language Models via Alternating Teaching","date":"2022-10-13","arxiv_id":"2210.06772","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-associative-memory-model-with-very-high","title":"An associative memory model with very high memory rate: Image storage by sequential addition learning","date":"2022-10-08","arxiv_id":"2210.03893","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-dataset-generation-for-privacy","title":"Synthetic Dataset Generation for Privacy-Preserving Machine Learning","date":"2022-10-06","arxiv_id":"2210.03205","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-beats-concatenation-for","title":"Attention Beats Concatenation for Conditioning Neural Fields","date":"2022-09-21","arxiv_id":"2209.10684","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-isotopes-for-data-provenance-in-dnns","title":"Data Isotopes for Data Provenance in DNNs","date":"2022-08-29","arxiv_id":"2208.13893","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-the-number-of-tasks-in-continual","title":"Challenging Common Assumptions about Catastrophic Forgetting","date":"2022-07-10","arxiv_id":"2207.04543","repositories_listed":0,"syntology":null},{"url":null,"slug":"does-it-really-generalize-well-on-unseen-data","title":"Does it Really Generalize Well on Unseen Data? Systematic Evaluation of Relational Triple Extraction Methods","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-leakage-in-text-classification-a-data-1","title":"Privacy Leakage in Text Classification A Data Extraction Approach","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"training-text-to-text-transformers-with","title":"Training Text-to-Text Transformers with Privacy Guarantees","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-forgetting-of-memorized-training","title":"Measuring Forgetting of Memorized Training Examples","date":"2022-06-30","arxiv_id":"2207.00099","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-harnessing-feature-embedding-for","title":"Towards Harnessing Feature Embedding for Robust Learning with Noisy Labels","date":"2022-06-27","arxiv_id":"2206.13025","repositories_listed":0,"syntology":null},{"url":null,"slug":"max-margin-works-while-large-margin-fails","title":"Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence","date":"2022-06-16","arxiv_id":"2206.07892","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-generate-imaginary-tasks-for","title":"Learning to generate imaginary tasks for improving generalization in meta-learning","date":"2022-06-09","arxiv_id":"2206.04335","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-leakage-in-text-classification-a-data","title":"Privacy Leakage in Text Classification: A Data Extraction Approach","date":"2022-06-09","arxiv_id":"2206.04591","repositories_listed":0,"syntology":null},{"url":null,"slug":"msr-making-self-supervised-learning-robust-to","title":"MSR: Making Self-supervised learning Robust to Aggressive Augmentations","date":"2022-06-04","arxiv_id":"2206.01999","repositories_listed":0,"syntology":null},{"url":null,"slug":"white-box-membership-attack-against-machine","title":"White-box Membership Attack Against Machine Learning Based Retinopathy Classification","date":"2022-05-30","arxiv_id":"2206.03584","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-based-virtual-adversarial-training","title":"Context-based Virtual Adversarial Training for Text Classification with Noisy Labels","date":"2022-05-29","arxiv_id":"2206.11851","repositories_listed":0,"syntology":null},{"url":null,"slug":"memorization-without-overfitting-analyzing","title":"Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models","date":"2022-05-22","arxiv_id":"2205.10770","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-laws-and-interpretability-of-learning","title":"Scaling Laws and Interpretability of Learning from Repeated Data","date":"2022-05-21","arxiv_id":"2205.10487","repositories_listed":0,"syntology":null},{"url":null,"slug":"memorization-and-optimization-in-deep-neural","title":"Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization","date":"2022-05-20","arxiv_id":"2205.10217","repositories_listed":0,"syntology":null},{"url":null,"slug":"adacap-adaptive-capacity-control-for-feed","title":"AdaCap: Adaptive Capacity control for Feed-Forward Neural Networks","date":"2022-05-09","arxiv_id":"2205.07860","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixup-based-deep-metric-learning-approaches","title":"Mixup-based Deep Metric Learning Approaches for Incomplete Supervision","date":"2022-04-28","arxiv_id":"2204.13572","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-unintended-memorization-in-language","title":"Detecting Unintended Memorization in Language-Model-Fused ASR","date":"2022-04-20","arxiv_id":"2204.09606","repositories_listed":0,"syntology":null},{"url":null,"slug":"local-feature-swapping-for-generalization-in-1","title":"Local Feature Swapping for Generalization in Reinforcement Learning","date":"2022-04-13","arxiv_id":"2204.06355","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-differential-relational-privacy-and","title":"Towards Differential Relational Privacy and its use in Question Answering","date":"2022-03-30","arxiv_id":"2203.16701","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-meta-learning-for-low-resource-text","title":"Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation","date":"2022-03-22","arxiv_id":"2203.11670","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-generalization-mystery-in-deep","title":"On the Generalization Mystery in Deep Learning","date":"2022-03-18","arxiv_id":"2203.10036","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantifying-privacy-risks-of-masked-language","title":"Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks","date":"2022-03-08","arxiv_id":"2203.03929","repositories_listed":0,"syntology":null},{"url":"/paper/kmir-a-benchmark-for-evaluating-knowledge","slug":"kmir-a-benchmark-for-evaluating-knowledge","title":"KMIR: A Benchmark for Evaluating Knowledge Memorization, Identification and Reasoning Abilities of Language Models","date":"2022-02-28","arxiv_id":"2202.13529","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-planning-for-deep-neural-networks","title":"Memory Planning for Deep Neural Networks","date":"2022-02-23","arxiv_id":"2203.00448","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-we-need-to-penalize-variance-of-losses-for","title":"Do We Need to Penalize Variance of Losses for Learning with Label Noise?","date":"2022-01-30","arxiv_id":"2201.12739","repositories_listed":0,"syntology":null},{"url":null,"slug":"collaborative-learning-in-general-graphs-with","title":"Collaborative Learning in General Graphs with Limited Memorization: Complexity, Learnability, and Reliability","date":"2022-01-29","arxiv_id":"2201.12482","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-online-learning-with-unbounded","title":"Universal Online Learning with Unbounded Losses: Memory Is All You Need","date":"2022-01-21","arxiv_id":"2201.08903","repositories_listed":0,"syntology":null},{"url":null,"slug":"evidentiality-guided-generation-for-knowledge-1","title":"Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"polling-latent-opinions-a-method-for","title":"Polling Latent Opinions: A Method for Computational Sociolinguistics Using Transformer Language Models","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-confidential-language-modelling","title":"Provably Confidential Language Modelling","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"quantifying-adaptability-in-pre-trained-1","title":"Quantifying Adaptability in Pre-trained Language Models with 500 Tasks","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-online-learning-an-optimistically","title":"Universal Online Learning: an Optimistically Universal Learning Rule","date":"2022-01-16","arxiv_id":"2201.05947","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantics-preserved-distortion-for-personal","title":"Semantics-Preserved Distortion for Personal Privacy Protection in Information Management","date":"2022-01-04","arxiv_id":"2201.00965","repositories_listed":0,"syntology":null},{"url":null,"slug":"counterfactual-memorization-in-neural","title":"Counterfactual Memorization in Neural Language Models","date":"2021-12-24","arxiv_id":"2112.12938","repositories_listed":0,"syntology":null},{"url":null,"slug":"economics-of-innovation-and-perceptions-of","title":"Economics of Innovation and Perceptions of Renewed Education and Curriculum Design in Bangladesh","date":"2021-12-23","arxiv_id":"2112.13842","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-positional-embeddings-for-coordinate","title":"Learning Positional Embeddings for Coordinate-MLPs","date":"2021-12-21","arxiv_id":"2112.11577","repositories_listed":0,"syntology":null},{"url":null,"slug":"lifelong-unsupervised-domain-adaptive-person","title":"Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptation","date":"2021-12-13","arxiv_id":"2112.06632","repositories_listed":0,"syntology":null}],"record_sha256":"be0468ffc6195589dfbe3062cd328655952c024f9c4ae7b34ccc556800dd84d5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}