{"total":68,"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":"2209.00840","title":"FOLIO: Natural Language Reasoning with First-Order Logic","created":"2022-09-02","cited_by_count":235,"area":"lr"},{"id":"2502.19187","title":"BIG-Bench Extra Hard","created":"2025-02-26","cited_by_count":125,"area":"lr"},{"id":"2306.04618","title":"Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations","created":"2023-06-07","cited_by_count":97,"area":null},{"id":"2402.17834","title":"Stable LM 2 1.6B Technical Report","created":"2024-02-27","cited_by_count":90,"area":null},{"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":"2307.07696","title":"Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Text","created":"2023-07-15","cited_by_count":59,"area":"lr"},{"id":"2406.02537","title":"TopViewRS: Vision-Language Models as Top-View Spatial Reasoners","created":"2024-06-04","cited_by_count":49,"area":"lr"},{"id":"2405.14394","title":"Instruction Tuning With Loss Over Instructions","created":"2024-05-23","cited_by_count":40,"area":null},{"id":"2309.05173","title":"DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning","created":"2023-09-11","cited_by_count":35,"area":null},{"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":"2406.13948","title":"CityGPT: Empowering Urban Spatial Cognition of Large Language Models","created":"2024-06-20","cited_by_count":30,"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":"2305.01711","title":"Don't Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner","created":"2023-05-02","cited_by_count":23,"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":"2305.13002","title":"Rethinking Semi-supervised Learning with Language Models","created":"2023-05-22","cited_by_count":17,"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":"2405.15302","title":"Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism","created":"2024-05-24","cited_by_count":15,"area":"lr"},{"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":"2403.05330","title":"Consecutive Batch Model Editing with HooK Layers","created":"2024-03-08","cited_by_count":10,"area":null},{"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":"2305.13179","title":"Teaching Probabilistic Logical Reasoning to Transformers","created":"2023-05-22","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":"2511.18450","title":"ORIGAMISPACE: Benchmarking Multimodal LLMs in Multi-Step Spatial Reasoning with Mathematical Constraints","created":"2025-11-23","cited_by_count":7,"area":"lr"},{"id":"2411.18564","title":"Dspy-based Neural-Symbolic Pipeline to Enhance Spatial Reasoning in LLMs","created":"2024-11-27","cited_by_count":6,"area":"lr"},{"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":"2407.12734","title":"A LLM Benchmark based on the Minecraft Builder Dialog Agent Task","created":"2024-07-17","cited_by_count":4,"area":"agents"},{"id":"2508.03366","title":"A Comparative Study of Neurosymbolic AI Approaches to Interpretable Logical Reasoning","created":"2025-08-05","cited_by_count":4,"area":"lr"},{"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":"2306.01266","title":"Self Contrastive Learning for Session-based Recommendation","created":"2023-06-02","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":"2406.14035","title":"Using Game Play to Investigate Multimodal and Conversational Grounding in Large Multimodal Models","created":"2024-06-20","cited_by_count":3,"area":"mllm"},{"id":"2503.05439","title":"An Empirical Study of Conformal Prediction in LLM with ASP Scaffolds for Robust Reasoning","created":"2025-03-07","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":"2306.07664","title":"Rethink the Effectiveness of Text Data Augmentation: An Empirical Analysis","created":"2023-06-13","cited_by_count":2,"area":"lr"},{"id":"2406.01012","title":"Attention-based Iterative Decomposition for Tensor Product Representation","created":"2024-06-03","cited_by_count":2,"area":null},{"id":"2603.03002","title":"SpatialText: A Pure-Text Cognitive Benchmark for Spatial Understanding in Large Language Models","created":"2026-03-03","cited_by_count":2,"area":"lr"},{"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":"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":"2511.02627","title":"DecompSR: A dataset for decomposed analyses of compositional multihop spatial reasoning","created":"2025-11-04","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":"2604.15294","title":"How Do LLMs and VLMs Understand Viewpoint Rotation Without Vision? An Interpretability Study","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2605.31558","title":"Positional versus Symbolic Attention Heads: Learning Dynamics, RoPE Geometry, and Length Generalization","created":"2026-05-29","cited_by_count":1,"area":null},{"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":"2210.02535","title":"Attention-based Ingredient Phrase Parser","created":"2022-10-05","cited_by_count":0,"area":null},{"id":"2306.12387","title":"Solving Dialogue Grounding Embodied Task in a Simulated Environment using Further Masked Language Modeling","created":"2023-06-21","cited_by_count":0,"area":null},{"id":"2310.09651","title":"Lexical Entrainment for Conversational Systems","created":"2023-10-14","cited_by_count":0,"area":null},{"id":"2402.05440","title":"Improving Agent Interactions in Virtual Environments with Language Models","created":"2024-02-08","cited_by_count":0,"area":"agents"},{"id":"2406.06976","title":"Discrete Dictionary-based Decomposition Layer for Structured Representation Learning","created":"2024-06-11","cited_by_count":0,"area":null},{"id":"2603.17333","title":"Grid Spatial Understanding: A Dataset for Textual Spatial Reasoning over Grids, Embodied Settings, and Coordinate Structures","created":"2026-03-18","cited_by_count":0,"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":"2606.19788","title":"CombEval: A Framework for Evaluating Combinatorial Counting in Large Language Models","created":"2026-06-18","cited_by_count":0,"area":null},{"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":"2608.07411","title":"GeoBenchLLM: A Comprehensive Benchmark for Evaluating LLMs on Geo-Related Tasks","created":"2026-08-07","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":"2608.25623","title":"Using profiles of cognitive capability to assess AI suitability for workplace tasks","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.21493","title":"PolyBridgeBench: Benchmarking Multimodal LLMs for Physics-Grounded Bridge Design","created":"2026-09-18","cited_by_count":0,"area":"mllm"},{"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":"2610.05114","title":"Belief-Trajectory Energy: Measuring the Path to a Prediction","created":"2026-10-04","cited_by_count":0,"area":null},{"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}