{"total":55,"rows":[{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354,"area":null},{"id":"2205.13636","title":"Quark: Controllable Text Generation with Reinforced Unlearning","created":"2022-05-26","cited_by_count":237,"area":"safety"},{"id":"2203.16804","title":"BRIO: Bringing Order to Abstractive Summarization","created":"2022-03-31","cited_by_count":161,"area":null},{"id":"2106.01890","title":"SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization","created":"2021-06-03","cited_by_count":132,"area":null},{"id":"2210.00045","title":"Calibrating Sequence likelihood Improves Conditional Language Generation","created":"2022-09-30","cited_by_count":121,"area":null},{"id":"2111.09388","title":"High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metrics","created":"2021-11-17","cited_by_count":104,"area":null},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"area":null},{"id":"2305.14239","title":"On Learning to Summarize with Large Language Models as References","created":"2023-05-23","cited_by_count":80,"area":null},{"id":"2205.09726","title":"RankGen: Improving Text Generation with Large Ranking Models","created":"2022-05-19","cited_by_count":72,"area":null},{"id":"2108.01850","title":"Controlled Text Generation as Continuous Optimization with Multiple Constraints","created":"2021-08-04","cited_by_count":70,"area":null},{"id":"2104.05336","title":"Machine Translation Decoding beyond Beam Search","created":"2021-04-12","cited_by_count":55,"area":null},{"id":"2205.00978","title":"Quality-Aware Decoding for Neural Machine Translation","created":"2022-05-02","cited_by_count":49,"area":null},{"id":"2310.10047","title":"Improving Large Language Model Fine-tuning for Solving Math Problems","created":"2023-10-16","cited_by_count":49,"area":null},{"id":"2404.10859","title":"Forcing Diffuse Distributions out of Language Models","created":"2024-04-16","cited_by_count":48,"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":"2106.08942","title":"Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation","created":"2021-06-16","cited_by_count":33,"area":null},{"id":"2106.05251","title":"Bayesian Attention Belief Networks","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2307.03131","title":"BLEURT Has Universal Translations: An Analysis of Automatic Metrics by Minimum Risk Training","created":"2023-07-06","cited_by_count":24,"area":null},{"id":"2407.13709","title":"Understanding Reference Policies in Direct Preference Optimization","created":"2024-07-18","cited_by_count":22,"area":"alignment"},{"id":"2106.02208","title":"BERTTune: Fine-Tuning Neural Machine Translation with BERTScore","created":"2021-06-04","cited_by_count":18,"area":null},{"id":"2106.08122","title":"Sequence-Level Training for Non-Autoregressive Neural Machine Translation","created":"2021-06-15","cited_by_count":18,"area":null},{"id":"2107.11353","title":"Modelling Latent Translations for Cross-Lingual Transfer","created":"2021-07-23","cited_by_count":16,"area":null},{"id":"2308.02223","title":"ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation","created":"2023-08-04","cited_by_count":15,"area":null},{"id":"2210.10929","title":"Hierarchical classification at multiple operating points","created":"2022-10-19","cited_by_count":14,"area":null},{"id":"2104.07541","title":"Reward Optimization for Neural Machine Translation with Learned Metrics","created":"2021-04-15","cited_by_count":12,"area":null},{"id":"2204.05424","title":"A Call for Clarity in Beam Search: How It Works and When It Stops","created":"2022-04-11","cited_by_count":10,"area":null},{"id":"2310.13340","title":"Large-Scale and Multi-Perspective Opinion Summarization with Diverse Review Subsets","created":"2023-10-20","cited_by_count":10,"area":null},{"id":"2106.15880","title":"Mixed Cross Entropy Loss for Neural Machine Translation","created":"2021-06-30","cited_by_count":8,"area":null},{"id":"2212.04257","title":"Momentum Calibration for Text Generation","created":"2022-12-08","cited_by_count":8,"area":null},{"id":"2207.08583","title":"MAD for Robust Reinforcement Learning in Machine Translation","created":"2022-07-18","cited_by_count":7,"area":null},{"id":"2210.11017","title":"Multi-Granularity Optimization for Non-Autoregressive Translation","created":"2022-10-20","cited_by_count":6,"area":null},{"id":"2106.04080","title":"RewardsOfSum: Exploring Reinforcement Learning Rewards for Summarisation","created":"2021-06-08","cited_by_count":4,"area":null},{"id":"2205.04686","title":"AdMix: A Mixed Sample Data Augmentation Method for Neural Machine Translation","created":"2022-05-10","cited_by_count":4,"area":null},{"id":"2212.03230","title":"Switching to Discriminative Image Captioning by Relieving a Bottleneck of Reinforcement Learning","created":"2022-12-06","cited_by_count":4,"area":null},{"id":"2310.17217","title":"Beyond MLE: Convex Learning for Text Generation","created":"2023-10-26","cited_by_count":4,"area":null},{"id":"2506.05070","title":"RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translation","created":"2025-06-05","cited_by_count":4,"area":"alignment"},{"id":"2103.11795","title":"Simpson's Bias in NLP Training","created":"2021-03-13","cited_by_count":3,"area":null},{"id":"2109.03939","title":"What's Hidden in a One-layer Randomly Weighted Transformer?","created":"2021-09-08","cited_by_count":3,"area":null},{"id":"2203.02889","title":"Focus on the Target's Vocabulary: Masked Label Smoothing for Machine Translation","created":"2022-03-06","cited_by_count":3,"area":null},{"id":"2310.13385","title":"Tuna: Instruction Tuning using Feedback from Large Language Models","created":"2023-10-20","cited_by_count":3,"area":"alignment"},{"id":"2603.12248","title":"Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models","created":"2026-03-12","cited_by_count":3,"area":null},{"id":"2207.13354","title":"Are Neighbors Enough? Multi-Head Neural n-gram can be Alternative to Self-attention","created":"2022-07-27","cited_by_count":2,"area":null},{"id":"2210.03053","title":"Reinforcement Learning with Large Action Spaces for Neural Machine Translation","created":"2022-10-06","cited_by_count":2,"area":null},{"id":"2307.13421","title":"On the Learning Dynamics of Attention Networks","created":"2023-07-25","cited_by_count":2,"area":null},{"id":"2207.11161","title":"Lagrangian Method for Q-Function Learning (with Applications to Machine Translation)","created":"2022-07-22","cited_by_count":1,"area":null},{"id":"2209.14694","title":"GROOT: Corrective Reward Optimization for Generative Sequential Labeling","created":"2022-09-29","cited_by_count":1,"area":null},{"id":"2305.14380","title":"Finding the Pillars of Strength for Multi-Head Attention","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2410.19586","title":"Diverse Sign Language Translation","created":"2024-10-25","cited_by_count":1,"area":null},{"id":"2606.14283","title":"DIFF-ERO: A Conformance-Aware Loss for Deep Learning in Process Mining","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2105.14850","title":"Cascaded Head-colliding Attention","created":"2021-05-31","cited_by_count":0,"area":null},{"id":"2211.11649","title":"Implicit Training of Energy Model for Structure Prediction","created":"2022-11-21","cited_by_count":0,"area":null},{"id":"2211.16550","title":"Soft Alignment Objectives for Robust Adaptation of Language Generation","created":"2022-11-29","cited_by_count":0,"area":null},{"id":"2310.15259","title":"Reference Free Domain Adaptation for Translation of Noisy Questions with Question Specific Rewards","created":"2023-10-23","cited_by_count":0,"area":null},{"id":"2311.07066","title":"Context Consistency between Training and Testing in Simultaneous Machine Translation","created":"2023-11-13","cited_by_count":0,"area":null},{"id":"2410.06118","title":"Optimizing the Training Schedule of Multilingual NMT using Reinforcement Learning","created":"2024-10-08","cited_by_count":0,"area":"alignment"}],"next_cursor":null}