{"total":410,"rows":[{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267,"area":"agents"},{"id":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075,"area":"lr"},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916,"area":null},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743,"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":"2109.00122","title":"FinQA: A Dataset of Numerical Reasoning over Financial Data","created":"2021-09-01","cited_by_count":562,"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":"2105.07624","title":"TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance","created":"2021-05-17","cited_by_count":408,"area":null},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403,"area":"lr"},{"id":"2310.01061","title":"Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning","created":"2023-10-02","cited_by_count":328,"area":"lr"},{"id":"2408.08921","title":"Graph Retrieval-Augmented Generation: A Survey","created":"2024-08-15","cited_by_count":324,"area":"rag"},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295,"area":null},{"id":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290,"area":null},{"id":"2305.11554","title":"ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings","created":"2023-05-19","cited_by_count":240,"area":"agents"},{"id":"2502.17416","title":"Reasoning with Latent Thoughts: On the Power of Looped Transformers","created":"2025-02-24","cited_by_count":240,"area":"lr"},{"id":"2307.07697","title":"Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph","created":"2023-07-15","cited_by_count":238,"area":"lr"},{"id":"2201.05966","title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","created":"2022-01-16","cited_by_count":231,"area":null},{"id":"2112.08608","title":"QuALITY: Question Answering with Long Input Texts, Yes!","created":"2021-12-16","cited_by_count":208,"area":null},{"id":"2104.06039","title":"MultiModalQA: Complex Question Answering over Text, Tables and Images","created":"2021-04-13","cited_by_count":179,"area":null},{"id":"2301.04883","title":"SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images","created":"2023-01-12","cited_by_count":179,"area":null},{"id":"2301.13808","title":"Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning","created":"2023-01-31","cited_by_count":178,"area":"lr"},{"id":"2311.05772","title":"ADaPT: As-Needed Decomposition and Planning with Language Models","created":"2023-11-08","cited_by_count":177,"area":"lr"},{"id":"2104.08768","title":"Constrained Language Models Yield Few-Shot Semantic Parsers","created":"2021-04-18","cited_by_count":163,"area":null},{"id":"2405.20139","title":"GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning","created":"2024-05-30","cited_by_count":128,"area":"lr"},{"id":"2206.01347","title":"MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data","created":"2022-06-03","cited_by_count":121,"area":null},{"id":"2305.11859","title":"Complex Claim Verification with Evidence Retrieved in the Wild","created":"2023-05-19","cited_by_count":110,"area":null},{"id":"2109.00590","title":"WebQA: Multihop and Multimodal QA","created":"2021-09-01","cited_by_count":109,"area":null},{"id":"2201.05320","title":"CommonsenseQA 2.0: Exposing the Limits of AI through Gamification","created":"2022-01-14","cited_by_count":109,"area":null},{"id":"2104.08762","title":"Case-based Reasoning for Natural Language Queries over Knowledge Bases","created":"2021-04-18","cited_by_count":107,"area":null},{"id":"2306.09224","title":"Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories","created":"2023-06-15","cited_by_count":107,"area":"rag"},{"id":"2212.00959","title":"UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph","created":"2022-12-02","cited_by_count":103,"area":"lr"},{"id":"2101.03737","title":"Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals","created":"2021-01-11","cited_by_count":101,"area":null},{"id":"2106.01515","title":"Question Answering Over Temporal Knowledge Graphs","created":"2021-06-03","cited_by_count":99,"area":null},{"id":"2308.13259","title":"Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering","created":"2023-08-25","cited_by_count":97,"area":"lr"},{"id":"2406.04744","title":"CRAG -- Comprehensive RAG Benchmark","created":"2024-06-07","cited_by_count":97,"area":"rag"},{"id":"2202.13296","title":"Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering","created":"2022-02-27","cited_by_count":93,"area":null},{"id":"2301.07507","title":"Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing","created":"2023-01-18","cited_by_count":93,"area":null},{"id":"2402.11163","title":"KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph","created":"2024-02-17","cited_by_count":93,"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":"2501.13958","title":"A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models","created":"2025-01-21","cited_by_count":88,"area":"rag"},{"id":"2304.13007","title":"Answering Questions by Meta-Reasoning over Multiple Chains of Thought","created":"2023-04-25","cited_by_count":87,"area":"lr"},{"id":"2407.04069","title":"A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations","created":"2024-07-04","cited_by_count":85,"area":null},{"id":"2210.00063","title":"DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases","created":"2022-09-30","cited_by_count":84,"area":null},{"id":"2410.20724","title":"Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation","created":"2024-10-28","cited_by_count":80,"area":"lr"},{"id":"2105.11644","title":"A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutions","created":"2021-05-25","cited_by_count":78,"area":null},{"id":"2410.23875","title":"Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs","created":"2024-10-31","cited_by_count":78,"area":"lr"},{"id":"2203.10321","title":"Sequence-to-Sequence Knowledge Graph Completion and Question Answering","created":"2022-03-19","cited_by_count":75,"area":null},{"id":"2305.01750","title":"Few-shot In-context Learning for Knowledge Base Question Answering","created":"2023-05-02","cited_by_count":74,"area":null},{"id":"2210.01613","title":"Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering","created":"2022-10-04","cited_by_count":72,"area":null},{"id":"2303.07992","title":"Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family","created":"2023-03-14","cited_by_count":71,"area":null},{"id":"2109.08935","title":"Complex Temporal Question Answering on Knowledge Graphs","created":"2021-09-18","cited_by_count":69,"area":null},{"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":"2209.08199","title":"ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots","created":"2022-09-16","cited_by_count":66,"area":null},{"id":"2409.14924","title":"Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely","created":"2024-09-23","cited_by_count":66,"area":"rag"},{"id":"2309.11206","title":"Retrieve-Rewrite-Answer: A KG-to-Text Enhanced LLMs Framework for Knowledge Graph Question Answering","created":"2023-09-20","cited_by_count":65,"area":null},{"id":"2402.00559","title":"A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains","created":"2024-02-01","cited_by_count":65,"area":"lr"},{"id":"2502.12289","title":"Evaluating Step-by-step Reasoning Traces: A Survey","created":"2025-02-17","cited_by_count":63,"area":"lr"},{"id":"2303.14725","title":"Natural Language Reasoning, A Survey","created":"2023-03-26","cited_by_count":61,"area":"lr"},{"id":"2502.14902","title":"PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths","created":"2025-02-18","cited_by_count":61,"area":"rag"},{"id":"2104.07302","title":"TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph","created":"2021-04-15","cited_by_count":60,"area":null},{"id":"2112.09924","title":"The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpus","created":"2021-12-18","cited_by_count":60,"area":null},{"id":"2404.14741","title":"Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answering","created":"2024-04-23","cited_by_count":60,"area":"agents"},{"id":"2106.10502","title":"JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs","created":"2021-06-19","cited_by_count":58,"area":null},{"id":"2502.06864","title":"Knowledge Graph-Guided Retrieval Augmented Generation","created":"2025-02-08","cited_by_count":58,"area":"rag"},{"id":"2405.12035","title":"KG-RAG: Bridging the Gap Between Knowledge and Creativity","created":"2024-05-20","cited_by_count":56,"area":"rag"},{"id":"2404.13207","title":"STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases","created":"2024-04-19","cited_by_count":55,"area":null},{"id":"2108.06688","title":"Complex Knowledge Base Question Answering: A Survey","created":"2021-08-15","cited_by_count":52,"area":null},{"id":"2104.06598","title":"AR-LSAT: Investigating Analytical Reasoning of Text","created":"2021-04-14","cited_by_count":51,"area":null},{"id":"2410.13080","title":"Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models","created":"2024-10-16","cited_by_count":48,"area":"lr"},{"id":"2310.08975","title":"ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models","created":"2023-10-13","cited_by_count":44,"area":null},{"id":"2410.14211","title":"Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning","created":"2024-10-18","cited_by_count":44,"area":"lr"},{"id":"2110.06176","title":"Mention Memory: incorporating textual knowledge into Transformers through entity mention attention","created":"2021-10-12","cited_by_count":43,"area":null},{"id":"2507.09477","title":"Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs","created":"2025-07-13","cited_by_count":42,"area":"lr"},{"id":"2107.07261","title":"Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills","created":"2021-07-15","cited_by_count":39,"area":null},{"id":"2311.09278","title":"Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models","created":"2023-11-15","cited_by_count":39,"area":null},{"id":"2402.14672","title":"Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments","created":"2024-02-22","cited_by_count":39,"area":"agents"},{"id":"2405.13873","title":"FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering","created":"2024-05-22","cited_by_count":39,"area":"lr"},{"id":"2501.15915","title":"Parametric Retrieval Augmented Generation","created":"2025-01-27","cited_by_count":38,"area":"rag"},{"id":"2205.12538","title":"Is a Question Decomposition Unit All We Need?","created":"2022-05-25","cited_by_count":37,"area":null},{"id":"2406.13397","title":"MoreHopQA: More Than Multi-hop Reasoning","created":"2024-06-19","cited_by_count":37,"area":"lr"},{"id":"2110.13472","title":"Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretable","created":"2021-10-26","cited_by_count":35,"area":null},{"id":"2110.05743","title":"Program Transfer for Answering Complex Questions over Knowledge Bases","created":"2021-10-12","cited_by_count":34,"area":null},{"id":"2103.05568","title":"Select, Substitute, Search: A New Benchmark for Knowledge-Augmented Visual Question Answering","created":"2021-03-09","cited_by_count":33,"area":null},{"id":"2305.11694","title":"QUEST: A Retrieval Dataset of Entity-Seeking Queries with Implicit Set Operations","created":"2023-05-19","cited_by_count":31,"area":null},{"id":"2105.11698","title":"Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting","created":"2021-05-25","cited_by_count":30,"area":null},{"id":"2502.06872","title":"Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey","created":"2025-02-08","cited_by_count":30,"area":"rag"},{"id":"2110.06884","title":"ConditionalQA: A Complex Reading Comprehension Dataset with Conditional Answers","created":"2021-10-13","cited_by_count":29,"area":null},{"id":"2402.14116","title":"FanOutQA: A Multi-Hop, Multi-Document Question Answering Benchmark for Large Language Models","created":"2024-02-21","cited_by_count":29,"area":null},{"id":"2402.16671","title":"StructLM: Towards Building Generalist Models for Structured Knowledge Grounding","created":"2024-02-26","cited_by_count":29,"area":null},{"id":"2407.11417","title":"SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questions","created":"2024-07-16","cited_by_count":27,"area":null},{"id":"2504.15909","title":"Synergizing RAG and Reasoning: A Systematic Review","created":"2025-04-22","cited_by_count":27,"area":"lr"},{"id":"2410.13765","title":"Knowledge-Aware Query Expansion with Large Language Models for Textual and Relational Retrieval","created":"2024-10-17","cited_by_count":26,"area":null},{"id":"2104.05883","title":"Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval","created":"2021-04-13","cited_by_count":25,"area":null},{"id":"2402.15131","title":"Interactive-KBQA: Multi-Turn Interactions for Knowledge Base Question Answering with Large Language Models","created":"2024-02-23","cited_by_count":25,"area":null},{"id":"2503.23895","title":"Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement","created":"2025-03-31","cited_by_count":25,"area":"rag"},{"id":"2401.17585","title":"Propagation and Pitfalls: Reasoning-based Assessment of Knowledge Editing through Counterfactual Tasks","created":"2024-01-31","cited_by_count":24,"area":null},{"id":"2409.20163","title":"MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistants","created":"2024-09-30","cited_by_count":24,"area":"agents"},{"id":"2410.08085","title":"Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study Over Open-ended Question Answering","created":"2024-10-10","cited_by_count":24,"area":"lr"},{"id":"2503.01478","title":"SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction","created":"2025-03-03","cited_by_count":24,"area":"rag"},{"id":"2206.15030","title":"Modern Question Answering Datasets and Benchmarks: A Survey","created":"2022-06-30","cited_by_count":23,"area":null}],"next_cursor":"100"}