{"total":71,"rows":[{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"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":"2212.10001","title":"Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters","created":"2022-12-20","cited_by_count":222,"area":"lr"},{"id":"2302.05698","title":"Compositional Exemplars for In-context Learning","created":"2023-02-11","cited_by_count":144,"area":null},{"id":"2212.06800","title":"Diverse Demonstrations Improve In-context Compositional Generalization","created":"2022-12-13","cited_by_count":139,"area":null},{"id":"2407.02646","title":"A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models","created":"2024-07-02","cited_by_count":118,"area":"mechinterp"},{"id":"2305.11391","title":"A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation","created":"2023-05-19","cited_by_count":93,"area":null},{"id":"2305.15269","title":"Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples","created":"2023-05-24","cited_by_count":84,"area":"lr"},{"id":"2310.09881","title":"In-Context Learning with Iterative Demonstration Selection","created":"2023-10-15","cited_by_count":74,"area":null},{"id":"2402.01383","title":"LLM-based NLG Evaluation: Current Status and Challenges","created":"2024-02-02","cited_by_count":73,"area":null},{"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":"2303.14725","title":"Natural Language Reasoning, A Survey","created":"2023-03-26","cited_by_count":61,"area":"lr"},{"id":"2212.10378","title":"Data Curation Alone Can Stabilize In-context Learning","created":"2022-12-20","cited_by_count":59,"area":null},{"id":"2304.04193","title":"Extractive Summarization via ChatGPT for Faithful Summary Generation","created":"2023-04-09","cited_by_count":59,"area":null},{"id":"2305.14907","title":"Coverage-based Example Selection for In-Context Learning","created":"2023-05-24","cited_by_count":59,"area":null},{"id":"2305.14264","title":"Active Learning Principles for In-Context Learning with Large Language Models","created":"2023-05-23","cited_by_count":54,"area":null},{"id":"2305.14210","title":"Skill-Based Few-Shot Selection for In-Context Learning","created":"2023-05-23","cited_by_count":46,"area":null},{"id":"2307.05052","title":"Towards Understanding In-Context Learning with Contrastive Demonstrations and Saliency Maps","created":"2023-07-11","cited_by_count":35,"area":null},{"id":"2311.17944","title":"PALM: Predicting Actions through Language Models","created":"2023-11-29","cited_by_count":29,"area":null},{"id":"2409.04556","title":"How Does Code Pretraining Affect Language Model Task Performance?","created":"2024-09-06","cited_by_count":28,"area":null},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2306.09719","title":"Pushing the Limits of ChatGPT on NLP Tasks","created":"2023-06-16","cited_by_count":27,"area":null},{"id":"2503.22165","title":"Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models","created":"2025-03-28","cited_by_count":25,"area":"lr"},{"id":"2308.04945","title":"LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarking","created":"2023-08-09","cited_by_count":20,"area":null},{"id":"2308.10783","title":"Zero- and Few-Shot Prompting with LLMs: A Comparative Study with Fine-tuned Models for Bangla Sentiment Analysis","created":"2023-08-21","cited_by_count":20,"area":null},{"id":"2405.20902","title":"Preemptive Answer \"Attacks\" on Chain-of-Thought Reasoning","created":"2024-05-31","cited_by_count":19,"area":"lr"},{"id":"2305.19821","title":"LMCap: Few-shot Multilingual Image Captioning by Retrieval Augmented Language Model Prompting","created":"2023-05-31","cited_by_count":17,"area":"rag"},{"id":"2305.14982","title":"LAraBench: Benchmarking Arabic AI with Large Language Models","created":"2023-05-24","cited_by_count":16,"area":null},{"id":"2306.16545","title":"Palm: Predicting Actions through Language Models @ Ego4D Long-Term Action Anticipation Challenge 2023","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2402.02212","title":"A Survey to Recent Progress Towards Understanding In-Context Learning","created":"2024-02-03","cited_by_count":14,"area":null},{"id":"2306.17384","title":"SummQA at MEDIQA-Chat 2023:In-Context Learning with GPT-4 for Medical Summarization","created":"2023-06-30","cited_by_count":13,"area":null},{"id":"2506.08607","title":"Sample Efficient Demonstration Selection for In-Context Learning","created":"2025-06-10","cited_by_count":13,"area":null},{"id":"2406.14955","title":"ICLEval: Evaluating In-Context Learning Ability of Large Language Models","created":"2024-06-21","cited_by_count":12,"area":null},{"id":"2307.01453","title":"Diverse Retrieval-Augmented In-Context Learning for Dialogue State Tracking","created":"2023-07-04","cited_by_count":10,"area":"rag"},{"id":"2402.13874","title":"$Se^2$: Sequential Example Selection for In-Context Learning","created":"2024-02-21","cited_by_count":8,"area":null},{"id":"2305.05982","title":"Generating medically-accurate summaries of patient-provider dialogue: A multi-stage approach using large language models","created":"2023-05-10","cited_by_count":7,"area":null},{"id":"2402.14837","title":"An Empirical Categorization of Prompting Techniques for Large Language Models: A Practitioner's Guide","created":"2024-02-18","cited_by_count":7,"area":null},{"id":"2405.19795","title":"SLM as Guardian: Pioneering AI Safety with Small Language Models","created":"2024-05-30","cited_by_count":7,"area":null},{"id":"2410.12583","title":"STRUX: An LLM for Decision-Making with Structured Explanations","created":"2024-10-16","cited_by_count":7,"area":null},{"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":"2409.01247","title":"Conversational Complexity for Assessing Risk in Large Language Models","created":"2024-09-02","cited_by_count":6,"area":"safety"},{"id":"2505.19426","title":"The Role of Diversity in In-Context Learning for Large Language Models","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2507.13236","title":"Enhancing Cross-task Transfer of Large Language Models via Activation Steering","created":"2025-07-17","cited_by_count":6,"area":"mechinterp"},{"id":"2310.10707","title":"Demonstrations Are All You Need: Advancing Offensive Content Paraphrasing using In-Context Learning","created":"2023-10-16","cited_by_count":5,"area":null},{"id":"2312.07405","title":"ICL Markup: Structuring In-Context Learning using Soft-Token Tags","created":"2023-12-12","cited_by_count":5,"area":null},{"id":"2312.17055","title":"Beyond Output Matching: Bidirectional Alignment for Enhanced In-Context Learning","created":"2023-12-28","cited_by_count":5,"area":null},{"id":"2402.03038","title":"Automatic Combination of Sample Selection Strategies for Few-Shot Learning","created":"2024-02-05","cited_by_count":5,"area":null},{"id":"2502.15990","title":"Automated Query-Product Relevance Labeling using Large Language Models for E-commerce Search","created":"2025-02-21","cited_by_count":5,"area":null},{"id":"2310.07488","title":"KwaiYiiMath: Technical Report","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2311.09136","title":"Rescue: Ranking LLM Responses with Partial Ordering to Improve Response Generation","created":"2023-11-15","cited_by_count":4,"area":null},{"id":"2405.17587","title":"RAGSys: Item-Cold-Start Recommender as RAG System","created":"2024-05-27","cited_by_count":4,"area":"rag"},{"id":"2406.02911","title":"Improving In-Context Learning with Prediction Feedback for Sentiment Analysis","created":"2024-06-05","cited_by_count":4,"area":null},{"id":"2409.17702","title":"Episodic Memory Verbalization using Hierarchical Representations of Life-Long Robot Experience","created":"2024-09-26","cited_by_count":4,"area":null},{"id":"2410.21728","title":"Let's Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Models","created":"2024-10-29","cited_by_count":4,"area":"lr"},{"id":"2506.06052","title":"DCP-Bench-Open: Evaluating LLMs for Constraint Modelling of Discrete Combinatorial Problems","created":"2025-06-06","cited_by_count":4,"area":null},{"id":"2506.13109","title":"Leveraging In-Context Learning for Language Model Agents","created":"2025-06-16","cited_by_count":4,"area":"agents"},{"id":"2407.04573","title":"Vector Retrieval with Similarity and Diversity: How Hard Is It?","created":"2024-07-05","cited_by_count":3,"area":"rag"},{"id":"2505.22635","title":"Learning Composable Chains-of-Thought","created":"2025-05-28","cited_by_count":3,"area":"lr"},{"id":"2512.01899","title":"Provably Safe Model Updates","created":"2025-12-01","cited_by_count":3,"area":null},{"id":"2402.10424","title":"Pelican Soup Framework: A Theoretical Framework for Language Model Capabilities","created":"2024-02-16","cited_by_count":2,"area":null},{"id":"2503.09249","title":"Considering Length Diversity in Retrieval-Augmented Summarization","created":"2025-03-12","cited_by_count":2,"area":"rag"},{"id":"2406.02804","title":"ACCORD: Closing the Commonsense Measurability Gap","created":"2024-06-04","cited_by_count":1,"area":"lr"},{"id":"2410.13118","title":"Retrieval-Enhanced Named Entity Recognition","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2506.06033","title":"Large Language Models are Demonstration Pre-Selectors for Themselves","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2507.20398","title":"Length Representations in Large Language Models","created":"2025-07-27","cited_by_count":1,"area":null},{"id":"2508.00385","title":"Multi-Layer Attention is the Amplifier of Demonstration Effectiveness","created":"2025-08-01","cited_by_count":1,"area":null},{"id":"2409.09261","title":"What Is Wrong with My Model? Identifying Systematic Problems with Semantic Data Slicing","created":"2024-09-14","cited_by_count":0,"area":null},{"id":"2502.04037","title":"Exploring Imbalanced Annotations for Effective In-Context Learning","created":"2025-02-06","cited_by_count":0,"area":null},{"id":"2604.12015","title":"UCS: Estimating Unseen Coverage for Improved In-Context Learning","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2609.06670","title":"Data Efficient Sample Selection for In-Context Learning","created":"2026-09-06","cited_by_count":0,"area":null}],"next_cursor":null}