{"total":47,"rows":[{"id":"2504.02234","title":"LLM Social Simulations Are a Promising Research Method","created":"2025-04-03","cited_by_count":99,"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":"2503.03064","title":"Improving LLM-as-a-Judge Inference with the Judgment Distribution","created":"2025-03-04","cited_by_count":37,"area":null},{"id":"2501.04961","title":"Demystifying Domain-adaptive Post-training for Financial LLMs","created":"2025-01-09","cited_by_count":24,"area":null},{"id":"2603.13285","title":"Brittlebench: Quantifying LLM robustness via prompt sensitivity","created":"2026-02-27","cited_by_count":21,"area":null},{"id":"2512.10941","title":"Mull-Tokens: Modality-Agnostic Latent Thinking","created":"2025-12-11","cited_by_count":19,"area":null},{"id":"2505.17968","title":"Are Large Language Models Reliable AI Scientists? Assessing Reverse-Engineering of Black-Box Systems","created":"2025-05-23","cited_by_count":14,"area":null},{"id":"2502.16435","title":"Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs","created":"2025-02-23","cited_by_count":13,"area":null},{"id":"2603.20882","title":"RubricRAG: Towards Interpretable and Reliable LLM Evaluation via Domain Knowledge Retrieval for Rubric Generation","created":"2026-03-21","cited_by_count":11,"area":null},{"id":"2412.08258","title":"Large Language Models for Scholarly Ontology Generation: An Extensive Analysis in the Engineering Field","created":"2024-12-11","cited_by_count":10,"area":null},{"id":"2503.13401","title":"Levels of Analysis for Large Language Models","created":"2025-03-17","cited_by_count":10,"area":null},{"id":"2510.19687","title":"Are Large Language Models Sensitive to the Motives Behind Communication?","created":"2025-10-22","cited_by_count":8,"area":null},{"id":"2509.24216","title":"MoVa: Towards Generalizable Classification of Human Morals and Values","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2510.23182","title":"SI-Bench: Benchmarking Social Intelligence of Large Language Models in Human-to-Human Conversations","created":"2025-10-27","cited_by_count":7,"area":null},{"id":"2505.00147","title":"AdaptMI: Adaptive Skill-based In-context Math Instruction for Small Language Models","created":"2025-04-30","cited_by_count":5,"area":null},{"id":"2507.15851","title":"The Other Mind: How Language Models Exhibit Human Temporal Cognition","created":"2025-07-21","cited_by_count":5,"area":null},{"id":"2509.07370","title":"PersonaFuse: A Personality Activation-Driven Framework for Enhancing Human-LLM Interactions","created":"2025-09-09","cited_by_count":5,"area":null},{"id":"2504.04141","title":"Self-Adaptive Cognitive Debiasing for Large Language Models in Decision-Making","created":"2025-04-05","cited_by_count":4,"area":null},{"id":"2505.19025","title":"SQUiD: Synthesizing Relational Databases from Unstructured Text","created":"2025-05-25","cited_by_count":4,"area":null},{"id":"2509.16567","title":"V-CECE: Visual Counterfactual Explanations via Conceptual Edits","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2502.18791","title":"Can LLMs Help Uncover Insights about LLMs? A Large-Scale, Evolving Literature Analysis of Frontier LLMs","created":"2025-02-26","cited_by_count":3,"area":null},{"id":"2412.01340","title":"A 2-step Framework for Automated Literary Translation Evaluation: Its Promises and Pitfalls","created":"2024-12-02","cited_by_count":2,"area":null},{"id":"2412.17794","title":"Memory makes computation universal, remember?","created":"2024-12-23","cited_by_count":2,"area":null},{"id":"2503.24190","title":"Implicit In-Context Learning: Evidence from Artificial Language Experiments","created":"2025-03-31","cited_by_count":2,"area":null},{"id":"2504.03352","title":"StereoDetect: Detecting Stereotypes and Anti-stereotypes the Correct Way Using Social Psychological Underpinnings","created":"2025-04-04","cited_by_count":2,"area":null},{"id":"2509.16765","title":"The Sound of Syntax: Finetuning and Comprehensive Evaluation of Language Models for Speech Pathology","created":"2025-09-20","cited_by_count":2,"area":null},{"id":"2510.12699","title":"Generation Space Size: Understanding and Calibrating Open-Endedness of LLM Generations","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2511.06148","title":"Large Language Models Develop Novel Social Biases Through Adaptive Exploration","created":"2025-11-08","cited_by_count":2,"area":null},{"id":"2604.10027","title":"SinkTrack: Attention Sink based Context Anchoring for Large Language Models","created":"2026-04-11","cited_by_count":2,"area":null},{"id":"2508.04691","title":"Before Humans Join the Team: Diagnosing Coordination Failures in Healthcare Robot Team Simulation","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2508.18992","title":"Automatic Prompt Optimization with Prompt Distillation","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2510.23464","title":"Evaluating Large Language Models for Stance Detection on Financial Targets from SEC Filing Reports and Earnings Call Transcripts","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2512.05765","title":"AGI Requires a Coordination Layer on Top of Pattern Repositories","created":"2025-12-05","cited_by_count":1,"area":null},{"id":"2607.00672","title":"DART: Difficulty-Adaptive Routing for Zero-Shot Video Temporal Grounding","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2509.20805","title":"Few-Shot and Training-Free Review Generation via Conversational Prompting","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2510.21839","title":"Evaluating ChatGPT's Performance in Classifying Pneumonia from Chest X-Ray Images","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2603.28731","title":"SAGAI-MID: A Generative AI-Driven Middleware for Dynamic Runtime Interoperability","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.01652","title":"ThinknCheck: Grounded Claim Verification with Compact, Reasoning-Driven, and Interpretable Models","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2605.03858","title":"MCJudgeBench: A Benchmark for Constraint-Level Judge Evaluation in Multi-Constraint Instruction Following","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.14084","title":"CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.24267","title":"DRInQ: Evaluating Conversational Implicature with Controlled Context Variation","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.22496","title":"Enabling Cloud-Level Accuracy in Edge AI through IoT Data Preprocessing","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2607.18767","title":"Bounding Boxes to Improve Small Language Model Performance on Vision-Based Grading Tasks","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2607.19847","title":"Auto-Fill: Learning to Predict Missing Values Accurately with Specialist Language Models","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2609.21259","title":"CogGym: Towards Large-Scale Comparative Evaluation of Human and Machine Cognition","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.23592","title":"Collapse, Not Complexity: Failure-Conditioned Decomposition Repair for End-to-End Document Parsing","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2610.13999","title":"SemTree: Judge-Aware Semantic Decision Trees for Inspectable and Repairable Rule Decisions","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}