{"total":146,"rows":[{"id":"2301.07069","title":"Prompting Large Language Model for Machine Translation: A Case Study","created":"2023-01-17","cited_by_count":250,"area":null},{"id":"2312.12148","title":"Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","created":"2023-12-19","cited_by_count":230,"area":null},{"id":"2208.03306","title":"Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models","created":"2022-08-05","cited_by_count":191,"area":null},{"id":"2212.02437","title":"In-context Examples Selection for Machine Translation","created":"2022-12-05","cited_by_count":172,"area":null},{"id":"2108.05036","title":"DEMix Layers: Disentangling Domains for Modular Language Modeling","created":"2021-08-11","cited_by_count":132,"area":null},{"id":"2104.07143","title":"An Interpretability Illusion for BERT","created":"2021-04-14","cited_by_count":97,"area":null},{"id":"2109.04212","title":"Efficient Nearest Neighbor Language Models","created":"2021-09-09","cited_by_count":93,"area":null},{"id":"2302.07027","title":"AdapterSoup: Weight Averaging to Improve Generalization of Pretrained Language Models","created":"2023-02-14","cited_by_count":84,"area":null},{"id":"2302.07856","title":"Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translation","created":"2023-02-15","cited_by_count":74,"area":null},{"id":"2101.11109","title":"First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERT","created":"2021-01-26","cited_by_count":65,"area":null},{"id":"2302.14233","title":"Goal Driven Discovery of Distributional Differences via Language Descriptions","created":"2023-02-28","cited_by_count":62,"area":null},{"id":"2105.11269","title":"Neural Machine Translation with Monolingual Translation Memory","created":"2021-05-24","cited_by_count":61,"area":null},{"id":"2201.12431","title":"Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval","created":"2022-01-28","cited_by_count":60,"area":null},{"id":"2303.14177","title":"Scaling Expert Language Models with Unsupervised Domain Discovery","created":"2023-03-24","cited_by_count":60,"area":null},{"id":"2305.13749","title":"Goal-Driven Explainable Clustering via Language Descriptions","created":"2023-05-23","cited_by_count":58,"area":null},{"id":"2201.12323","title":"Describing Differences between Text Distributions with Natural Language","created":"2022-01-28","cited_by_count":54,"area":null},{"id":"2312.10523","title":"Paloma: A Benchmark for Evaluating Language Model Fit","created":"2023-12-16","cited_by_count":54,"area":null},{"id":"2310.13448","title":"Steering Large Language Models for Machine Translation with Finetuning and In-Context Learning","created":"2023-10-20","cited_by_count":49,"area":null},{"id":"2407.12994","title":"A Survey of Prompt Engineering Methods in Large Language Models for Different NLP Tasks","created":"2024-07-17","cited_by_count":47,"area":null},{"id":"2104.06951","title":"Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey","created":"2021-04-14","cited_by_count":46,"area":null},{"id":"2105.14528","title":"Fast Nearest Neighbor Machine Translation","created":"2021-05-30","cited_by_count":37,"area":null},{"id":"2209.12616","title":"T-NER: An All-Round Python Library for Transformer-based Named Entity Recognition","created":"2022-09-09","cited_by_count":37,"area":null},{"id":"2204.09874","title":"Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for Topics","created":"2022-04-21","cited_by_count":35,"area":null},{"id":"2311.08545","title":"Efficient Continual Pre-training for Building Domain Specific Large Language Models","created":"2023-11-14","cited_by_count":34,"area":null},{"id":"2112.08786","title":"Efficient Hierarchical Domain Adaptation for Pretrained Language Models","created":"2021-12-16","cited_by_count":32,"area":null},{"id":"2405.02774","title":"Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs","created":"2024-05-05","cited_by_count":32,"area":null},{"id":"2202.04824","title":"AdaPrompt: Adaptive Model Training for Prompt-based NLP","created":"2022-02-10","cited_by_count":30,"area":null},{"id":"2305.13282","title":"Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection","created":"2023-05-22","cited_by_count":29,"area":null},{"id":"2410.11303","title":"TSDS: Data Selection for Task-Specific Model Finetuning","created":"2024-10-15","cited_by_count":28,"area":null},{"id":"2106.11346","title":"GAIA: A Transfer Learning System of Object Detection that Fits Your Needs","created":"2021-06-21","cited_by_count":27,"area":null},{"id":"2305.16876","title":"CombLM: Adapting Black-Box Language Models through Small Fine-Tuned Models","created":"2023-05-23","cited_by_count":26,"area":null},{"id":"2104.05904","title":"DirectProbe: Studying Representations without Classifiers","created":"2021-04-13","cited_by_count":25,"area":null},{"id":"2109.09991","title":"Learning Kernel-Smoothed Machine Translation with Retrieved Examples","created":"2021-09-21","cited_by_count":25,"area":null},{"id":"2106.04564","title":"Are Pretrained Transformers Robust in Intent Classification? A Missing Ingredient in Evaluation of Out-of-Scope Intent Detection","created":"2021-06-08","cited_by_count":22,"area":null},{"id":"2405.20089","title":"The Fine-Tuning Paradox: Boosting Translation Quality Without Sacrificing LLM Abilities","created":"2024-05-30","cited_by_count":22,"area":null},{"id":"2110.08395","title":"DS-TOD: Efficient Domain Specialization for Task Oriented Dialog","created":"2021-10-15","cited_by_count":21,"area":null},{"id":"2110.09574","title":"Multilingual Domain Adaptation for NMT: Decoupling Language and Domain Information with Adapters","created":"2021-10-18","cited_by_count":21,"area":null},{"id":"2205.12230","title":"Chunk-based Nearest Neighbor Machine Translation","created":"2022-05-24","cited_by_count":21,"area":null},{"id":"2305.17367","title":"Augmenting Large Language Model Translators via Translation Memories","created":"2023-05-27","cited_by_count":21,"area":null},{"id":"2409.08466","title":"Explaining Datasets in Words: Statistical Models with Natural Language Parameters","created":"2024-09-13","cited_by_count":21,"area":null},{"id":"2108.05682","title":"(Un)solving Morphological Inflection: Lemma Overlap Artificially Inflates Models' Performance","created":"2021-08-12","cited_by_count":20,"area":null},{"id":"2109.06604","title":"Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translation","created":"2021-09-14","cited_by_count":20,"area":null},{"id":"2311.05350","title":"There's no Data Like Better Data: Using QE Metrics for MT Data Filtering","created":"2023-11-09","cited_by_count":19,"area":null},{"id":"2410.03735","title":"Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling","created":"2024-09-30","cited_by_count":18,"area":null},{"id":"2105.10912","title":"CiteWorth: Cite-Worthiness Detection for Improved Scientific Document Understanding","created":"2021-05-23","cited_by_count":17,"area":null},{"id":"2401.08350","title":"Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models","created":"2024-01-16","cited_by_count":17,"area":null},{"id":"2110.02600","title":"Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning","created":"2021-10-06","cited_by_count":16,"area":null},{"id":"2110.06997","title":"Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits","created":"2021-10-13","cited_by_count":16,"area":null},{"id":"2209.06995","title":"Cold-Start Data Selection for Few-shot Language Model Fine-tuning: A Prompt-Based Uncertainty Propagation Approach","created":"2022-09-15","cited_by_count":16,"area":null},{"id":"2403.05921","title":"OntoChat: a Framework for Conversational Ontology Engineering using Language Models","created":"2024-03-09","cited_by_count":15,"area":null},{"id":"2403.18365","title":"BLADE: Enhancing Black-box Large Language Models with Small Domain-Specific Models","created":"2024-03-27","cited_by_count":15,"area":null},{"id":"2109.10274","title":"The Trade-offs of Domain Adaptation for Neural Language Models","created":"2021-09-21","cited_by_count":14,"area":null},{"id":"2209.15236","title":"Language-Family Adapters for Low-Resource Multilingual Neural Machine Translation","created":"2022-09-30","cited_by_count":14,"area":null},{"id":"2212.09676","title":"Words as Gatekeepers: Measuring Discipline-specific Terms and Meanings in Scholarly Publications","created":"2022-12-19","cited_by_count":14,"area":null},{"id":"2404.08417","title":"AdapterSwap: Continuous Training of LLMs with Data Removal and Access-Control Guarantees","created":"2024-04-12","cited_by_count":14,"area":null},{"id":"2106.11375","title":"Phrase-level Active Learning for Neural Machine Translation","created":"2021-06-21","cited_by_count":13,"area":null},{"id":"2401.02709","title":"German Text Embedding Clustering Benchmark","created":"2024-01-05","cited_by_count":13,"area":null},{"id":"2210.16637","title":"Beyond Prompting: Making Pre-trained Language Models Better Zero-shot Learners by Clustering Representations","created":"2022-10-29","cited_by_count":11,"area":null},{"id":"2311.11973","title":"Adaptive Training Distributions with Scalable Online Bilevel Optimization","created":"2023-11-20","cited_by_count":11,"area":null},{"id":"2410.02631","title":"Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning","created":"2024-10-03","cited_by_count":11,"area":null},{"id":"2109.07591","title":"On the Complementarity of Data Selection and Fine Tuning for Domain Adaptation","created":"2021-09-15","cited_by_count":10,"area":null},{"id":"2210.07362","title":"Can Demographic Factors Improve Text Classification? Revisiting Demographic Adaptation in the Age of Transformers","created":"2022-10-13","cited_by_count":10,"area":null},{"id":"2408.06537","title":"Introducing the NewsPaLM MBR and QE Dataset: LLM-Generated High-Quality Parallel Data Outperforms Traditional Web-Crawled Data","created":"2024-08-13","cited_by_count":10,"area":null},{"id":"2410.02498","title":"Dynamic Gradient Alignment for Online Data Mixing","created":"2024-10-03","cited_by_count":10,"area":null},{"id":"2506.15538","title":"Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework","created":"2025-06-18","cited_by_count":10,"area":null},{"id":"2308.10263","title":"Scaling up Discovery of Latent Concepts in Deep NLP Models","created":"2023-08-20","cited_by_count":9,"area":null},{"id":"2109.04733","title":"Genre as Weak Supervision for Cross-lingual Dependency Parsing","created":"2021-09-10","cited_by_count":8,"area":null},{"id":"2112.08152","title":"Faster Nearest Neighbor Machine Translation","created":"2021-12-15","cited_by_count":8,"area":null},{"id":"2309.08590","title":"Neural Machine Translation Models Can Learn to be Few-shot Learners","created":"2023-09-15","cited_by_count":8,"area":null},{"id":"2403.09259","title":"To Label or Not to Label: Hybrid Active Learning for Neural Machine Translation","created":"2024-03-14","cited_by_count":8,"area":null},{"id":"2204.12608","title":"Efficient Machine Translation Domain Adaptation","created":"2022-04-26","cited_by_count":7,"area":null},{"id":"2206.01328","title":"Augmenting Scientific Creativity with Retrieval across Knowledge Domains","created":"2022-06-02","cited_by_count":7,"area":null},{"id":"2209.11409","title":"Zero-shot Domain Adaptation for Neural Machine Translation with Retrieved Phrase-level Prompts","created":"2022-09-23","cited_by_count":7,"area":null},{"id":"2211.04052","title":"What Knowledge Is Needed? Towards Explainable Memory for kNN-MT Domain Adaptation","created":"2022-11-08","cited_by_count":7,"area":null},{"id":"2505.16066","title":"Merge to Mix: Mixing Datasets via Model Merging","created":"2025-05-21","cited_by_count":7,"area":null},{"id":"2211.01542","title":"Continual Learning of Neural Machine Translation within Low Forgetting Risk Regions","created":"2022-11-03","cited_by_count":6,"area":null},{"id":"2305.12401","title":"WOT-Class: Weakly Supervised Open-world Text Classification","created":"2023-05-21","cited_by_count":6,"area":null},{"id":"2305.12749","title":"A Benchmark on Extremely Weakly Supervised Text Classification: Reconcile Seed Matching and Prompting Approaches","created":"2023-05-22","cited_by_count":6,"area":null},{"id":"2311.01866","title":"Towards Concept-Aware Large Language Models","created":"2023-11-03","cited_by_count":6,"area":null},{"id":"2410.04275","title":"Language Model-Driven Data Pruning Enables Efficient Active Learning","created":"2024-10-05","cited_by_count":6,"area":null},{"id":"2203.11724","title":"Explainable Misinformation Detection Across Multiple Social Media Platforms","created":"2022-03-20","cited_by_count":5,"area":null},{"id":"2205.11490","title":"Local Byte Fusion for Neural Machine Translation","created":"2022-05-23","cited_by_count":5,"area":null},{"id":"2209.06687","title":"How people talk about each other: Modeling Generalized Intergroup Bias and Emotion","created":"2022-09-14","cited_by_count":5,"area":null},{"id":"2210.04802","title":"SimSCOOD: Systematic Analysis of Out-of-Distribution Generalization in Fine-tuned Source Code Models","created":"2022-10-10","cited_by_count":5,"area":null},{"id":"2407.17624","title":"Forecasting Credit Ratings: A Case Study where Traditional Methods Outperform Generative LLMs","created":"2024-07-24","cited_by_count":5,"area":null},{"id":"2104.08673","title":"\"Average\" Approximates \"First Principal Component\"? An Empirical Analysis on Representations from Neural Language Models","created":"2021-04-18","cited_by_count":4,"area":null},{"id":"2109.07140","title":"On the Universality of Deep Contextual Language Models","created":"2021-09-15","cited_by_count":4,"area":null},{"id":"2112.04971","title":"How Universal is Genre in Universal Dependencies?","created":"2021-12-09","cited_by_count":4,"area":null},{"id":"2112.06096","title":"Selecting Parallel In-domain Sentences for Neural Machine Translation Using Monolingual Texts","created":"2021-12-11","cited_by_count":4,"area":null},{"id":"2207.04564","title":"Domain Confused Contrastive Learning for Unsupervised Domain Adaptation","created":"2022-07-10","cited_by_count":4,"area":null},{"id":"2304.01969","title":"MEGClass: Extremely Weakly Supervised Text Classification via Mutually-Enhancing Text Granularities","created":"2023-04-04","cited_by_count":4,"area":null},{"id":"2310.08908","title":"Human-in-the-loop Machine Translation with Large Language Model","created":"2023-10-13","cited_by_count":4,"area":null},{"id":"2503.05010","title":"Leveraging Domain Knowledge at Inference Time for LLM Translation: Retrieval versus Generation","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2503.18247","title":"AfroXLMR-Social: Adapting Pre-trained Language Models for African Languages Social Media Text","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2105.05498","title":"Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction","created":"2021-05-12","cited_by_count":3,"area":null},{"id":"2206.12529","title":"Probing Causes of Hallucinations in Neural Machine Translations","created":"2022-06-25","cited_by_count":3,"area":null},{"id":"2210.14431","title":"$N$-gram Is Back: Residual Learning of Neural Text Generation with $n$-gram Language Model","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2305.18503","title":"From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework","created":"2023-05-29","cited_by_count":3,"area":null},{"id":"2307.00968","title":"REAL: A Representative Error-Driven Approach for Active Learning","created":"2023-07-03","cited_by_count":3,"area":null},{"id":"2311.02310","title":"Narrowing the Gap between Zero- and Few-shot Machine Translation by Matching Styles","created":"2023-11-04","cited_by_count":3,"area":null}],"next_cursor":"100"}