{"total":121,"rows":[{"id":"2507.16806","title":"Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty","created":"2025-07-22","cited_by_count":117,"area":"lr"},{"id":"2407.18370","title":"Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement","created":"2024-07-25","cited_by_count":105,"area":null},{"id":"2505.22660","title":"Maximizing Confidence Alone Improves Reasoning","created":"2025-05-28","cited_by_count":100,"area":"lr"},{"id":"2409.19886","title":"RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models","created":"2024-09-30","cited_by_count":88,"area":null},{"id":"2502.08773","title":"Universal Model Routing for Efficient LLM Inference","created":"2025-02-12","cited_by_count":86,"area":"inference"},{"id":"2502.18036","title":"Harnessing Multiple Large Language Models: A Survey on LLM Ensemble","created":"2025-02-25","cited_by_count":86,"area":null},{"id":"2410.10347","title":"A Unified Approach to Routing and Cascading for LLMs","created":"2024-10-14","cited_by_count":80,"area":"agents"},{"id":"2506.22716","title":"BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute","created":"2025-06-28","cited_by_count":67,"area":null},{"id":"2505.14489","title":"Reasoning Models Better Express Their Confidence","created":"2025-05-20","cited_by_count":65,"area":"lr"},{"id":"2406.11675","title":"BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models","created":"2024-06-17","cited_by_count":50,"area":null},{"id":"2405.16587","title":"Cost-Effective Online Multi-LLM Selection with Versatile Reward Models","created":"2024-05-26","cited_by_count":39,"area":"alignment"},{"id":"2405.19261","title":"Faster Cascades via Speculative Decoding","created":"2024-05-29","cited_by_count":38,"area":"inference"},{"id":"2412.03324","title":"A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs","created":"2024-12-04","cited_by_count":35,"area":"mllm"},{"id":"2502.01976","title":"CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing","created":"2025-02-04","cited_by_count":30,"area":null},{"id":"2509.26209","title":"Diversity-Incentivized Exploration for Versatile Reasoning","created":"2025-09-30","cited_by_count":28,"area":"lr"},{"id":"2502.00290","title":"Estimating LLM Uncertainty with Evidence","created":"2025-02-01","cited_by_count":26,"area":null},{"id":"2506.17871","title":"LLM Probability Concentration: How Alignment Shrinks the Generative Horizon","created":"2025-06-22","cited_by_count":26,"area":"alignment"},{"id":"2502.04392","title":"Division-of-Thoughts: Harnessing Hybrid Language Model Synergy for Efficient On-Device Agents","created":"2025-02-06","cited_by_count":25,"area":"lr"},{"id":"2409.18786","title":"A Survey on the Honesty of Large Language Models","created":"2024-09-27","cited_by_count":23,"area":"alignment"},{"id":"2502.17214","title":"CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thought","created":"2025-02-24","cited_by_count":23,"area":"lr"},{"id":"2502.17421","title":"LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification","created":"2025-02-24","cited_by_count":21,"area":"agents"},{"id":"2502.10709","title":"An Empirical Analysis of Uncertainty in Large Language Model Evaluations","created":"2025-02-15","cited_by_count":20,"area":null},{"id":"2501.00555","title":"Prune 'n Predict: Optimizing LLM Decision-making with Conformal Prediction","created":"2024-12-31","cited_by_count":18,"area":null},{"id":"2506.13351","title":"Direct Reasoning Optimization: Token-Level Reasoning Reflectivity Meets Rubric Gates for Unverifiable Tasks","created":"2025-06-16","cited_by_count":18,"area":"lr"},{"id":"2406.05213","title":"On Subjective Uncertainty Quantification and Calibration in Natural Language Generation","created":"2024-06-07","cited_by_count":16,"area":null},{"id":"2407.02348","title":"Agreement-Based Cascading for Efficient Inference","created":"2024-07-02","cited_by_count":16,"area":null},{"id":"2410.02719","title":"UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation","created":"2024-10-03","cited_by_count":16,"area":"rag"},{"id":"2508.12491","title":"Cost-Aware Contrastive Routing for LLMs","created":"2025-08-17","cited_by_count":16,"area":null},{"id":"2406.00060","title":"Cascade-Aware Training of Language Models","created":"2024-05-29","cited_by_count":15,"area":null},{"id":"2410.18779","title":"A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2505.02874","title":"Uncertainty Quantification for Machine Learning in Healthcare: A Survey","created":"2025-05-04","cited_by_count":14,"area":null},{"id":"2505.07961","title":"Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement","created":"2025-05-12","cited_by_count":14,"area":"lr"},{"id":"2506.09669","title":"Query-Level Uncertainty in Large Language Models","created":"2025-06-11","cited_by_count":14,"area":null},{"id":"2510.24051","title":"Pie: A Programmable Serving System for Emerging LLM Applications","created":"2025-10-28","cited_by_count":14,"area":"lr"},{"id":"2412.05723","title":"Training-Free Bayesianization for Low-Rank Adapters of Large Language Models","created":"2024-12-07","cited_by_count":12,"area":null},{"id":"2506.03880","title":"RadialRouter: Structured Representation for Efficient and Robust Large Language Models Routing","created":"2025-06-04","cited_by_count":11,"area":null},{"id":"2602.01062","title":"SetPO: Set-Level Policy Optimization for Diversity-Preserving LLM Reasoning","created":"2026-02-01","cited_by_count":11,"area":"lr"},{"id":"2501.09345","title":"Rational Tuning of LLM Cascades via Probabilistic Modeling","created":"2025-01-16","cited_by_count":10,"area":null},{"id":"2502.19335","title":"Gatekeeper: Improving Model Cascades Through Confidence Tuning","created":"2025-02-26","cited_by_count":10,"area":null},{"id":"2510.09913","title":"Don't Throw Away Your Pretrained Model","created":"2025-10-10","cited_by_count":10,"area":"lr"},{"id":"2511.06190","title":"Confidence-Guided Stepwise Model Routing for Cost-Efficient Reasoning","created":"2025-11-09","cited_by_count":9,"area":"lr"},{"id":"2410.08014","title":"Privacy-preserved LLM Cascade via CoT-enhanced Policy Learning","created":"2024-10-10","cited_by_count":8,"area":null},{"id":"2501.02020","title":"Enhancing Uncertainty Modeling with Semantic Graph for Hallucination Detection","created":"2025-01-02","cited_by_count":8,"area":null},{"id":"2509.23129","title":"C$^2$GSPG: Confidence-calibrated Group Sequence Policy Gradient towards Self-aware Reasoning","created":"2025-09-27","cited_by_count":8,"area":"lr"},{"id":"2509.21837","title":"Semantic Agreement Enables Efficient Open-Ended LLM Cascades","created":"2025-09-26","cited_by_count":7,"area":null},{"id":"2602.05176","title":"Among Us: Measuring and Mitigating Malicious Contributions in Model Collaboration Systems","created":"2026-02-05","cited_by_count":7,"area":"agents"},{"id":"2506.17336","title":"PPMI: Privacy-Preserving LLM Interaction with Socratic Chain-of-Thought Reasoning and Homomorphically Encrypted Vector Databases","created":"2025-06-19","cited_by_count":6,"area":"lr"},{"id":"2601.21257","title":"MoCo: A One-Stop Shop for Model Collaboration Research","created":"2026-01-29","cited_by_count":6,"area":null},{"id":"2603.24844","title":"Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models","created":"2026-03-25","cited_by_count":6,"area":"lr"},{"id":"2605.15206","title":"AgentStop: Terminating Local AI Agents Early to Save Energy in Consumer Devices","created":"2026-05-01","cited_by_count":6,"area":"agents"},{"id":"2410.02173","title":"Efficiently Deploying LLMs with Controlled Risk","created":"2024-10-03","cited_by_count":5,"area":null},{"id":"2411.07858","title":"Verbosity $\\neq$ Veracity: Demystify Verbosity Compensation Behavior of Large Language Models","created":"2024-11-12","cited_by_count":5,"area":null},{"id":"2505.19060","title":"UNCERTAINTY-LINE: Length-Invariant Estimation of Uncertainty for Large Language Models","created":"2025-05-25","cited_by_count":5,"area":null},{"id":"2506.04203","title":"Cascadia: An Efficient Cascade Serving System for Large Language Models","created":"2025-06-04","cited_by_count":5,"area":"inference"},{"id":"2604.03904","title":"I-CALM: Incentivizing Confidence-Aware Abstention for LLM Selective Answering","created":"2026-04-05","cited_by_count":5,"area":null},{"id":"2406.14424","title":"CascadeServe: Unlocking Model Cascades for Inference Serving","created":"2024-06-20","cited_by_count":4,"area":null},{"id":"2502.01459","title":"Learning to Partially Defer for Sequences","created":"2025-02-03","cited_by_count":4,"area":null},{"id":"2502.12701","title":"Translate Smart, not Hard: Cascaded Translation Systems with Quality-Aware Deferral","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2506.14753","title":"Cost-Aware Routing for Efficient Text-To-Image Generation","created":"2025-06-17","cited_by_count":4,"area":"diffusion"},{"id":"2601.07006","title":"LLM Performance Predictors: Learning When to Escalate in Hybrid Human-AI Moderation Systems","created":"2026-01-11","cited_by_count":4,"area":null},{"id":"2605.06350","title":"Is Escalation Worth It? On the Depth of LLM Cascades","created":"2026-05-07","cited_by_count":4,"area":null},{"id":"2506.17254","title":"Near-Optimal Online Deployment and Routing for Streaming LLMs","created":"2025-06-08","cited_by_count":3,"area":null},{"id":"2510.01389","title":"INSIGHT: INference-time Sequence Introspection for Generating Help Triggers in Vision-Language-Action Models","created":"2025-10-01","cited_by_count":3,"area":"vla"},{"id":"2510.15346","title":"When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling","created":"2025-10-17","cited_by_count":3,"area":null},{"id":"2511.14275","title":"Let the Model Distribute Its Doubt: Confidence Estimation through Verbalized Probability Distribution","created":"2025-11-18","cited_by_count":3,"area":null},{"id":"2601.08064","title":"Calibration Is Not Enough: Evaluating Confidence Estimation Under Language Variations","created":"2026-01-12","cited_by_count":3,"area":null},{"id":"2602.11877","title":"Towards Fair and Comprehensive Evaluation of Routers in Collaborative LLM Systems","created":"2026-02-12","cited_by_count":3,"area":null},{"id":"2603.05432","title":"Ensembling Language Models with Sequential Monte Carlo","created":"2026-03-05","cited_by_count":3,"area":null},{"id":"2606.11512","title":"SAGE: Answer-Conditioned Uncertainty Targets for Verbal Uncertainty Alignment","created":"2026-06-09","cited_by_count":3,"area":"alignment"},{"id":"2607.23765","title":"WISERouter: LLM Routing with Workload Budget Constraint","created":"2026-07-26","cited_by_count":3,"area":null},{"id":"2609.32160","title":"Typed Decision Models: An Early Evidence Audit and Evaluation Checklist","created":"2026-09-26","cited_by_count":3,"area":null},{"id":"2411.01271","title":"Interacting Large Language Model Agents. Interpretable Models and Social Learning","created":"2024-11-02","cited_by_count":2,"area":"agents"},{"id":"2504.07247","title":"Resource-efficient Inference with Foundation Model Programs","created":"2025-04-09","cited_by_count":2,"area":null},{"id":"2504.19391","title":"Bi-directional Model Cascading with Proxy Confidence","created":"2025-04-27","cited_by_count":2,"area":null},{"id":"2512.02543","title":"Inference-Time Distillation: Cost-Efficient Agents Without Fine-Tuning or Manual Prompt Engineering","created":"2025-12-02","cited_by_count":2,"area":"agents"},{"id":"2601.22132","title":"Pay for Hints, Not Answers: LLM Shepherding for Cost-Efficient Inference","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2602.05182","title":"The Single-Multi Evolution Loop for Self-Improving Model Collaboration Systems","created":"2026-02-05","cited_by_count":2,"area":"synth"},{"id":"2602.05307","title":"MentorCollab: Large-to-Small Inference-Time Mentorship for Concise Reasoning in Language Models","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2604.22520","title":"RouteLMT: Learned Sample Routing for Hybrid LLM Translation Deployment","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2604.23333","title":"Process Supervision of Confidence Margin for Calibrated LLM Reasoning","created":"2026-04-25","cited_by_count":2,"area":"lr"},{"id":"2604.23577","title":"RouteNLP: Closed-Loop LLM Routing with Conformal Cascading and Distillation Co-Optimization","created":"2026-04-26","cited_by_count":2,"area":null},{"id":"2506.07448","title":"Extending Epistemic Uncertainty Beyond Parameters Would Assist in Designing Reliable LLMs","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2510.27017","title":"Kad: A Framework for Proxy-based Test-time Alignment with Knapsack Approximation Deferral","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2511.00620","title":"Certain but not Probable? Differentiating Certainty from Probability in LLM Token Outputs for Probabilistic Scenarios","created":"2025-11-01","cited_by_count":1,"area":null},{"id":"2512.16349","title":"Collaborative Edge-to-Server Inference for Vision-Language Models","created":"2025-12-18","cited_by_count":1,"area":"mllm"},{"id":"2603.24617","title":"Multi-LLM Query Optimization","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2604.12035","title":"When Does Visual Token Pruning Improve Calibration? The Role of Evidence Coverage in MLLMs","created":"2026-04-13","cited_by_count":1,"area":"mllm"},{"id":"2605.19557","title":"Density-Ratio Losses for Post-Hoc Learning to Defer","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2606.07392","title":"Online Pandora's Box for Contextual LLM Cascading","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2608.06171","title":"Routing Is Least Learnable Where It Is Most Valuable: Bounds on Representation Routing for Web Agents","created":"2026-08-06","cited_by_count":1,"area":"agents"},{"id":"2410.08388","title":"Responsible AI in NLP: GUS-Net Span-Level Bias Detection Dataset and Benchmark for Generalizations, Unfairness, and Stereotypes","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2410.11857","title":"LLMBridge: Reducing Costs to Access LLMs in a Prompt-Centric Internet","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2503.16511","title":"Token-Level Uncertainty-Aware Objective for Language Model Post-Training","created":"2025-03-15","cited_by_count":0,"area":"distill"},{"id":"2505.22752","title":"Climate Finance Bench","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2507.11352","title":"Foundation Models for Logistics: Toward Certifiable, Conversational Planning Interfaces","created":"2025-07-15","cited_by_count":0,"area":null},{"id":"2510.25412","title":"Serve Programs, Not Prompts","created":"2025-10-29","cited_by_count":0,"area":"inference"},{"id":"2602.12005","title":"LaCy: What Small Language Models Can and Should Learn is Not Just a Question of Loss","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.24787","title":"ReLope: KL-Regularized LoRA Probes for Multimodal LLM Routing","created":"2026-03-25","cited_by_count":0,"area":"mllm"},{"id":"2604.02230","title":"Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs","created":"2026-04-02","cited_by_count":0,"area":"lr"},{"id":"2604.19781","title":"Do Small Language Models Know When They're Wrong? Confidence-Based Cascade Scoring for Educational Assessment","created":"2026-03-29","cited_by_count":0,"area":null}],"next_cursor":"100"}