{"total":43,"rows":[{"id":"2309.11235","title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","created":"2023-09-20","cited_by_count":252,"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":"2310.17022","title":"Controlled Decoding from Language Models","created":"2023-10-25","cited_by_count":135,"area":null},{"id":"2206.00761","title":"On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting","created":"2022-06-01","cited_by_count":82,"area":null},{"id":"2306.03081","title":"Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs","created":"2023-06-05","cited_by_count":80,"area":null},{"id":"2310.00035","title":"LoRA ensembles for large language model fine-tuning","created":"2023-09-29","cited_by_count":67,"area":null},{"id":"2310.12962","title":"An Emulator for Fine-Tuning Large Language Models using Small Language Models","created":"2023-10-19","cited_by_count":61,"area":null},{"id":"2510.17516","title":"SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors","created":"2025-10-20","cited_by_count":52,"area":null},{"id":"2504.13139","title":"Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo","created":"2025-04-17","cited_by_count":46,"area":null},{"id":"2305.15065","title":"Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning","created":"2023-05-24","cited_by_count":33,"area":null},{"id":"2211.08714","title":"Reward Gaming in Conditional Text Generation","created":"2022-11-16","cited_by_count":30,"area":null},{"id":"2410.07927","title":"Efficient Reinforcement Learning with Large Language Model Priors","created":"2024-10-10","cited_by_count":30,"area":null},{"id":"2401.13586","title":"Instruction Fine-Tuning: Does Prompt Loss Matter?","created":"2024-01-24","cited_by_count":26,"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":"2504.02367","title":"Reinforcement Fine-Tuning for Materials Design","created":"2025-04-03","cited_by_count":13,"area":null},{"id":"2302.00805","title":"Conditioning Predictive Models: Risks and Strategies","created":"2023-02-02","cited_by_count":11,"area":null},{"id":"2410.22296","title":"Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks","created":"2024-10-29","cited_by_count":10,"area":null},{"id":"2512.15605","title":"Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Prediction","created":"2025-12-17","cited_by_count":8,"area":null},{"id":"2310.02263","title":"Automatic Pair Construction for Contrastive Post-training","created":"2023-10-03","cited_by_count":7,"area":null},{"id":"2402.03284","title":"Deal, or no deal (or who knows)? Forecasting Uncertainty in Conversations using Large Language Models","created":"2024-02-05","cited_by_count":6,"area":null},{"id":"2410.00362","title":"FedPT: Federated Proxy-Tuning of Large Language Models on Resource-Constrained Edge Devices","created":"2024-10-01","cited_by_count":5,"area":null},{"id":"2505.01954","title":"Semantic Probabilistic Control of Language Models","created":"2025-05-04","cited_by_count":4,"area":null},{"id":"2505.17795","title":"DialogXpert: Driving Intelligent and Emotion-Aware Conversations through Online Value-Based Reinforcement Learning with LLM Priors","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2412.02626","title":"Time-Reversal Provides Unsupervised Feedback to LLMs","created":"2024-12-03","cited_by_count":3,"area":null},{"id":"2510.21296","title":"An Evidence-Based Post-Hoc Adjustment Framework for Anomaly Detection Under Data Contamination","created":"2025-10-24","cited_by_count":3,"area":null},{"id":"2605.26552","title":"Aligning Few-Step Generative Models by Amortizing Sample-based Variational Inference","created":"2026-05-26","cited_by_count":3,"area":null},{"id":"2606.29604","title":"Mechanistically Eliciting Latent Behaviors in Language Models","created":"2026-06-28","cited_by_count":3,"area":null},{"id":"2507.02315","title":"Improving Constrained Language Generation via Self-Distilled Twisted Sequential Monte Carlo","created":"2025-07-03","cited_by_count":2,"area":null},{"id":"2406.13660","title":"Towards Minimal Targeted Updates of Language Models with Targeted Negative Training","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2508.10409","title":"Dataset Construction for Training LLM to Learn Analog Circuit Knowledge","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2604.28036","title":"Exponential families from a single KL identity","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.21195","title":"RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2607.22837","title":"Frustratingly Simple Black-Box Adaptation of Language Models via Logit Bias","created":"2026-07-24","cited_by_count":1,"area":null},{"id":"2610.05292","title":"Erased, Rerouted, or Rescaled? Post-Training and the Causal Quotient of a Language Model's Belief State","created":"2026-10-04","cited_by_count":1,"area":null},{"id":"2310.04483","title":"Reward Dropout Improves Control: Bi-objective Perspective on Reinforced LM","created":"2023-10-06","cited_by_count":0,"area":null},{"id":"2510.21184","title":"Reducing the Probability of Undesirable Outputs in Language Models Using Probabilistic Inference","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2605.05732","title":"CRAFT: Forgetting-Aware Intervention-Based Adaptation for Continual Learning","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.08368","title":"On Distinguishing Capability Elicitation from Capability Creation in Post-Training: A Free-Energy Perspective","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2607.05855","title":"Unsupervised Anomaly Detection of Information Operations Users via Behavioral and Language Patterns","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2609.30218","title":"Minimally Invasive Steering of Language Models","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.35083","title":"Continuous Variational Synthesis","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.01034","title":"Posterior sampling by source-space MCMC via prior-based few-step transport maps","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.15058","title":"The Optimal Decoder is Tilted Temperature","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}