{"total":114,"rows":[{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601,"area":null},{"id":"2305.13971","title":"Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning","created":"2023-05-23","cited_by_count":197,"area":null},{"id":"2305.00633","title":"Self-Evaluation Guided Beam Search for Reasoning","created":"2023-05-01","cited_by_count":196,"area":"lr"},{"id":"2203.16804","title":"BRIO: Bringing Order to Abstractive Summarization","created":"2022-03-31","cited_by_count":161,"area":null},{"id":"2406.16838","title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2203.05115","title":"Internet-augmented language models through few-shot prompting for open-domain question answering","created":"2022-03-10","cited_by_count":131,"area":null},{"id":"2303.03329","title":"End-to-End Speech Recognition: A Survey","created":"2023-03-03","cited_by_count":129,"area":null},{"id":"2303.16104","title":"Hallucinations in Large Multilingual Translation Models","created":"2023-03-28","cited_by_count":129,"area":null},{"id":"2202.00666","title":"Locally Typical Sampling","created":"2022-02-01","cited_by_count":111,"area":null},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"area":null},{"id":"2203.15721","title":"On Decoding Strategies for Neural Text Generators","created":"2022-03-29","cited_by_count":90,"area":null},{"id":"2211.16490","title":"Coder Reviewer Reranking for Code Generation","created":"2022-11-29","cited_by_count":84,"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":"2108.04718","title":"Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation","created":"2021-08-10","cited_by_count":65,"area":null},{"id":"2009.07839","title":"Text Generation by Learning from Demonstrations","created":"2020-09-16","cited_by_count":64,"area":"offlinerl"},{"id":"2208.05309","title":"Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation","created":"2022-08-10","cited_by_count":61,"area":null},{"id":"2307.15703","title":"Uncertainty in Natural Language Generation: From Theory to Applications","created":"2023-07-28","cited_by_count":61,"area":null},{"id":"2105.08504","title":"Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation","created":"2021-05-18","cited_by_count":56,"area":null},{"id":"2111.00607","title":"A Systematic Investigation of Commonsense Knowledge in Large Language Models","created":"2021-10-31","cited_by_count":56,"area":null},{"id":"2104.05336","title":"Machine Translation Decoding beyond Beam Search","created":"2021-04-12","cited_by_count":55,"area":null},{"id":"2212.09739","title":"LENS: A Learnable Evaluation Metric for Text Simplification","created":"2022-12-19","cited_by_count":54,"area":null},{"id":"2310.01387","title":"It's MBR All the Way Down: Modern Generation Techniques Through the Lens of Minimum Bayes Risk","created":"2023-10-02","cited_by_count":51,"area":null},{"id":"2205.00978","title":"Quality-Aware Decoding for Neural Machine Translation","created":"2022-05-02","cited_by_count":49,"area":null},{"id":"2509.06870","title":"The Majority is not always right: RL training for solution aggregation","created":"2025-09-08","cited_by_count":47,"area":"lr"},{"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":"2302.08242","title":"Tuning computer vision models with task rewards","created":"2023-02-16","cited_by_count":37,"area":null},{"id":"2305.11746","title":"HalOmi: A Manually Annotated Benchmark for Multilingual Hallucination and Omission Detection in Machine Translation","created":"2023-05-19","cited_by_count":35,"area":null},{"id":"2310.01693","title":"Closing the Curious Case of Neural Text Degeneration","created":"2023-10-02","cited_by_count":32,"area":null},{"id":"2303.03278","title":"Faithfulness-Aware Decoding Strategies for Abstractive Summarization","created":"2023-03-06","cited_by_count":31,"area":null},{"id":"2211.08714","title":"Reward Gaming in Conditional Text Generation","created":"2022-11-16","cited_by_count":30,"area":null},{"id":"2104.07429","title":"First the worst: Finding better gender translations during beam search","created":"2021-04-15","cited_by_count":29,"area":null},{"id":"2301.02828","title":"Why do Nearest Neighbor Language Models Work?","created":"2023-01-07","cited_by_count":29,"area":"rag"},{"id":"2110.08191","title":"Why don't people use character-level machine translation?","created":"2021-10-15","cited_by_count":27,"area":null},{"id":"2202.00528","title":"Examining Scaling and Transfer of Language Model Architectures for Machine Translation","created":"2022-02-01","cited_by_count":26,"area":null},{"id":"2404.01054","title":"Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment","created":"2024-04-01","cited_by_count":25,"area":"alignment"},{"id":"2504.05410","title":"Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Sampling","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2106.07207","title":"Straight to the Gradient: Learning to Use Novel Tokens for Neural Text Generation","created":"2021-06-14","cited_by_count":19,"area":null},{"id":"2203.12788","title":"Evaluating Distributional Distortion in Neural Language Modeling","created":"2022-03-24","cited_by_count":19,"area":null},{"id":"2308.00189","title":"Generative Models as a Complex Systems Science: How can we make sense of large language model behavior?","created":"2023-07-31","cited_by_count":19,"area":null},{"id":"2404.14600","title":"Planning Ahead in Generative Retrieval: Guiding Autoregressive Generation through Simultaneous Decoding","created":"2024-04-22","cited_by_count":19,"area":null},{"id":"2106.07400","title":"Determinantal Beam Search","created":"2021-06-14","cited_by_count":18,"area":null},{"id":"2203.17217","title":"On the probability-quality paradox in language generation","created":"2022-03-31","cited_by_count":16,"area":null},{"id":"2305.16958","title":"MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies","created":"2023-05-26","cited_by_count":16,"area":null},{"id":"2406.00049","title":"QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation","created":"2024-05-28","cited_by_count":16,"area":null},{"id":"2506.03149","title":"Causal Estimation of Tokenisation Bias","created":"2025-06-03","cited_by_count":16,"area":null},{"id":"2401.02749","title":"Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding","created":"2024-01-05","cited_by_count":15,"area":null},{"id":"2410.09303","title":"Exact Byte-Level Probabilities from Tokenized Language Models for FIM-Tasks and Model Ensembles","created":"2024-10-11","cited_by_count":15,"area":null},{"id":"2510.02172","title":"RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalization","created":"2025-10-02","cited_by_count":15,"area":"lr"},{"id":"2210.05193","title":"Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translation","created":"2022-10-11","cited_by_count":13,"area":null},{"id":"2401.06688","title":"Don't Rank, Combine! Combining Machine Translation Hypotheses Using Quality Estimation","created":"2024-01-12","cited_by_count":13,"area":null},{"id":"2103.10291","title":"Smoothing and Shrinking the Sparse Seq2Seq Search Space","created":"2021-03-18","cited_by_count":11,"area":null},{"id":"2311.05263","title":"Model-Based Minimum Bayes Risk Decoding for Text Generation","created":"2023-11-09","cited_by_count":11,"area":null},{"id":"2401.05054","title":"Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding","created":"2024-01-10","cited_by_count":11,"area":null},{"id":"2503.05318","title":"Uncertainty-Aware Decoding with Minimum Bayes Risk","created":"2025-03-07","cited_by_count":11,"area":null},{"id":"2112.08914","title":"Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modeling","created":"2021-12-16","cited_by_count":10,"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":"2205.00704","title":"Jam or Cream First? Modeling Ambiguity in Neural Machine Translation with SCONES","created":"2022-05-02","cited_by_count":10,"area":null},{"id":"2210.14502","title":"SentBS: Sentence-level Beam Search for Controllable Summarization","created":"2022-10-26","cited_by_count":10,"area":null},{"id":"2105.03458","title":"Duplex Sequence-to-Sequence Learning for Reversible Machine Translation","created":"2021-05-07","cited_by_count":9,"area":null},{"id":"2204.00471","title":"Uncertainty Determines the Adequacy of the Mode and the Tractability of Decoding in Sequence-to-Sequence Models","created":"2022-04-01","cited_by_count":9,"area":null},{"id":"2205.09665","title":"Automated Crossword Solving","created":"2022-05-19","cited_by_count":9,"area":null},{"id":"2112.07660","title":"Massive-scale Decoding for Text Generation using Lattices","created":"2021-12-14","cited_by_count":8,"area":null},{"id":"2205.15217","title":"GraphWalks: Efficient Shape Agnostic Geodesic Shortest Path Estimation","created":"2022-05-30","cited_by_count":8,"area":null},{"id":"2209.14569","title":"COLO: A Contrastive Learning based Re-ranking Framework for One-Stage Summarization","created":"2022-09-29","cited_by_count":8,"area":null},{"id":"2402.03131","title":"Constrained Decoding for Cross-lingual Label Projection","created":"2024-02-05","cited_by_count":8,"area":null},{"id":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2107.09729","title":"What Do You Get When You Cross Beam Search with Nucleus Sampling?","created":"2021-07-20","cited_by_count":7,"area":null},{"id":"2102.02574","title":"Incremental Beam Manipulation for Natural Language Generation","created":"2021-02-04","cited_by_count":6,"area":null},{"id":"2211.11924","title":"Best-$k$ Search Algorithm for Neural Text Generation","created":"2022-11-22","cited_by_count":6,"area":null},{"id":"2210.07228","title":"Language Model Decoding as Likelihood-Utility Alignment","created":"2022-10-13","cited_by_count":5,"area":null},{"id":"2305.19330","title":"Breeding Machine Translations: Evolutionary approach to survive and thrive in the world of automated evaluation","created":"2023-05-30","cited_by_count":5,"area":null},{"id":"2410.10810","title":"Local and Global Decoding in Text Generation","created":"2024-10-14","cited_by_count":5,"area":null},{"id":"2101.05400","title":"Machine-Assisted Script Curation","created":"2021-01-14","cited_by_count":4,"area":null},{"id":"2109.06253","title":"Multi-Sentence Resampling: A Simple Approach to Alleviate Dataset Length Bias and Beam-Search Degradation","created":"2021-09-13","cited_by_count":4,"area":null},{"id":"2205.09273","title":"Twist Decoding: Diverse Generators Guide Each Other","created":"2022-05-19","cited_by_count":4,"area":null},{"id":"2210.08763","title":"ReasonChainQA: Text-based Complex Question Answering with Explainable Evidence Chains","created":"2022-10-17","cited_by_count":4,"area":null},{"id":"2212.04205","title":"DC-MBR: Distributional Cooling for Minimum Bayesian Risk Decoding","created":"2022-12-08","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":"2407.03951","title":"Uncertainty-Guided Likelihood Tree Search","created":"2024-07-04","cited_by_count":4,"area":"lr"},{"id":"2605.01357","title":"On Stable Long-Form Generation: Benchmarking and Mitigating Length Volatility","created":"2026-05-02","cited_by_count":4,"area":null},{"id":"2111.06832","title":"Speeding Up Entmax","created":"2021-11-12","cited_by_count":3,"area":null},{"id":"2210.10817","title":"A Continuum of Generation Tasks for Investigating Length Bias and Degenerate Repetition","created":"2022-10-19","cited_by_count":3,"area":null},{"id":"2302.08531","title":"Learning with Rejection for Abstractive Text Summarization","created":"2023-02-16","cited_by_count":3,"area":null},{"id":"2102.08424","title":"Searching for Search Errors in Neural Morphological Inflection","created":"2021-02-16","cited_by_count":2,"area":null},{"id":"2106.15217","title":"Digging Errors in NMT: Evaluating and Understanding Model Errors from Partial Hypothesis Space","created":"2021-06-29","cited_by_count":2,"area":null},{"id":"2205.00659","title":"The Implicit Length Bias of Label Smoothing on Beam Search Decoding","created":"2022-05-02","cited_by_count":2,"area":null},{"id":"2211.16174","title":"CUNI Submission in WMT22 General Task","created":"2022-11-29","cited_by_count":2,"area":null},{"id":"2308.13696","title":"On the Depth between Beam Search and Exhaustive Search for Text Generation","created":"2023-08-25","cited_by_count":2,"area":null},{"id":"2408.05738","title":"Language-Informed Beam Search Decoding for Multilingual Machine Translation","created":"2024-08-11","cited_by_count":2,"area":null},{"id":"2411.09689","title":"Probing LLM Hallucination from Within: Perturbation-Driven Approach via Internal Knowledge","created":"2024-11-14","cited_by_count":2,"area":null},{"id":"2506.06832","title":"Cross-Entropy Games for Language Models: From Implicit Knowledge to General Capability Measures","created":"2025-06-07","cited_by_count":2,"area":null},{"id":"2510.20700","title":"Structure-Conditional Minimum Bayes Risk Decoding","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2106.05459","title":"Mode recovery in neural autoregressive sequence modeling","created":"2021-06-10","cited_by_count":1,"area":null},{"id":"2106.12698","title":"Comparative Error Analysis in Neural and Finite-state Models for Unsupervised Character-level Transduction","created":"2021-06-24","cited_by_count":1,"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":"2212.09895","title":"Improved Long-Form Spoken Language Translation with Large Language Models","created":"2022-12-19","cited_by_count":1,"area":null},{"id":"2305.13000","title":"Bidirectional Transformer Reranker for Grammatical Error Correction","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2305.14859","title":"Utility-Probability Duality of Neural Networks","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2401.00379","title":"DREAM: Debugging and Repairing AutoML Pipelines","created":"2023-12-31","cited_by_count":1,"area":null},{"id":"2403.14562","title":"Agentic AI: The Era of Semantic Decoding","created":"2024-03-21","cited_by_count":1,"area":"agents"}],"next_cursor":"100"}