{"total":95,"rows":[{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807,"area":"lr"},{"id":"2211.12588","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","created":"2022-11-22","cited_by_count":1076,"area":"lr"},{"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":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596,"area":"lr"},{"id":"2309.05653","title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","created":"2023-09-11","cited_by_count":487,"area":null},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403,"area":"lr"},{"id":"2309.01431","title":"Benchmarking Large Language Models in Retrieval-Augmented Generation","created":"2023-09-04","cited_by_count":312,"area":"rag"},{"id":"2402.12875","title":"Chain of Thought Empowers Transformers to Solve Inherently Serial Problems","created":"2024-02-20","cited_by_count":260,"area":"lr"},{"id":"2212.10450","title":"Is GPT-3 a Good Data Annotator?","created":"2022-12-20","cited_by_count":208,"area":null},{"id":"2302.12246","title":"Active Prompting with Chain-of-Thought for Large Language Models","created":"2023-02-23","cited_by_count":154,"area":"lr"},{"id":"2212.06800","title":"Diverse Demonstrations Improve In-context Compositional Generalization","created":"2022-12-13","cited_by_count":139,"area":null},{"id":"2305.18703","title":"Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey","created":"2023-05-30","cited_by_count":135,"area":null},{"id":"2306.03872","title":"Deductive Verification of Chain-of-Thought Reasoning","created":"2023-06-06","cited_by_count":124,"area":"lr"},{"id":"2307.03381","title":"Teaching Arithmetic to Small Transformers","created":"2023-07-07","cited_by_count":123,"area":null},{"id":"2210.06710","title":"Large Language Models are few(1)-shot Table Reasoners","created":"2022-10-13","cited_by_count":116,"area":"lr"},{"id":"2402.03620","title":"Self-Discover: Large Language Models Self-Compose Reasoning Structures","created":"2024-02-06","cited_by_count":110,"area":"lr"},{"id":"2310.01714","title":"Large Language Models as Analogical Reasoners","created":"2023-10-03","cited_by_count":107,"area":"lr"},{"id":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96,"area":"alignment"},{"id":"2308.10379","title":"Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models","created":"2023-08-20","cited_by_count":92,"area":"lr"},{"id":"2401.12973","title":"In-Context Language Learning: Architectures and Algorithms","created":"2024-01-23","cited_by_count":89,"area":null},{"id":"2301.12810","title":"Crawling the Internal Knowledge-Base of Language Models","created":"2023-01-30","cited_by_count":85,"area":null},{"id":"2401.12242","title":"BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models","created":"2024-01-20","cited_by_count":80,"area":"lr"},{"id":"2401.11624","title":"In-context Learning with Retrieved Demonstrations for Language Models: A Survey","created":"2024-01-21","cited_by_count":70,"area":null},{"id":"2401.14295","title":"Demystifying Chains, Trees, and Graphs of Thoughts","created":"2024-01-25","cited_by_count":63,"area":"lr"},{"id":"2310.04959","title":"Towards Better Chain-of-Thought Prompting Strategies: A Survey","created":"2023-10-08","cited_by_count":62,"area":"lr"},{"id":"2302.00618","title":"Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models","created":"2023-02-01","cited_by_count":61,"area":"lr"},{"id":"2305.14907","title":"Coverage-based Example Selection for In-Context Learning","created":"2023-05-24","cited_by_count":59,"area":null},{"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":"2210.11399","title":"Transcending Scaling Laws with 0.1% Extra Compute","created":"2022-10-20","cited_by_count":57,"area":null},{"id":"2305.04835","title":"How Do In-Context Examples Affect Compositional Generalization?","created":"2023-05-08","cited_by_count":51,"area":"lr"},{"id":"2301.12868","title":"On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codex","created":"2023-01-30","cited_by_count":41,"area":null},{"id":"2401.07950","title":"SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models","created":"2024-01-15","cited_by_count":39,"area":null},{"id":"2403.05110","title":"Efficient Data Collection for Robotic Manipulation via Compositional Generalization","created":"2024-03-08","cited_by_count":37,"area":null},{"id":"2303.14617","title":"Neural Graph Reasoning: Complex Logical Query Answering Meets Graph Databases","created":"2023-03-26","cited_by_count":35,"area":"lr"},{"id":"2305.11938","title":"XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages","created":"2023-05-19","cited_by_count":34,"area":null},{"id":"2310.07096","title":"Sparse Universal Transformer","created":"2023-10-11","cited_by_count":32,"area":"moe"},{"id":"2410.08047","title":"Divide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical Reasoning","created":"2024-10-10","cited_by_count":27,"area":"lr"},{"id":"2303.13716","title":"ReCOGS: How Incidental Details of a Logical Form Overshadow an Evaluation of Semantic Interpretation","created":"2023-03-24","cited_by_count":24,"area":null},{"id":"2311.18751","title":"Exposing Limitations of Language Model Agents in Sequential-Task Compositions on the Web","created":"2023-11-30","cited_by_count":24,"area":"agents"},{"id":"2307.13883","title":"ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis","created":"2023-07-26","cited_by_count":17,"area":null},{"id":"2406.17534","title":"Retrieval-style In-Context Learning for Few-shot Hierarchical Text Classification","created":"2024-06-25","cited_by_count":16,"area":null},{"id":"2301.01751","title":"Iterated Decomposition: Improving Science Q&A by Supervising Reasoning Processes","created":"2023-01-04","cited_by_count":15,"area":"lr"},{"id":"2402.13415","title":"Structure Guided Prompt: Instructing Large Language Model in Multi-Step Reasoning by Exploring Graph Structure of the Text","created":"2024-02-20","cited_by_count":14,"area":"lr"},{"id":"2402.05785","title":"Limits of Transformer Language Models on Learning to Compose Algorithms","created":"2024-02-08","cited_by_count":13,"area":null},{"id":"2210.01603","title":"Neural-Symbolic Recursive Machine for Systematic Generalization","created":"2022-10-04","cited_by_count":12,"area":null},{"id":"2410.16719","title":"Progressive Compositionality in Text-to-Image Generative Models","created":"2024-10-22","cited_by_count":12,"area":"diffusion"},{"id":"2306.04347","title":"World Models for Math Story Problems","created":"2023-06-07","cited_by_count":11,"area":null},{"id":"2311.07850","title":"Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQA","created":"2023-11-14","cited_by_count":11,"area":null},{"id":"2305.08677","title":"Natural Language Decomposition and Interpretation of Complex Utterances","created":"2023-05-15","cited_by_count":10,"area":null},{"id":"2405.06410","title":"Potential and Limitations of LLMs in Capturing Structured Semantics: A Case Study on SRL","created":"2024-05-10","cited_by_count":10,"area":null},{"id":"2410.22296","title":"Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks","created":"2024-10-29","cited_by_count":10,"area":null},{"id":"2405.15164","title":"From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks","created":"2024-05-24","cited_by_count":7,"area":null},{"id":"2406.11403","title":"Multimodal Structured Generation: CVPR's 2nd MMFM Challenge Technical Report","created":"2024-06-17","cited_by_count":7,"area":null},{"id":"2212.10815","title":"ZEROTOP: Zero-Shot Task-Oriented Semantic Parsing using Large Language Models","created":"2022-12-21","cited_by_count":6,"area":null},{"id":"2310.05074","title":"DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models","created":"2023-10-08","cited_by_count":6,"area":"lr"},{"id":"2311.09606","title":"GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks","created":"2023-11-16","cited_by_count":6,"area":null},{"id":"2401.13849","title":"TPD: Enhancing Student Language Model Reasoning via Principle Discovery and Guidance","created":"2024-01-24","cited_by_count":6,"area":"lr"},{"id":"2406.01045","title":"Decompose, Enrich, and Extract! Schema-aware Event Extraction using LLMs","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2407.21060","title":"Using Large Language Models for the Interpretation of Building Regulations","created":"2024-07-26","cited_by_count":6,"area":null},{"id":"2410.19000","title":"Make LLMs better zero-shot reasoners: Structure-orientated autonomous reasoning","created":"2024-10-18","cited_by_count":6,"area":"lr"},{"id":"2604.27707","title":"Contextual Agentic Memory is a Memo, Not True Memory","created":"2026-04-30","cited_by_count":6,"area":"rag"},{"id":"2305.07789","title":"HPE:Answering Complex Questions over Text by Hybrid Question Parsing and Execution","created":"2023-05-12","cited_by_count":5,"area":null},{"id":"2305.16954","title":"Compositional Generalization without Trees using Multiset Tagging and Latent Permutations","created":"2023-05-26","cited_by_count":5,"area":null},{"id":"2405.02350","title":"What makes Models Compositional? A Theoretical View: With Supplement","created":"2024-05-02","cited_by_count":5,"area":null},{"id":"2509.16590","title":"Question Answering with LLMs and Learning from Answer Sets","created":"2025-09-20","cited_by_count":4,"area":"lr"},{"id":"2310.18358","title":"A Communication Theory Perspective on Prompting Engineering Methods for Large Language Models","created":"2023-10-24","cited_by_count":3,"area":null},{"id":"2501.01473","title":"Unraveling Indirect In-Context Learning Using Influence Functions","created":"2025-01-01","cited_by_count":3,"area":null},{"id":"2505.22635","title":"Learning Composable Chains-of-Thought","created":"2025-05-28","cited_by_count":3,"area":"lr"},{"id":"2512.00319","title":"RL-Struct: A Lightweight Reinforcement Learning Framework for Reliable Structured Output in LLMs","created":"2025-11-29","cited_by_count":3,"area":null},{"id":"2512.07608","title":"Metric-Fair Prompting: Treating Similar Samples Similarly","created":"2025-12-08","cited_by_count":3,"area":null},{"id":"2305.04346","title":"Laziness Is a Virtue When It Comes to Compositionality in Neural Semantic Parsing","created":"2023-05-07","cited_by_count":2,"area":null},{"id":"2307.10799","title":"Layer-wise Representation Fusion for Compositional Generalization","created":"2023-07-20","cited_by_count":2,"area":null},{"id":"2501.05662","title":"Cascaded Self-Evaluation Augmented Training for Lightweight Multimodal LLMs","created":"2025-01-10","cited_by_count":2,"area":"lr"},{"id":"2510.03223","title":"Attention-Aligned Reasoning for Large Language Models","created":"2025-10-03","cited_by_count":2,"area":"lr"},{"id":"2305.14750","title":"Mastering the ABCDs of Complex Questions: Answer-Based Claim Decomposition for Fine-grained Self-Evaluation","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2309.06550","title":"Synthetic Text Generation using Hypergraph Representations","created":"2023-09-06","cited_by_count":1,"area":null},{"id":"2309.12294","title":"Reranking for Natural Language Generation from Logical Forms: A Study based on Large Language Models","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2404.13077","title":"Improving the Capabilities of Large Language Model Based Marketing Analytics Copilots With Semantic Search And Fine-Tuning","created":"2024-04-16","cited_by_count":1,"area":null},{"id":"2406.02642","title":"E-ICL: Enhancing Fine-Grained Emotion Recognition through the Lens of Prototype Theory","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2407.13419","title":"From Words to Worlds: Compositionality for Cognitive Architectures","created":"2024-07-18","cited_by_count":1,"area":null},{"id":"2502.20834","title":"Learning to Substitute Components for Compositional Generalization","created":"2025-02-28","cited_by_count":1,"area":null},{"id":"2602.16512","title":"Framework of Thoughts: A Foundation Framework for Dynamic and Optimized Reasoning based on Chains, Trees, and Graphs","created":"2026-02-18","cited_by_count":1,"area":"lr"},{"id":"2604.25166","title":"Training Transformers as a Universal Computer","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2304.11473","title":"(Vector) Space is Not the Final Frontier: Product Search as Program Synthesis","created":"2023-04-22","cited_by_count":0,"area":null},{"id":"2305.14600","title":"Learning Semantic Role Labeling from Compatible Label Sequences","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2309.07429","title":"Semantic Parsing in Limited Resource Conditions","created":"2023-09-14","cited_by_count":0,"area":null},{"id":"2309.11688","title":"LLM Guided Inductive Inference for Solving Compositional Problems","created":"2023-09-20","cited_by_count":0,"area":null},{"id":"2402.16910","title":"NeSy is alive and well: A LLM-driven symbolic approach for better code comment data generation and classification","created":"2024-02-25","cited_by_count":0,"area":null},{"id":"2502.20499","title":"Data Distributional Properties As Inductive Bias for Systematic Generalization","created":"2025-02-27","cited_by_count":0,"area":null},{"id":"2503.01804","title":"$\\texttt{SEM-CTRL}$: Semantically Controlled Decoding","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2512.20954","title":"Reflection Pretraining Enables Token-Level Self-Correction in Biological Sequence Models","created":"2025-12-24","cited_by_count":0,"area":"lr"},{"id":"2605.00845","title":"Graph Query Generation with Constraint-guided Large Language Agents","created":"2026-04-09","cited_by_count":0,"area":"agents"},{"id":"2605.29250","title":"OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2609.22285","title":"ORDER: A Fictitious-World Benchmark for Domain-Adaptive Embodied AI","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.39368","title":"Making Grid Beam Search Less Greedy","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}