{"total":153,"rows":[{"id":"2310.11324","title":"Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting","created":"2023-10-17","cited_by_count":817,"area":null},{"id":"2301.00234","title":"A Survey on In-context Learning","created":"2022-12-31","cited_by_count":721,"area":null},{"id":"2401.00595","title":"State of What Art? A Call for Multi-Prompt LLM Evaluation","created":"2023-12-31","cited_by_count":310,"area":null},{"id":"2404.02936","title":"Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models","created":"2024-04-03","cited_by_count":103,"area":null},{"id":"2311.09180","title":"Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrievers","created":"2023-11-15","cited_by_count":92,"area":null},{"id":"2302.13439","title":"Navigating the Grey Area: How Expressions of Uncertainty and Overconfidence Affect Language Models","created":"2023-02-26","cited_by_count":91,"area":null},{"id":"2303.07971","title":"A Theory of Emergent In-Context Learning as Implicit Structure Induction","created":"2023-03-14","cited_by_count":86,"area":null},{"id":"2306.08189","title":"Language models are not naysayers: An analysis of language models on negation benchmarks","created":"2023-06-14","cited_by_count":74,"area":null},{"id":"2305.14128","title":"Dr.ICL: Demonstration-Retrieved In-context Learning","created":"2023-05-23","cited_by_count":72,"area":null},{"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":"2302.11042","title":"In-context Example Selection with Influences","created":"2023-02-21","cited_by_count":61,"area":null},{"id":"2212.10378","title":"Data Curation Alone Can Stabilize In-context Learning","created":"2022-12-20","cited_by_count":59,"area":null},{"id":"2401.12087","title":"Revisiting Demonstration Selection Strategies in In-Context Learning","created":"2024-01-22","cited_by_count":58,"area":null},{"id":"2404.09937","title":"Compression Represents Intelligence Linearly","created":"2024-04-15","cited_by_count":56,"area":null},{"id":"2404.11531","title":"Pack of LLMs: Model Fusion at Test-Time via Perplexity Optimization","created":"2024-04-17","cited_by_count":56,"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":"2307.12375","title":"In-Context Learning Learns Label Relationships but Is Not Conventional Learning","created":"2023-07-23","cited_by_count":51,"area":null},{"id":"2212.10539","title":"Toward Human Readable Prompt Tuning: Kubrick's The Shining is a good movie, and a good prompt too?","created":"2022-12-20","cited_by_count":49,"area":null},{"id":"2311.17435","title":"MM-Narrator: Narrating Long-form Videos with Multimodal In-Context Learning","created":"2023-11-29","cited_by_count":46,"area":null},{"id":"2305.12586","title":"Enhancing Few-shot Text-to-SQL Capabilities of Large Language Models: A Study on Prompt Design Strategies","created":"2023-05-21","cited_by_count":45,"area":null},{"id":"2305.10847","title":"Large Language Models can be Guided to Evade AI-Generated Text Detection","created":"2023-05-18","cited_by_count":44,"area":null},{"id":"2311.01967","title":"The language of prompting: What linguistic properties make a prompt successful?","created":"2023-11-03","cited_by_count":44,"area":null},{"id":"2404.01266","title":"IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representations","created":"2024-04-01","cited_by_count":38,"area":null},{"id":"2406.10248","title":"On the Worst Prompt Performance of Large Language Models","created":"2024-06-08","cited_by_count":38,"area":null},{"id":"2503.05788","title":"Emergent Abilities in Large Language Models: A Survey","created":"2025-02-28","cited_by_count":37,"area":null},{"id":"2305.14291","title":"Evaluation of African American Language Bias in Natural Language Generation","created":"2023-05-23","cited_by_count":36,"area":null},{"id":"2311.07230","title":"How are Prompts Different in Terms of Sensitivity?","created":"2023-11-13","cited_by_count":35,"area":null},{"id":"2312.02614","title":"Prompt Optimization via Adversarial In-Context Learning","created":"2023-12-05","cited_by_count":33,"area":null},{"id":"2303.10475","title":"Large Language Model Instruction Following: A Survey of Progresses and Challenges","created":"2023-03-18","cited_by_count":31,"area":null},{"id":"2412.04692","title":"Smoothie: Label Free Language Model Routing","created":"2024-12-06","cited_by_count":31,"area":null},{"id":"2308.14321","title":"Leveraging Medical Knowledge Graphs Into Large Language Models for Diagnosis Prediction: Design and Application Study","created":"2023-08-28","cited_by_count":30,"area":null},{"id":"2311.03648","title":"Instruct Me More! Random Prompting for Visual In-Context Learning","created":"2023-11-07","cited_by_count":30,"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":"2310.13620","title":"Bridging Information-Theoretic and Geometric Compression in Language Models","created":"2023-10-20","cited_by_count":26,"area":null},{"id":"2410.14516","title":"Do LLMs \"know\" internally when they follow instructions?","created":"2024-10-18","cited_by_count":26,"area":null},{"id":"2305.18262","title":"Beyond Confidence: Reliable Models Should Also Consider Atypicality","created":"2023-05-29","cited_by_count":25,"area":null},{"id":"2401.06408","title":"AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters","created":"2024-01-12","cited_by_count":22,"area":null},{"id":"2503.01622","title":"DOVE: A Large-Scale Multi-Dimensional Predictions Dataset Towards Meaningful LLM Evaluation","created":"2025-03-03","cited_by_count":21,"area":null},{"id":"2406.10023","title":"Deep Bayesian Active Learning for Preference Modeling in Large Language Models","created":"2024-06-14","cited_by_count":19,"area":null},{"id":"2402.02872","title":"How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric Learning","created":"2024-02-05","cited_by_count":18,"area":null},{"id":"2501.01303","title":"Citations and Trust in LLM Generated Responses","created":"2025-01-02","cited_by_count":18,"area":null},{"id":"2305.14726","title":"In-Context Demonstration Selection with Cross Entropy Difference","created":"2023-05-24","cited_by_count":17,"area":null},{"id":"2312.01700","title":"Data Management For Training Large Language Models: A Survey","created":"2023-12-04","cited_by_count":17,"area":null},{"id":"2405.17264","title":"On the Noise Robustness of In-Context Learning for Text Generation","created":"2024-05-27","cited_by_count":16,"area":null},{"id":"2402.11192","title":"I Learn Better If You Speak My Language: Understanding the Superior Performance of Fine-Tuning Large Language Models with LLM-Generated Responses","created":"2024-02-17","cited_by_count":15,"area":null},{"id":"2408.06518","title":"Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models","created":"2024-08-12","cited_by_count":15,"area":null},{"id":"2312.01082","title":"A Survey on Stability of Learning with Limited Labelled Data and its Sensitivity to the Effects of Randomness","created":"2023-12-02","cited_by_count":14,"area":null},{"id":"2305.14877","title":"Improving Probability-based Prompt Selection Through Unified Evaluation and Analysis","created":"2023-05-24","cited_by_count":13,"area":null},{"id":"2307.00259","title":"InstructEval: Systematic Evaluation of Instruction Selection Methods","created":"2023-07-01","cited_by_count":13,"area":null},{"id":"2311.03498","title":"In-Context Exemplars as Clues to Retrieving from Large Associative Memory","created":"2023-11-06","cited_by_count":13,"area":null},{"id":"2402.12976","title":"The Impact of Demonstrations on Multilingual In-Context Learning: A Multidimensional Analysis","created":"2024-02-20","cited_by_count":13,"area":null},{"id":"2405.10548","title":"Language Models can Exploit Cross-Task In-context Learning for Data-Scarce Novel Tasks","created":"2024-05-17","cited_by_count":13,"area":null},{"id":"2407.15343","title":"Improving Minimum Bayes Risk Decoding with Multi-Prompt","created":"2024-07-22","cited_by_count":13,"area":null},{"id":"2305.14105","title":"CTQScorer: Combining Multiple Features for In-context Example Selection for Machine Translation","created":"2023-05-23","cited_by_count":12,"area":null},{"id":"2406.04823","title":"BERTs are Generative In-Context Learners","created":"2024-06-07","cited_by_count":12,"area":null},{"id":"2408.11854","title":"When Raw Data Prevails: Are Large Language Model Embeddings Effective in Numerical Data Representation for Medical Machine Learning Applications?","created":"2024-08-15","cited_by_count":12,"area":null},{"id":"2404.17120","title":"Talking Nonsense: Probing Large Language Models' Understanding of Adversarial Gibberish Inputs","created":"2024-04-26","cited_by_count":11,"area":null},{"id":"2305.03573","title":"In-context Learning as Maintaining Coherency: A Study of On-the-fly Machine Translation Using Large Language Models","created":"2023-05-05","cited_by_count":10,"area":null},{"id":"2403.16038","title":"Monotonic Paraphrasing Improves Generalization of Language Model Prompting","created":"2024-03-24","cited_by_count":10,"area":null},{"id":"2310.08309","title":"Not All Demonstration Examples are Equally Beneficial: Reweighting Demonstration Examples for In-Context Learning","created":"2023-10-12","cited_by_count":9,"area":null},{"id":"2311.09006","title":"Data Similarity is Not Enough to Explain Language Model Performance","created":"2023-11-15","cited_by_count":9,"area":null},{"id":"2402.06733","title":"NICE: To Optimize In-Context Examples or Not?","created":"2024-02-09","cited_by_count":9,"area":null},{"id":"2403.04445","title":"Classist Tools: Social Class Correlates with Performance in NLP","created":"2024-03-07","cited_by_count":9,"area":null},{"id":"2406.16535","title":"Token-based Decision Criteria Are Suboptimal in In-context Learning","created":"2024-06-24","cited_by_count":9,"area":null},{"id":"2408.02103","title":"Effective Demonstration Annotation for In-Context Learning via Language Model-Based Determinantal Point Process","created":"2024-08-04","cited_by_count":9,"area":null},{"id":"2408.09172","title":"Unlocking the Power of LLM Uncertainty for Active In-Context Example Selection","created":"2024-08-17","cited_by_count":9,"area":null},{"id":"2510.11905","title":"LLM Knowledge is Brittle: Truthfulness Representations Rely on Superficial Resemblance","created":"2025-10-13","cited_by_count":9,"area":null},{"id":"2310.15829","title":"Unnatural language processing: How do language models handle machine-generated prompts?","created":"2023-10-24","cited_by_count":8,"area":null},{"id":"2311.06555","title":"LLMs Learn Task Heuristics from Demonstrations: A Heuristic-Driven Prompting Strategy for Document-Level Event Argument Extraction","created":"2023-11-11","cited_by_count":8,"area":null},{"id":"2406.11243","title":"FamiCom: Further Demystifying Prompts for Language Models with Task-Agnostic Performance Estimation","created":"2024-06-17","cited_by_count":8,"area":null},{"id":"2407.04046","title":"Systematic Task Exploration with LLMs: A Study in Citation Text Generation","created":"2024-07-04","cited_by_count":8,"area":null},{"id":"2411.02018","title":"Shortcut Learning in In-Context Learning: A Survey","created":"2024-11-04","cited_by_count":8,"area":null},{"id":"2510.04950","title":"Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy (short paper)","created":"2025-10-06","cited_by_count":8,"area":null},{"id":"2504.03159","title":"Beyond the Next Token: Towards Prompt-Robust Zero-Shot Classification via Efficient Multi-Token Prediction","created":"2025-04-04","cited_by_count":7,"area":null},{"id":"2310.00385","title":"Dynamic Demonstrations Controller for In-Context Learning","created":"2023-09-30","cited_by_count":6,"area":null},{"id":"2311.01949","title":"Hint-enhanced In-Context Learning wakes Large Language Models up for knowledge-intensive tasks","created":"2023-11-03","cited_by_count":6,"area":null},{"id":"2403.00236","title":"Benchmarking zero-shot stance detection with FlanT5-XXL: Insights from training data, prompting, and decoding strategies into its near-SoTA performance","created":"2024-03-01","cited_by_count":6,"area":null},{"id":"2510.09259","title":"Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models","created":"2025-10-10","cited_by_count":6,"area":null},{"id":"2402.19421","title":"Crafting Knowledge: Exploring the Creative Mechanisms of Chat-Based Search Engines","created":"2024-02-29","cited_by_count":5,"area":null},{"id":"2411.13187","title":"Engagement-Driven Content Generation with Large Language Models","created":"2024-11-20","cited_by_count":5,"area":null},{"id":"2411.18126","title":"Curriculum Demonstration Selection for In-Context Learning","created":"2024-11-27","cited_by_count":5,"area":null},{"id":"2412.02857","title":"Measuring Fingerprints of Web-filtered Text Datasets and Fingerprint Propagation Through Training","created":"2024-12-03","cited_by_count":5,"area":null},{"id":"2503.01345","title":"Same Question, Different Words: A Latent Adversarial Framework for Prompt Robustness","created":"2025-03-03","cited_by_count":5,"area":null},{"id":"2308.02432","title":"Performance of Large Language Models in a Computer Science Degree Program","created":"2023-07-24","cited_by_count":4,"area":null},{"id":"2402.01093","title":"Need a Small Specialized Language Model? Plan Early!","created":"2024-02-02","cited_by_count":4,"area":null},{"id":"2402.02541","title":"Knowledge Generation for Zero-shot Knowledge-based VQA","created":"2024-02-04","cited_by_count":4,"area":null},{"id":"2403.18969","title":"A Survey on Large Language Models from Concept to Implementation","created":"2024-03-27","cited_by_count":4,"area":null},{"id":"2407.01409","title":"Dynamic Few-Shot Learning for Knowledge Graph Question Answering","created":"2024-07-01","cited_by_count":4,"area":null},{"id":"2502.17605","title":"PICASO: Permutation-Invariant Context Composition with State Space Models","created":"2025-02-24","cited_by_count":4,"area":null},{"id":"2503.22040","title":"Navigating the Risks of Using Large Language Models for Text Annotation in Social Science Research","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2505.05946","title":"Full-Parameter Continual Pretraining of Gemma2: Insights into Fluency and Domain Knowledge","created":"2025-05-09","cited_by_count":4,"area":null},{"id":"2307.14632","title":"Metric-Based In-context Learning: A Case Study in Text Simplification","created":"2023-07-27","cited_by_count":3,"area":null},{"id":"2402.02408","title":"GLaPE: Gold Label-agnostic Prompt Evaluation and Optimization for Large Language Model","created":"2024-02-04","cited_by_count":3,"area":null},{"id":"2407.21227","title":"TaskEval: Assessing Difficulty of Code Generation Tasks for Large Language Models","created":"2024-07-30","cited_by_count":3,"area":null},{"id":"2410.10901","title":"3DS: Medical Domain Adaptation of LLMs via Decomposed Difficulty-based Data Selection","created":"2024-10-13","cited_by_count":3,"area":null},{"id":"2410.14049","title":"Learning Metadata-Agnostic Representations for Text-to-SQL In-Context Example Selection","created":"2024-10-17","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":"2502.01804","title":"Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging","created":"2025-02-03","cited_by_count":3,"area":null},{"id":"2502.09589","title":"Logical forms complement probability in understanding language model (and human) performance","created":"2025-02-13","cited_by_count":3,"area":null},{"id":"2504.07288","title":"MDIT: A Model-free Data Interpolation Method for Diverse Instruction Tuning","created":"2025-04-09","cited_by_count":3,"area":null}],"next_cursor":"100"}