{"total":118,"rows":[{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407,"area":"lr"},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122,"area":"lr"},{"id":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075,"area":"lr"},{"id":"2211.14275","title":"Solving math word problems with process- and outcome-based feedback","created":"2022-11-25","cited_by_count":901,"area":"lr"},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836,"area":"alignment"},{"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":"2210.02406","title":"Decomposed Prompting: A Modular Approach for Solving Complex Tasks","created":"2022-10-05","cited_by_count":558,"area":null},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403,"area":"lr"},{"id":"2105.11447","title":"True Few-Shot Learning with Language Models","created":"2021-05-24","cited_by_count":344,"area":null},{"id":"2109.10862","title":"Recursively Summarizing Books with Human Feedback","created":"2021-09-22","cited_by_count":290,"area":null},{"id":"2406.02818","title":"Chain of Agents: Large Language Models Collaborating on Long-Context Tasks","created":"2024-06-04","cited_by_count":206,"area":"agents"},{"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":"2407.06023","title":"Distilling System 2 into System 1","created":"2024-07-08","cited_by_count":159,"area":"lr"},{"id":"2403.01248","title":"SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code","created":"2024-03-02","cited_by_count":134,"area":"agents"},{"id":"2203.05115","title":"Internet-augmented language models through few-shot prompting for open-domain question answering","created":"2022-03-10","cited_by_count":131,"area":null},{"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":"2307.11768","title":"Question Decomposition Improves the Faithfulness of Model-Generated Reasoning","created":"2023-07-17","cited_by_count":108,"area":"lr"},{"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":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96,"area":"alignment"},{"id":"2502.11271","title":"OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning","created":"2025-02-16","cited_by_count":69,"area":"lr"},{"id":"2303.14725","title":"Natural Language Reasoning, A Survey","created":"2023-03-26","cited_by_count":61,"area":"lr"},{"id":"2406.13121","title":"Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?","created":"2024-06-19","cited_by_count":56,"area":null},{"id":"2403.06840","title":"RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback","created":"2024-03-11","cited_by_count":46,"area":"rag"},{"id":"2211.12835","title":"Automatic Generation of Socratic Subquestions for Teaching Math Word Problems","created":"2022-11-23","cited_by_count":43,"area":null},{"id":"2112.08688","title":"Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks","created":"2021-12-16","cited_by_count":40,"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":"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":"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":"2506.07642","title":"TreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer Review","created":"2025-06-09","cited_by_count":31,"area":null},{"id":"2210.03992","title":"Generative Language Models for Paragraph-Level Question Generation","created":"2022-10-08","cited_by_count":28,"area":null},{"id":"2406.06027","title":"HOLMES: Hyper-Relational Knowledge Graphs for Multi-hop Question Answering using LLMs","created":"2024-06-10","cited_by_count":24,"area":null},{"id":"2212.09656","title":"Visconde: Multi-document QA with GPT-3 and Neural Reranking","created":"2022-12-19","cited_by_count":23,"area":null},{"id":"2103.03872","title":"Rissanen Data Analysis: Examining Dataset Characteristics via Description Length","created":"2021-03-05","cited_by_count":22,"area":null},{"id":"2203.11027","title":"Reasoning over Public and Private Data in Retrieval-Based Systems","created":"2022-03-14","cited_by_count":21,"area":null},{"id":"2205.12650","title":"Few-shot Reranking for Multi-hop QA via Language Model Prompting","created":"2022-05-25","cited_by_count":19,"area":null},{"id":"2210.16865","title":"Learning to Decompose: Hypothetical Question Decomposition Based on Comparable Texts","created":"2022-10-30","cited_by_count":18,"area":null},{"id":"2402.15000","title":"Divide-or-Conquer? Which Part Should You Distill Your LLM?","created":"2024-02-22","cited_by_count":17,"area":"lr"},{"id":"2204.07190","title":"Measuring Compositional Consistency for Video Question Answering","created":"2022-04-14","cited_by_count":15,"area":null},{"id":"2305.17002","title":"An Empirical Comparison of LM-based Question and Answer Generation Methods","created":"2023-05-26","cited_by_count":15,"area":null},{"id":"2502.04322","title":"Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions","created":"2025-02-06","cited_by_count":15,"area":"alignment"},{"id":"2506.10446","title":"Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty","created":"2025-06-12","cited_by_count":15,"area":"lr"},{"id":"2310.13575","title":"Semantic Decomposition of Question and SQL for Text-to-SQL Parsing","created":"2023-10-20","cited_by_count":14,"area":null},{"id":"2107.11823","title":"Graph-free Multi-hop Reading Comprehension: A Select-to-Guide Strategy","created":"2021-07-25","cited_by_count":13,"area":null},{"id":"2110.08542","title":"Hey AI, Can You Solve Complex Tasks by Talking to Agents?","created":"2021-10-16","cited_by_count":13,"area":null},{"id":"2205.11729","title":"From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answering","created":"2022-05-24","cited_by_count":12,"area":null},{"id":"2206.08486","title":"Interpretable AMR-Based Question Decomposition for Multi-hop Question Answering","created":"2022-06-16","cited_by_count":12,"area":null},{"id":"2310.17050","title":"Exploring Question Decomposition for Zero-Shot VQA","created":"2023-10-25","cited_by_count":12,"area":null},{"id":"2109.11020","title":"Exploring Decomposition for Table-based Fact Verification","created":"2021-09-22","cited_by_count":11,"area":null},{"id":"2305.05364","title":"Large Language Model Programs","created":"2023-05-09","cited_by_count":11,"area":null},{"id":"2305.15056","title":"Reasoning over Hierarchical Question Decomposition Tree for Explainable Question Answering","created":"2023-05-24","cited_by_count":11,"area":null},{"id":"2407.12982","title":"Retrieval-Enhanced Machine Learning: Synthesis and Opportunities","created":"2024-07-17","cited_by_count":11,"area":null},{"id":"2502.08080","title":"NLI under the Microscope: What Atomic Hypothesis Decomposition Reveals","created":"2025-02-12","cited_by_count":11,"area":null},{"id":"2507.00355","title":"Question Decomposition for Retrieval-Augmented Generation","created":"2025-07-01","cited_by_count":11,"area":"rag"},{"id":"2105.13608","title":"Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax","created":"2021-05-28","cited_by_count":10,"area":null},{"id":"2210.12607","title":"Learning to Perform Complex Tasks through Compositional Fine-Tuning of Language Models","created":"2022-10-23","cited_by_count":10,"area":null},{"id":"2409.05197","title":"Seemingly Plausible Distractors in Multi-Hop Reasoning: Are Large Language Models Attentive Readers?","created":"2024-09-08","cited_by_count":10,"area":"lr"},{"id":"2204.07693","title":"Calibrating Trust of Multi-Hop Question Answering Systems with Decompositional Probes","created":"2022-04-16","cited_by_count":9,"area":"lr"},{"id":"2204.13778","title":"Inferring Implicit Relations in Complex Questions with Language Models","created":"2022-04-28","cited_by_count":9,"area":"lr"},{"id":"2101.09893","title":"MadDog: A Web-based System for Acronym Identification and Disambiguation","created":"2021-01-25","cited_by_count":8,"area":null},{"id":"2105.14875","title":"Bangla Natural Language Processing: A Comprehensive Analysis of Classical, Machine Learning, and Deep Learning Based Methods","created":"2021-05-31","cited_by_count":8,"area":null},{"id":"2110.06560","title":"Simple or Complex? Complexity-Controllable Question Generation with Soft Templates and Deep Mixture of Experts Model","created":"2021-10-13","cited_by_count":8,"area":"moe"},{"id":"2305.14901","title":"Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2311.13565","title":"Drilling Down into the Discourse Structure with LLMs for Long Document Question Answering","created":"2023-11-22","cited_by_count":8,"area":null},{"id":"2505.20245","title":"KnowTrace: Bootstrapping Iterative Retrieval-Augmented Generation with Structured Knowledge Tracing","created":"2025-05-26","cited_by_count":8,"area":"rag"},{"id":"2104.08647","title":"Question Decomposition with Dependency Graphs","created":"2021-04-17","cited_by_count":7,"area":null},{"id":"2109.03731","title":"Cross-Policy Compliance Detection via Question Answering","created":"2021-09-08","cited_by_count":7,"area":null},{"id":"2210.04234","title":"Understanding and Improving Zero-shot Multi-hop Reasoning in Generative Question Answering","created":"2022-10-09","cited_by_count":7,"area":"lr"},{"id":"2211.03277","title":"Complex Reading Comprehension Through Question Decomposition","created":"2022-11-07","cited_by_count":7,"area":null},{"id":"2307.06869","title":"DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question Answering","created":"2023-07-13","cited_by_count":7,"area":null},{"id":"2501.17767","title":"Hybrid Graphs for Table-and-Text based Question Answering using LLMs","created":"2025-01-29","cited_by_count":7,"area":null},{"id":"2208.10297","title":"Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering","created":"2022-08-22","cited_by_count":6,"area":"lr"},{"id":"2311.08584","title":"Asking More Informative Questions for Grounded Retrieval","created":"2023-11-14","cited_by_count":6,"area":null},{"id":"2407.02964","title":"FSM: A Finite State Machine Based Zero-Shot Prompting Paradigm for Multi-Hop Question Answering","created":"2024-07-03","cited_by_count":6,"area":"lr"},{"id":"2506.12421","title":"Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints","created":"2025-06-14","cited_by_count":6,"area":null},{"id":"2606.00593","title":"SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering","created":"2026-05-30","cited_by_count":6,"area":null},{"id":"2404.13985","title":"Information Re-Organization Improves Reasoning in Large Language Models","created":"2024-04-22","cited_by_count":5,"area":"lr"},{"id":"2505.19189","title":"POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval","created":"2025-05-25","cited_by_count":5,"area":"rag"},{"id":"2511.02219","title":"TabDSR: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular Data","created":"2025-11-04","cited_by_count":5,"area":"lr"},{"id":"2112.09658","title":"Reasoning Chain Based Adversarial Attack for Multi-hop Question Answering","created":"2021-12-17","cited_by_count":4,"area":null},{"id":"2209.01824","title":"A Survey on Measuring and Mitigating Reasoning Shortcuts in Machine Reading Comprehension","created":"2022-09-05","cited_by_count":4,"area":null},{"id":"2402.19350","title":"Prompting Explicit and Implicit Knowledge for Multi-hop Question Answering Based on Human Reading Process","created":"2024-02-29","cited_by_count":4,"area":null},{"id":"2403.12678","title":"Empowering Air Travelers: A Chatbot for Canadian Air Passenger Rights","created":"2024-03-19","cited_by_count":4,"area":null},{"id":"2501.04341","title":"Understanding Before Reasoning: Enhancing Chain-of-Thought with Iterative Summarization Pre-Prompting","created":"2025-01-08","cited_by_count":4,"area":"lr"},{"id":"2601.20131","title":"Taxonomy of the Retrieval System Framework: Pitfalls and Paradigms","created":"2026-01-27","cited_by_count":4,"area":null},{"id":"2106.09983","title":"Weakly Supervised Pre-Training for Multi-Hop Retriever","created":"2021-06-18","cited_by_count":3,"area":null},{"id":"2109.05149","title":"Extract, Integrate, Compete: Towards Verification Style Reading Comprehension","created":"2021-09-11","cited_by_count":3,"area":null},{"id":"2111.09029","title":"Towards Interpretable and Reliable Reading Comprehension: A Pipeline Model with Unanswerability Prediction","created":"2021-11-17","cited_by_count":3,"area":null},{"id":"2209.06923","title":"Prompt-based Conservation Learning for Multi-hop Question Answering","created":"2022-09-14","cited_by_count":3,"area":null},{"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":"2310.18371","title":"In-Context Ability Transfer for Question Decomposition in Complex QA","created":"2023-10-26","cited_by_count":3,"area":null},{"id":"2311.02616","title":"Divide & Conquer for Entailment-aware Multi-hop Evidence Retrieval","created":"2023-11-05","cited_by_count":3,"area":null},{"id":"2406.03592","title":"Measuring Retrieval Complexity in Question Answering Systems","created":"2024-06-05","cited_by_count":3,"area":null},{"id":"2104.08744","title":"Generative Context Pair Selection for Multi-hop Question Answering","created":"2021-04-18","cited_by_count":2,"area":null},{"id":"2212.10019","title":"When Do Decompositions Help for Machine Reading?","created":"2022-12-20","cited_by_count":2,"area":null},{"id":"2302.05963","title":"Analyzing the Effectiveness of the Underlying Reasoning Tasks in Multi-hop Question Answering","created":"2023-02-12","cited_by_count":2,"area":"lr"},{"id":"2402.15764","title":"Look Before You Leap: Problem Elaboration Prompting Improves Mathematical Reasoning in Large Language Models","created":"2024-02-24","cited_by_count":2,"area":"lr"},{"id":"2410.17021","title":"SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machine","created":"2024-10-22","cited_by_count":2,"area":"lr"}],"next_cursor":"100"}