{"total":51,"rows":[{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841,"area":null},{"id":"2210.02406","title":"Decomposed Prompting: A Modular Approach for Solving Complex Tasks","created":"2022-10-05","cited_by_count":558,"area":null},{"id":"2303.17491","title":"Language Models can Solve Computer Tasks","created":"2023-03-30","cited_by_count":372,"area":null},{"id":"2406.11695","title":"Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs","created":"2024-06-17","cited_by_count":291,"area":null},{"id":"2302.14838","title":"EvoPrompting: Language Models for Code-Level Neural Architecture Search","created":"2023-02-28","cited_by_count":131,"area":null},{"id":"2212.06094","title":"Prompting Is Programming: A Query Language for Large Language Models","created":"2022-12-12","cited_by_count":110,"area":null},{"id":"2310.15123","title":"Branch-Solve-Merge Improves Large Language Model Evaluation and Generation","created":"2023-10-23","cited_by_count":106,"area":null},{"id":"2305.08844","title":"RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs","created":"2023-05-15","cited_by_count":105,"area":null},{"id":"2306.00937","title":"STEVE-1: A Generative Model for Text-to-Behavior in Minecraft","created":"2023-06-01","cited_by_count":97,"area":null},{"id":"2310.04363","title":"Amortizing intractable inference in large language models","created":"2023-10-06","cited_by_count":97,"area":null},{"id":"2208.11663","title":"PEER: A Collaborative Language Model","created":"2022-08-24","cited_by_count":86,"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":"2304.00612","title":"Eight Things to Know about Large Language Models","created":"2023-04-02","cited_by_count":73,"area":null},{"id":"2403.11322","title":"StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows","created":"2024-03-17","cited_by_count":65,"area":null},{"id":"2305.19234","title":"Grammar Prompting for Domain-Specific Language Generation with Large Language Models","created":"2023-05-30","cited_by_count":58,"area":null},{"id":"2301.04589","title":"Memory Augmented Large Language Models are Computationally Universal","created":"2023-01-10","cited_by_count":47,"area":null},{"id":"2310.09139","title":"The Consensus Game: Language Model Generation via Equilibrium Search","created":"2023-10-13","cited_by_count":36,"area":null},{"id":"2306.12509","title":"Joint Prompt Optimization of Stacked LLMs using Variational Inference","created":"2023-06-21","cited_by_count":32,"area":null},{"id":"2210.02498","title":"Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model","created":"2022-10-05","cited_by_count":20,"area":null},{"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":"2210.02506","title":"Large Language Models are Pretty Good Zero-Shot Video Game Bug Detectors","created":"2022-10-05","cited_by_count":14,"area":null},{"id":"2506.09669","title":"Query-Level Uncertainty in Large Language Models","created":"2025-06-11","cited_by_count":14,"area":null},{"id":"2212.06295","title":"Despite \"super-human\" performance, current LLMs are unsuited for decisions about ethics and safety","created":"2022-12-13","cited_by_count":13,"area":null},{"id":"2305.18498","title":"ANPL: Towards Natural Programming with Interactive Decomposition","created":"2023-05-29","cited_by_count":13,"area":null},{"id":"2402.19471","title":"Loose LIPS Sink Ships: Asking Questions in Battleship with Language-Informed Program Sampling","created":"2024-02-29","cited_by_count":12,"area":null},{"id":"2302.02801","title":"LaMPP: Language Models as Probabilistic Priors for Perception and Action","created":"2023-02-03","cited_by_count":11,"area":null},{"id":"2305.05364","title":"Large Language Model Programs","created":"2023-05-09","cited_by_count":11,"area":null},{"id":"2309.11197","title":"The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute","created":"2023-09-20","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":"2503.13505","title":"Ensemble Learning for Large Language Models in Text and Code Generation: A Survey","created":"2025-03-13","cited_by_count":9,"area":null},{"id":"2407.08642","title":"Towards Building Specialized Generalist AI with System 1 and System 2 Fusion","created":"2024-07-11","cited_by_count":8,"area":null},{"id":"2211.03277","title":"Complex Reading Comprehension Through Question Decomposition","created":"2022-11-07","cited_by_count":7,"area":null},{"id":"2310.04680","title":"The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning","created":"2023-10-07","cited_by_count":7,"area":null},{"id":"2504.12988","title":"Why Ask One When You Can Ask $k$? Learning-to-Defer to the Top-$k$ Experts","created":"2025-04-17","cited_by_count":7,"area":null},{"id":"2407.06146","title":"Using Grammar Masking to Ensure Syntactic Validity in LLM-based Modeling Tasks","created":"2024-07-08","cited_by_count":6,"area":null},{"id":"2307.00660","title":"Minimum Levels of Interpretability for Artificial Moral Agents","created":"2023-07-02","cited_by_count":5,"area":null},{"id":"2408.08624","title":"RealMedQA: A pilot biomedical question answering dataset containing realistic clinical questions","created":"2024-08-16","cited_by_count":5,"area":null},{"id":"2310.01441","title":"UPAR: A Kantian-Inspired Prompting Framework for Enhancing Large Language Model Capabilities","created":"2023-09-30","cited_by_count":3,"area":null},{"id":"2311.04954","title":"Prompt Sketching for Large Language Models","created":"2023-11-08","cited_by_count":3,"area":null},{"id":"2606.07812","title":"Scaling Participation in Modular AI Systems","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2603.07101","title":"Grounding Machine Creativity in Game Design Knowledge Representations: Empirical Probing of LLM-Based Executable Synthesis of Goal Playable Patterns under Structural Constraints","created":"2026-03-07","cited_by_count":1,"area":null},{"id":"2605.19557","title":"Density-Ratio Losses for Post-Hoc Learning to Defer","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2407.18945","title":"CogNarr Ecosystem: Facilitating Group Cognition at Scale","created":"2024-07-11","cited_by_count":0,"area":null},{"id":"2512.23049","title":"Accelerating Language Model Workflows with Prompt Choreography","created":"2025-12-28","cited_by_count":0,"area":null},{"id":"2601.02365","title":"FUSE : Failure-aware Usage of Subagent Evidence for MultiModal Search and Recommendation","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2604.14531","title":"TRACER: Trace-Based Adaptive Cost-Efficient Routing for LLM Classification","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.18245","title":"Correction and Corruption: A Two-Rate View of Error Flow in LLM Protocols","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.01710","title":"Model Routing as a Trust Problem: Route Receipts for Adaptive AI Systems","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2607.25018","title":"Conformal Cascade: Distribution-Free Accuracy Guarantees for Multi-Tier LLM Inference","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2609.23716","title":"STEVE: Stabilizing Textual Gradient-Based Prompt Optimization via Error-Driven Refinement and Regularized Verification","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2610.13276","title":"CopRoute: Dependence-Aware Conformal Routing for Language Models","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}