{"list":"other","total":60,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"1912.02164","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","created":"2019-12-04","cited_by_count":799},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609},{"id":"2412.13663","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","created":"2024-12-18","cited_by_count":554},{"id":"2105.03023","title":"DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts","created":"2021-05-07","cited_by_count":441},{"id":"2009.06367","title":"GeDi: Generative Discriminator Guided Sequence Generation","created":"2020-09-14","cited_by_count":378},{"id":"2103.00453","title":"Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP","created":"2021-02-28","cited_by_count":337},{"id":"2301.11270","title":"Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons","created":"2023-01-26","cited_by_count":247},{"id":"1704.07138","title":"Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search","created":"2017-04-24","cited_by_count":237},{"id":"2307.09702","title":"Efficient Guided Generation for Large Language Models","created":"2023-07-19","cited_by_count":200},{"id":"2305.13971","title":"Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning","created":"2023-05-23","cited_by_count":197},{"id":"2404.14367","title":"Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data","created":"2024-04-22","cited_by_count":185},{"id":"1804.06609","title":"Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation","created":"2018-04-18","cited_by_count":182},{"id":"2202.11705","title":"COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics","created":"2022-02-23","cited_by_count":161},{"id":"2201.11227","title":"Synchromesh: Reliable code generation from pre-trained language models","created":"2022-01-26","cited_by_count":156},{"id":"2112.08726","title":"NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics","created":"2021-12-16","cited_by_count":154},{"id":"2407.01082","title":"Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs","created":"2024-07-01","cited_by_count":150},{"id":"2010.12884","title":"NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints","created":"2020-10-24","cited_by_count":149},{"id":"2205.11275","title":"RL with KL penalties is better viewed as Bayesian inference","created":"2022-05-23","cited_by_count":135},{"id":"1805.06087","title":"Learning to Write with Cooperative Discriminators","created":"2018-05-16","cited_by_count":119},{"id":"2310.20410","title":"FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models","created":"2023-10-31","cited_by_count":117},{"id":"2410.20290","title":"Fast Best-of-N Decoding via Speculative Rejection","created":"2024-10-26","cited_by_count":112},{"id":"2212.06094","title":"Prompting Is Programming: A Query Language for Large Language Models","created":"2022-12-12","cited_by_count":110},{"id":"1612.00576","title":"Guided Open Vocabulary Image Captioning with Constrained Beam Search","created":"2016-12-02","cited_by_count":105},{"id":"2004.06231","title":"Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits","created":"2020-04-13","cited_by_count":103},{"id":"2206.00426","title":"Semantic Probabilistic Layers for Neuro-Symbolic Learning","created":"2022-06-01","cited_by_count":103},{"id":"2403.06988","title":"Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation","created":"2024-02-07","cited_by_count":101},{"id":"1811.10996","title":"CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling","created":"2018-11-14","cited_by_count":94},{"id":"2404.17546","title":"Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo","created":"2024-04-26","cited_by_count":90},{"id":"2406.11176","title":"Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement","created":"2024-06-17","cited_by_count":88},{"id":"2304.14293","title":"Controlled Text Generation with Natural Language Instructions","created":"2023-04-27","cited_by_count":87},{"id":"2306.03081","title":"Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs","created":"2023-06-05","cited_by_count":80},{"id":"2502.10341","title":"Organize the Web: Constructing Domains Enhances Pre-Training Data Curation","created":"2025-02-14","cited_by_count":76},{"id":"2310.14542","title":"Evaluating Large Language Models on Controlled Generation Tasks","created":"2023-10-23","cited_by_count":73},{"id":"2205.09726","title":"RankGen: Improving Text Generation with Large Ranking Models","created":"2022-05-19","cited_by_count":72},{"id":"2501.10868","title":"JSONSchemaBench: A Rigorous Benchmark of Structured Outputs for Language Models","created":"2025-01-18","cited_by_count":71},{"id":"2205.12558","title":"Gradient-Based Constrained Sampling from Language Models","created":"2022-05-25","cited_by_count":64},{"id":"2311.14479","title":"Controlled Text Generation via Language Model Arithmetic","created":"2023-11-24","cited_by_count":51},{"id":"2407.06057","title":"Variational Best-of-N Alignment","created":"2024-07-08","cited_by_count":51},{"id":"2407.08103","title":"Automata-based constraints for language model decoding","created":"2024-07-11","cited_by_count":51},{"id":"2012.02952","title":"Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation","created":"2020-12-05","cited_by_count":47},{"id":"2504.13139","title":"Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo","created":"2025-04-17","cited_by_count":46},{"id":"2502.12668","title":"Evaluation of Best-of-N Sampling Strategies for Language Model Alignment","created":"2025-02-18","cited_by_count":39},{"id":"2004.02082","title":"On Tractable Representations of Binary Neural Networks","created":"2020-04-05","cited_by_count":34},{"id":"2406.13892","title":"Adaptable Logical Control for Large Language Models","created":"2024-06-19","cited_by_count":30},{"id":"2404.15846","title":"From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models","created":"2024-04-24","cited_by_count":27},{"id":"2410.17195","title":"Non-myopic Generation of Language Models for Reasoning and Planning","created":"2024-10-22","cited_by_count":26},{"id":"2312.03905","title":"A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints","created":"2023-12-06","cited_by_count":22},{"id":"2212.10466","title":"Controllable Text Generation with Language Constraints","created":"2022-12-20","cited_by_count":18},{"id":"1903.01620","title":"What to Expect of Classifiers? Reasoning about Logistic Regression with Missing Features","created":"2019-03-05","cited_by_count":12},{"id":"2410.13111","title":"Controllable Generation via Locally Constrained Resampling","created":"2024-10-17","cited_by_count":11},{"id":"2405.01490","title":"Controllable Text Generation in the Instruction-Tuning Era","created":"2024-05-02","cited_by_count":7},{"id":"1602.07415","title":"Ensuring Rapid Mixing and Low Bias for Asynchronous Gibbs Sampling","created":"2016-02-24","cited_by_count":5}],"next_cursor":null}