{"total":56,"rows":[{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737,"area":null},{"id":"2212.09597","title":"Reasoning with Language Model Prompting: A Survey","created":"2022-12-19","cited_by_count":252,"area":"lr"},{"id":"2305.01879","title":"SCOTT: Self-Consistent Chain-of-Thought Distillation","created":"2023-05-03","cited_by_count":105,"area":"lr"},{"id":"2305.09656","title":"SatLM: Satisfiability-Aided Language Models Using Declarative Prompting","created":"2023-05-16","cited_by_count":102,"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":"2402.01207","title":"Efficient Causal Graph Discovery Using Large Language Models","created":"2024-02-02","cited_by_count":53,"area":null},{"id":"2305.12147","title":"LogiCoT: Logical Chain-of-Thought Instruction-Tuning","created":"2023-05-20","cited_by_count":31,"area":"lr"},{"id":"2311.00321","title":"HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning","created":"2023-11-01","cited_by_count":31,"area":null},{"id":"2402.11863","title":"How Interpretable are Reasoning Explanations from Prompting Large Language Models?","created":"2024-02-19","cited_by_count":29,"area":"lr"},{"id":"2310.14747","title":"MCC-KD: Multi-CoT Consistent Knowledge Distillation","created":"2023-10-23","cited_by_count":28,"area":"lr"},{"id":"2311.02805","title":"Tailoring Self-Rationalizers with Multi-Reward Distillation","created":"2023-11-06","cited_by_count":21,"area":null},{"id":"2312.08303","title":"Efficient Toxic Content Detection by Bootstrapping and Distilling Large Language Models","created":"2023-12-13","cited_by_count":21,"area":"synth"},{"id":"2305.13514","title":"Small Language Models Improve Giants by Rewriting Their Outputs","created":"2023-05-22","cited_by_count":18,"area":null},{"id":"2402.01729","title":"Contextualization Distillation from Large Language Model for Knowledge Graph Completion","created":"2024-01-28","cited_by_count":18,"area":null},{"id":"2310.04921","title":"Crystal: Introspective Reasoners Reinforced with Self-Feedback","created":"2023-10-07","cited_by_count":15,"area":"lr"},{"id":"2312.05434","title":"Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language Models","created":"2023-12-09","cited_by_count":15,"area":"lr"},{"id":"2311.09603","title":"Self-Contradictory Reasoning Evaluation and Detection","created":"2023-11-16","cited_by_count":14,"area":"lr"},{"id":"2410.18588","title":"Knowledge Distillation Using Frontier Open-source LLMs: Generalizability and the Role of Synthetic Data","created":"2024-10-24","cited_by_count":12,"area":"synth"},{"id":"2305.12723","title":"Enhancing Small Medical Learners with Privacy-preserving Contextual Prompting","created":"2023-05-22","cited_by_count":11,"area":null},{"id":"2403.10351","title":"TriSum: Learning Summarization Ability from Large Language Models with Structured Rationale","created":"2024-03-15","cited_by_count":10,"area":null},{"id":"2403.19167","title":"Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering","created":"2024-03-28","cited_by_count":10,"area":"lr"},{"id":"2505.22823","title":"Self-Critique and Refinement for Faithful Natural Language Explanations","created":"2025-05-28","cited_by_count":10,"area":null},{"id":"2505.18759","title":"The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillation","created":"2025-05-24","cited_by_count":9,"area":"lr"},{"id":"2605.12671","title":"All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs","created":"2026-05-12","cited_by_count":9,"area":"lr"},{"id":"2301.11879","title":"Case-Based Reasoning with Language Models for Classification of Logical Fallacies","created":"2023-01-27","cited_by_count":8,"area":"lr"},{"id":"2305.07355","title":"ZARA: Improving Few-Shot Self-Rationalization for Small Language Models","created":"2023-05-12","cited_by_count":8,"area":null},{"id":"2310.15575","title":"POE: Process of Elimination for Multiple Choice Reasoning","created":"2023-10-24","cited_by_count":8,"area":"lr"},{"id":"2509.23574","title":"Towards Efficient CoT Distillation: Self-Guided Rationale Selector for Better Performance with Fewer Rationales","created":"2025-09-28","cited_by_count":8,"area":"lr"},{"id":"2504.15848","title":"Exploring Cognitive and Aesthetic Causality for Multimodal Aspect-Based Sentiment Analysis","created":"2025-04-22","cited_by_count":6,"area":null},{"id":"2309.08583","title":"ICLEF: In-Context Learning with Expert Feedback for Explainable Style Transfer","created":"2023-09-15","cited_by_count":5,"area":"alignment"},{"id":"2407.14477","title":"Data-Centric Human Preference with Rationales for Direct Preference Alignment","created":"2024-07-19","cited_by_count":5,"area":"alignment"},{"id":"2412.07148","title":"MM-PoE: Multiple Choice Reasoning via. Process of Elimination using Multi-Modal Models","created":"2024-12-10","cited_by_count":5,"area":"lr"},{"id":"2412.13698","title":"Towards Efficient and Explainable Hate Speech Detection via Model Distillation","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2503.17569","title":"Fairness-Driven LLM-based Causal Discovery with Active Learning and Dynamic Scoring","created":"2025-03-21","cited_by_count":5,"area":null},{"id":"2310.07488","title":"KwaiYiiMath: Technical Report","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2311.07099","title":"Explanation-aware Soft Ensemble Empowers Large Language Model In-context Learning","created":"2023-11-13","cited_by_count":4,"area":null},{"id":"2306.03315","title":"Few Shot Rationale Generation using Self-Training with Dual Teachers","created":"2023-06-05","cited_by_count":3,"area":"synth"},{"id":"2405.10128","title":"Red Teaming Language Models for Processing Contradictory Dialogues","created":"2024-05-16","cited_by_count":3,"area":"safety"},{"id":"2406.11375","title":"Boosting Scientific Concepts Understanding: Can Analogy from Teacher Models Empower Student Models?","created":"2024-06-17","cited_by_count":3,"area":"lr"},{"id":"2412.12318","title":"Graph-Guided Textual Explanation Generation Framework","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2509.11026","title":"Rethinking Human Preference Evaluation of LLM Rationales","created":"2025-09-14","cited_by_count":3,"area":"lr"},{"id":"2305.08732","title":"Knowledge Rumination for Pre-trained Language Models","created":"2023-05-15","cited_by_count":2,"area":null},{"id":"2403.11129","title":"Enhancing Event Causality Identification with Rationale and Structure-Aware Causal Question Answering","created":"2024-03-17","cited_by_count":2,"area":null},{"id":"2412.08024","title":"TinyThinker: Distilling Reasoning through Coarse-to-Fine Knowledge Internalization with Self-Reflection","created":"2024-12-11","cited_by_count":2,"area":"lr"},{"id":"2212.09721","title":"KNIFE: Distilling Reasoning Knowledge From Free-Text Rationales","created":"2022-12-19","cited_by_count":1,"area":"lr"},{"id":"2402.14355","title":"Rule or Story, Which is a Better Commonsense Expression for Talking with Large Language Models?","created":"2024-02-22","cited_by_count":1,"area":"lr"},{"id":"2408.10795","title":"Adversarial Attack for Explanation Robustness of Rationalization Models","created":"2024-08-20","cited_by_count":1,"area":null},{"id":"2505.24147","title":"Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2605.02442","title":"Measuring AI Reasoning: A Guide for Researchers","created":"2026-05-04","cited_by_count":1,"area":"lr"},{"id":"2306.01753","title":"Preconditioned Visual Language Inference with Weak Supervision","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2503.05620","title":"Learning LLM Preference over Intra-Dialogue Pairs: A Framework for Utterance-level Understandings","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2506.19599","title":"ECCoT: A Framework for Enhancing Effective Cognition via Chain of Thought in Large Language Model","created":"2025-06-24","cited_by_count":0,"area":"lr"},{"id":"2507.19741","title":"Basic Reading Distillation","created":"2025-07-26","cited_by_count":0,"area":"distill"},{"id":"2603.09533","title":"Enhancing Debunking Effectiveness through LLM-based Personality Adaptation","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2604.23829","title":"Domain-Filtered Knowledge Graphs from Sparse Autoencoder Features","created":"2026-04-26","cited_by_count":0,"area":"mechinterp"},{"id":"2608.21043","title":"Evidence-Consistent Generative Detection under Scenario-Level Distribution Shift","created":"2026-08-21","cited_by_count":0,"area":null}],"next_cursor":null}