{"total":50,"rows":[{"id":"2212.03827","title":"Discovering Latent Knowledge in Language Models Without Supervision","created":"2022-12-07","cited_by_count":767,"area":null},{"id":"2212.09741","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","created":"2022-12-19","cited_by_count":333,"area":null},{"id":"2305.13281","title":"LM vs LM: Detecting Factual Errors via Cross Examination","created":"2023-05-22","cited_by_count":156,"area":null},{"id":"2209.07661","title":"On the Relation between Sensitivity and Accuracy in In-context Learning","created":"2022-09-16","cited_by_count":72,"area":null},{"id":"2205.02318","title":"Language Models in the Loop: Incorporating Prompting into Weak Supervision","created":"2022-05-04","cited_by_count":52,"area":null},{"id":"2310.01846","title":"Benchmarking and Improving Generator-Validator Consistency of Language Models","created":"2023-10-03","cited_by_count":44,"area":null},{"id":"2211.05853","title":"Measuring Reliability of Large Language Models through Semantic Consistency","created":"2022-11-10","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":"2309.07929","title":"Prompting Segmentation with Sound Is Generalizable Audio-Visual Source Localizer","created":"2023-09-13","cited_by_count":37,"area":null},{"id":"2403.20014","title":"PURPLE: Making a Large Language Model a Better SQL Writer","created":"2024-03-29","cited_by_count":34,"area":null},{"id":"2212.06202","title":"Doubly Right Object Recognition: A Why Prompt for Visual Rationales","created":"2022-12-12","cited_by_count":29,"area":null},{"id":"2311.01152","title":"Predicting Question-Answering Performance of Large Language Models through Semantic Consistency","created":"2023-11-02","cited_by_count":28,"area":null},{"id":"2310.12836","title":"Knowledge-Augmented Language Model Verification","created":"2023-10-19","cited_by_count":22,"area":null},{"id":"2307.01972","title":"Open-Domain Hierarchical Event Schema Induction by Incremental Prompting and Verification","created":"2023-07-05","cited_by_count":19,"area":null},{"id":"2411.12951","title":"On the Consistency of Video Large Language Models in Temporal Comprehension","created":"2024-11-20","cited_by_count":18,"area":null},{"id":"2210.09175","title":"Learning Instructions with Unlabeled Data for Zero-Shot Cross-Task Generalization","created":"2022-10-17","cited_by_count":15,"area":null},{"id":"2308.09138","title":"Semantic Consistency for Assuring Reliability of Large Language Models","created":"2023-08-17","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":"2501.11041","title":"Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach","created":"2025-01-19","cited_by_count":14,"area":null},{"id":"2210.14803","title":"Don't Prompt, Search! Mining-based Zero-Shot Learning with Language Models","created":"2022-10-26","cited_by_count":13,"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":"2502.15924","title":"Improving Consistency in Large Language Models through Chain of Guidance","created":"2025-02-21","cited_by_count":13,"area":null},{"id":"2405.09593","title":"SQL-to-Schema Enhances Schema Linking in Text-to-SQL","created":"2024-05-15","cited_by_count":12,"area":null},{"id":"2305.01645","title":"Distill or Annotate? Cost-Efficient Fine-Tuning of Compact Models","created":"2023-05-02","cited_by_count":11,"area":null},{"id":"2210.00185","title":"Zemi: Learning Zero-Shot Semi-Parametric Language Models from Multiple Tasks","created":"2022-10-01","cited_by_count":8,"area":null},{"id":"2312.01619","title":"How Many Validation Labels Do You Need? Exploring the Design Space of Label-Efficient Model Ranking","created":"2023-12-04","cited_by_count":8,"area":null},{"id":"2408.01963","title":"A Novel Metric for Measuring the Robustness of Large Language Models in Non-adversarial Scenarios","created":"2024-08-04","cited_by_count":8,"area":null},{"id":"2310.13307","title":"Test-Time Self-Adaptive Small Language Models for Question Answering","created":"2023-10-20","cited_by_count":7,"area":null},{"id":"2409.07072","title":"Latent Space Interpretation for Stylistic Analysis and Explainable Authorship Attribution","created":"2024-09-11","cited_by_count":7,"area":null},{"id":"2306.02569","title":"Prompt to be Consistent is Better than Self-Consistent? Few-Shot and Zero-Shot Fact Verification with Pre-trained Language Models","created":"2023-06-05","cited_by_count":6,"area":null},{"id":"2208.14889","title":"LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data","created":"2022-08-31","cited_by_count":5,"area":null},{"id":"2310.18804","title":"Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting","created":"2023-10-28","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":"2506.00074","title":"Whose Name Comes Up? Auditing LLM-Based Scholar Recommendations","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2211.04668","title":"Zero-Label Prompt Selection","created":"2022-11-09","cited_by_count":4,"area":null},{"id":"2310.15541","title":"Improving Language Models Meaning Understanding and Consistency by Learning Conceptual Roles from Dictionary","created":"2023-10-24","cited_by_count":4,"area":null},{"id":"2404.02054","title":"Deconstructing In-Context Learning: Understanding Prompts via Corruption","created":"2024-04-02","cited_by_count":4,"area":null},{"id":"2407.09030","title":"CAMP: Continuous and Adaptive Learning Model in Pathology","created":"2024-07-12","cited_by_count":4,"area":null},{"id":"2510.14242","title":"Flip-Flop Consistency: Unsupervised Training for Robustness to Prompt Perturbations in LLMs","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2602.04297","title":"Revisiting Prompt Sensitivity in Large Language Models for Text Classification: The Role of Prompt Underspecification","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2308.02862","title":"Improving Generalization of Image Captioning with Unsupervised Prompt Learning","created":"2023-08-05","cited_by_count":2,"area":null},{"id":"2406.19545","title":"Leveraging Machine-Generated Rationales to Facilitate Social Meaning Detection in Conversations","created":"2024-06-27","cited_by_count":2,"area":null},{"id":"2602.08873","title":"Whose Name Comes Up? II: Benchmarking and Intervention-Based Auditing of LLM-Based Scholar Recommendation","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2606.03810","title":"Consistency Training Can Entrench Misalignment","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2402.18807","title":"On the Decision-Making Abilities in Role-Playing using Large Language Models","created":"2024-02-29","cited_by_count":1,"area":null},{"id":"2509.08935","title":"Live(r) Die: Predicting Survival in Colorectal Liver Metastasis","created":"2025-09-10","cited_by_count":1,"area":null},{"id":"2407.18920","title":"Context-Masked Meta-Prompting for Privacy-Preserving LLM Adaptation in Finance","created":"2024-07-09","cited_by_count":0,"area":null},{"id":"2408.14467","title":"Explicit Inductive Inference using Large Language Models","created":"2024-08-26","cited_by_count":0,"area":null},{"id":"2509.19375","title":"Uncertainty-Aware Calibrated Clinical Text Classification with Large Language Models","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2609.01217","title":"Prompt-Robust Language Models: Which Training Strategies Work?","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}