{"total":77,"rows":[{"id":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894,"area":"lr"},{"id":"2205.00363","title":"Visual Spatial Reasoning","created":"2022-04-30","cited_by_count":293,"area":"lr"},{"id":"2506.09965","title":"Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing","created":"2025-06-11","cited_by_count":136,"area":"lr"},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2502.19187","title":"BIG-Bench Extra Hard","created":"2025-02-26","cited_by_count":125,"area":"lr"},{"id":"2406.14852","title":"Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models","created":"2024-06-21","cited_by_count":113,"area":"lr"},{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2402.11443","title":"Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation","created":"2024-02-18","cited_by_count":75,"area":"agents"},{"id":"2204.08292","title":"StepGame: A New Benchmark for Robust Multi-Hop Spatial Reasoning in Texts","created":"2022-04-18","cited_by_count":68,"area":"lr"},{"id":"2310.14540","title":"Evaluating Spatial Understanding of Large Language Models","created":"2023-10-23","cited_by_count":66,"area":null},{"id":"2404.03622","title":"Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models","created":"2024-04-04","cited_by_count":66,"area":"lr"},{"id":"2406.14491","title":"Instruction Pre-Training: Language Models are Supervised Multitask Learners","created":"2024-06-20","cited_by_count":63,"area":null},{"id":"2410.17385","title":"Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities","created":"2024-10-22","cited_by_count":59,"area":"mllm"},{"id":"2406.02537","title":"TopViewRS: Vision-Language Models as Top-View Spatial Reasoners","created":"2024-06-04","cited_by_count":49,"area":"lr"},{"id":"2203.08075","title":"Things not Written in Text: Exploring Spatial Commonsense from Visual Signals","created":"2022-03-15","cited_by_count":41,"area":null},{"id":"2310.00836","title":"Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models","created":"2023-10-02","cited_by_count":35,"area":"lr"},{"id":"2210.16952","title":"Transfer Learning with Synthetic Corpora for Spatial Role Labeling and Reasoning","created":"2022-10-30","cited_by_count":34,"area":"lr"},{"id":"2410.16162","title":"Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning","created":"2024-10-21","cited_by_count":34,"area":"lr"},{"id":"2401.03991","title":"Advancing Spatial Reasoning in Large Language Models: An In-Depth Evaluation and Enhancement Using the StepGame Benchmark","created":"2024-01-08","cited_by_count":27,"area":"lr"},{"id":"2502.03214","title":"iVISPAR -- An Interactive Visual-Spatial Reasoning Benchmark for VLMs","created":"2025-02-05","cited_by_count":25,"area":"lr"},{"id":"2506.21876","title":"Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation","created":"2025-06-27","cited_by_count":24,"area":"wm"},{"id":"2504.15037","title":"Scaling and Beyond: Advancing Spatial Reasoning in MLLMs Requires New Recipes","created":"2025-04-21","cited_by_count":22,"area":"lr"},{"id":"2109.04947","title":"Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding","created":"2021-09-10","cited_by_count":19,"area":null},{"id":"2310.12342","title":"Eliminating Reasoning via Inferring with Planning: A New Framework to Guide LLMs' Non-linear Thinking","created":"2023-10-18","cited_by_count":19,"area":"lr"},{"id":"2405.03146","title":"Quantifying the Capabilities of LLMs across Scale and Precision","created":"2024-05-06","cited_by_count":19,"area":null},{"id":"2602.07055","title":"Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?","created":"2026-02-04","cited_by_count":19,"area":null},{"id":"2405.15064","title":"Reframing Spatial Reasoning Evaluation in Language Models: A Real-World Simulation Benchmark for Qualitative Reasoning","created":"2024-05-23","cited_by_count":17,"area":"lr"},{"id":"2408.16662","title":"Space3D-Bench: Spatial 3D Question Answering Benchmark","created":"2024-08-29","cited_by_count":17,"area":null},{"id":"2511.07403","title":"SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards","created":"2025-11-10","cited_by_count":16,"area":"lr"},{"id":"2406.08787","title":"A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practices","created":"2024-06-13","cited_by_count":15,"area":null},{"id":"2108.12370","title":"DomiKnowS: A Library for Integration of Symbolic Domain Knowledge in Deep Learning","created":"2021-08-27","cited_by_count":12,"area":null},{"id":"2406.19065","title":"STBench: Assessing the Ability of Large Language Models in Spatio-Temporal Analysis","created":"2024-06-27","cited_by_count":11,"area":null},{"id":"2302.10914","title":"GLUECons: A Generic Benchmark for Learning Under Constraints","created":"2023-02-16","cited_by_count":9,"area":null},{"id":"2503.02003","title":"HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs","created":"2025-03-03","cited_by_count":9,"area":"lr"},{"id":"2409.12437","title":"Enhancing Logical Reasoning in Large Language Models through Graph-based Synthetic Data","created":"2024-09-19","cited_by_count":8,"area":"lr"},{"id":"2604.02580","title":"VoxelCodeBench: Benchmarking 3D World Modeling Through Code Generation","created":"2026-04-02","cited_by_count":8,"area":"wm"},{"id":"2205.09229","title":"PromptDA: Label-guided Data Augmentation for Prompt-based Few-shot Learners","created":"2022-05-18","cited_by_count":7,"area":null},{"id":"2303.12810","title":"Are LLMs the Master of All Trades? : Exploring Domain-Agnostic Reasoning Skills of LLMs","created":"2023-03-22","cited_by_count":7,"area":"lr"},{"id":"2407.01892","title":"GRASP: A Grid-Based Benchmark for Evaluating Commonsense Spatial Reasoning","created":"2024-07-02","cited_by_count":7,"area":"lr"},{"id":"2208.08010","title":"ShortcutLens: A Visual Analytics Approach for Exploring Shortcuts in Natural Language Understanding Dataset","created":"2022-08-17","cited_by_count":6,"area":null},{"id":"2305.10276","title":"Chain-of-Symbol Prompting Elicits Planning in Large Langauge Models","created":"2023-05-17","cited_by_count":6,"area":null},{"id":"2311.11477","title":"What's left can't be right -- The remaining positional incompetence of contrastive vision-language models","created":"2023-11-20","cited_by_count":6,"area":"mllm"},{"id":"2310.15010","title":"Statistical Depth for Ranking and Characterizing Transformer-Based Text Embeddings","created":"2023-10-23","cited_by_count":5,"area":null},{"id":"2406.04566","title":"SpaRC and SpaRP: Spatial Reasoning Characterization and Path Generation for Understanding Spatial Reasoning Capability of Large Language Models","created":"2024-06-07","cited_by_count":5,"area":"lr"},{"id":"2505.17572","title":"USTBench: Benchmarking and Dissecting Spatiotemporal Reasoning of LLMs as Urban Agents","created":"2025-05-23","cited_by_count":5,"area":"lr"},{"id":"2508.01984","title":"IMoRe: Implicit Program-Guided Reasoning for Human Motion Q&A","created":"2025-08-04","cited_by_count":5,"area":null},{"id":"2111.10756","title":"TraVLR: Now You See It, Now You Don't! A Bimodal Dataset for Evaluating Visio-Linguistic Reasoning","created":"2021-11-21","cited_by_count":4,"area":null},{"id":"2301.08913","title":"Unifying Structure Reasoning and Language Model Pre-training for Complex Reasoning","created":"2023-01-21","cited_by_count":4,"area":"lr"},{"id":"2307.02269","title":"SpaceNLI: Evaluating the Consistency of Predicting Inferences in Space","created":"2023-07-05","cited_by_count":4,"area":null},{"id":"2604.00558","title":"STAR: Mitigating Cascading Errors in Spatial Reasoning via Turn-point Alignment and Segment-level DPO","created":"2026-04-01","cited_by_count":4,"area":"lr"},{"id":"2201.06230","title":"Generalizable Neuro-symbolic Systems for Commonsense Question Answering","created":"2022-01-17","cited_by_count":3,"area":null},{"id":"2310.12557","title":"DepWiGNN: A Depth-wise Graph Neural Network for Multi-hop Spatial Reasoning in Text","created":"2023-10-19","cited_by_count":3,"area":"lr"},{"id":"2412.16599","title":"Do Multimodal Language Models Really Understand Direction? A Benchmark for Compass Direction Reasoning","created":"2024-12-21","cited_by_count":3,"area":"lr"},{"id":"2503.06218","title":"SCoRE: Benchmarking Long-Chain Reasoning in Commonsense Scenarios","created":"2025-03-08","cited_by_count":3,"area":"lr"},{"id":"2503.07323","title":"Navigating Motion Agents in Dynamic and Cluttered Environments through LLM Reasoning","created":"2025-03-10","cited_by_count":2,"area":"lr"},{"id":"2509.16866","title":"seqBench: A Tunable Benchmark to Quantify Sequential Reasoning Limits of LLMs","created":"2025-09-21","cited_by_count":2,"area":"lr"},{"id":"2603.20133","title":"Reasoning Gets Harder for LLMs Inside A Dialogue","created":"2026-03-20","cited_by_count":2,"area":"lr"},{"id":"2403.13666","title":"Grounding Spatial Relations in Text-Only Language Models","created":"2024-03-20","cited_by_count":1,"area":null},{"id":"2410.15312","title":"Synergistic Dual Spatial-aware Generation of Image-to-Text and Text-to-Image","created":"2024-10-20","cited_by_count":1,"area":null},{"id":"2505.20874","title":"Can LLMs Learn to Map the World from Local Descriptions?","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2507.12059","title":"Evaluating the Ability of Large Language Models to Reason about Cardinal Directions, Revisited","created":"2025-07-16","cited_by_count":1,"area":"lr"},{"id":"2508.08821","title":"3DFroMLLM: 3D Prototype Generation only from Pretrained Multimodal LLMs","created":"2025-08-12","cited_by_count":1,"area":"mllm"},{"id":"2508.11163","title":"MobQA: A Benchmark Dataset for Semantic Understanding of Human Mobility Data through Question Answering","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2508.18646","title":"Beyond Benchmarks: LLM Evaluation with an Anthropomorphic and Lifecycle-oriented Roadmap","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2509.23452","title":"FoR-SALE: Frame of Reference-guided Spatial Adjustment in LLM-based Diffusion Editing","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2604.06725","title":"Enhancing MLLM Spatial Understanding via Active 3D Scene Exploration for Multi-Perspective Reasoning","created":"2026-04-08","cited_by_count":1,"area":"lr"},{"id":"2604.09338","title":"Mind the Gap Between Spatial Reasoning and Acting! Step-by-Step Evaluation of Agents With Spatial-Gym","created":"2026-04-10","cited_by_count":1,"area":"lr"},{"id":"2606.31285","title":"Spatial Reasoning via Modality Switching Between Language and Symbolic Representations","created":"2026-06-30","cited_by_count":1,"area":"lr"},{"id":"2603.17832","title":"Text-to-Stage: Spatial Layouts from Long-form Narratives","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2604.14641","title":"Learning to Draw ASCII Improves Spatial Reasoning in Language Models","created":"2026-04-16","cited_by_count":0,"area":"lr"},{"id":"2607.03261","title":"OmniLayout: A Schematic-Coupled Multimodal Benchmark for Constraint-Aware Geometric Reasoning in PCB Layout","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2608.16011","title":"ReRef-3D: A Benchmark for Spatial Referring Expression-Guided 3D Scene Rearrangement","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.29431","title":"Evaluating the Semantic Specificity of Representation Steering in Language Models","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2609.26060","title":"ChainUQ: Reasoning Consistency-Aware Uncertainty Quantification for Large Language Models","created":"2026-08-08","cited_by_count":0,"area":"lr"},{"id":"2609.35486","title":"Who Is Left of Whom? Tracing Spatial Evidence and Role Binding in Relative-Position Reasoning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.15258","title":"Sequent-Prover: Training Agents for Formal, Checkable SMT-based Reasoning","created":"2026-10-11","cited_by_count":0,"area":"agents"},{"id":"2610.19443","title":"More Than Seeing: Vision as Scalable Anchors in Native Multimodal Pre-Training","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}