{"total":80,"rows":[{"id":"2310.05736","title":"LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models","created":"2023-10-09","cited_by_count":287,"area":null},{"id":"2210.09150","title":"Prompting GPT-3 To Be Reliable","created":"2022-10-17","cited_by_count":260,"area":null},{"id":"2211.13445","title":"Delving into Out-of-Distribution Detection with Vision-Language Representations","created":"2022-11-24","cited_by_count":216,"area":null},{"id":"2209.15558","title":"Out-of-Distribution Detection and Selective Generation for Conditional Language Models","created":"2022-09-30","cited_by_count":197,"area":null},{"id":"2306.01293","title":"LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning","created":"2023-06-02","cited_by_count":107,"area":null},{"id":"2210.10683","title":"Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP","created":"2022-10-19","cited_by_count":102,"area":null},{"id":"2306.04618","title":"Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations","created":"2023-06-07","cited_by_count":97,"area":null},{"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":"2406.02622","title":"Safeguarding Large Language Models: A Survey","created":"2024-06-03","cited_by_count":78,"area":"safety"},{"id":"2211.08073","title":"GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective","created":"2022-11-15","cited_by_count":72,"area":null},{"id":"2306.04459","title":"Uncertainty in Natural Language Processing: Sources, Quantification, and Applications","created":"2023-06-05","cited_by_count":44,"area":null},{"id":"2307.10236","title":"Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Models","created":"2023-07-16","cited_by_count":41,"area":null},{"id":"2304.04521","title":"GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection","created":"2023-04-10","cited_by_count":36,"area":null},{"id":"2305.03236","title":"A Survey on Out-of-Distribution Detection in NLP","created":"2023-05-05","cited_by_count":31,"area":null},{"id":"2305.13282","title":"Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection","created":"2023-05-22","cited_by_count":29,"area":null},{"id":"2409.11884","title":"Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advances","created":"2024-09-18","cited_by_count":26,"area":null},{"id":"2502.00290","title":"Estimating LLM Uncertainty with Evidence","created":"2025-02-01","cited_by_count":26,"area":null},{"id":"2210.15452","title":"Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity","created":"2022-10-20","cited_by_count":25,"area":null},{"id":"2210.12517","title":"Exploring The Landscape of Distributional Robustness for Question Answering Models","created":"2022-10-22","cited_by_count":23,"area":null},{"id":"2212.09171","title":"Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Data","created":"2022-12-18","cited_by_count":21,"area":null},{"id":"2306.15261","title":"A Survey on Out-of-Distribution Evaluation of Neural NLP Models","created":"2023-06-27","cited_by_count":20,"area":null},{"id":"2502.21239","title":"Semantic Volume: Quantifying and Detecting both External and Internal Uncertainty in LLMs","created":"2025-02-28","cited_by_count":20,"area":null},{"id":"2305.14463","title":"ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessment","created":"2023-05-23","cited_by_count":19,"area":null},{"id":"2405.14039","title":"Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoning","created":"2024-05-22","cited_by_count":18,"area":"lr"},{"id":"2308.10261","title":"How Good Are LLMs at Out-of-Distribution Detection?","created":"2023-08-20","cited_by_count":17,"area":null},{"id":"2305.08566","title":"NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist","created":"2023-05-15","cited_by_count":16,"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":"2302.09852","title":"Unsupervised Layer-wise Score Aggregation for Textual OOD Detection","created":"2023-02-20","cited_by_count":15,"area":null},{"id":"2210.09404","title":"Measures of Information Reflect Memorization Patterns","created":"2022-10-17","cited_by_count":12,"area":null},{"id":"2301.02427","title":"Mask-then-Fill: A Flexible and Effective Data Augmentation Framework for Event Extraction","created":"2023-01-06","cited_by_count":12,"area":null},{"id":"2301.12715","title":"Fine-Tuning Deteriorates General Textual Out-of-Distribution Detection by Distorting Task-Agnostic Features","created":"2023-01-30","cited_by_count":12,"area":null},{"id":"2202.00254","title":"Active Learning Over Multiple Domains in Natural Language Tasks","created":"2022-02-01","cited_by_count":11,"area":null},{"id":"2211.11300","title":"Multi-Level Knowledge Distillation for Out-of-Distribution Detection in Text","created":"2022-11-21","cited_by_count":11,"area":"distill"},{"id":"2308.11780","title":"Few-shot Anomaly Detection in Text with Deviation Learning","created":"2023-08-22","cited_by_count":11,"area":null},{"id":"2210.06799","title":"Benchmarking Long-tail Generalization with Likelihood Splits","created":"2022-10-13","cited_by_count":9,"area":null},{"id":"2511.06190","title":"Confidence-Guided Stepwise Model Routing for Cost-Efficient Reasoning","created":"2025-11-09","cited_by_count":9,"area":"lr"},{"id":"2305.00593","title":"Reliable Gradient-free and Likelihood-free Prompt Tuning","created":"2023-04-30","cited_by_count":8,"area":null},{"id":"2510.05782","title":"Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detection","created":"2025-10-07","cited_by_count":7,"area":null},{"id":"2210.07485","title":"Holistic Sentence Embeddings for Better Out-of-Distribution Detection","created":"2022-10-14","cited_by_count":6,"area":null},{"id":"2305.17055","title":"Counterfactuals of Counterfactuals: a back-translation-inspired approach to analyse counterfactual editors","created":"2023-05-26","cited_by_count":6,"area":null},{"id":"2309.06358","title":"Generative Data Augmentation using LLMs improves Distributional Robustness in Question Answering","created":"2023-09-03","cited_by_count":6,"area":null},{"id":"2404.08517","title":"Online Safety Analysis for LLMs: a Benchmark, an Assessment, and a Path Forward","created":"2024-04-12","cited_by_count":6,"area":null},{"id":"2501.00418","title":"Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models","created":"2024-12-31","cited_by_count":6,"area":null},{"id":"2204.05695","title":"Self-Supervised Losses for One-Class Textual Anomaly Detection","created":"2022-04-12","cited_by_count":5,"area":null},{"id":"2210.04802","title":"SimSCOOD: Systematic Analysis of Out-of-Distribution Generalization in Fine-tuned Source Code Models","created":"2022-10-10","cited_by_count":5,"area":null},{"id":"2303.01577","title":"DeepLens: Interactive Out-of-distribution Data Detection in NLP Models","created":"2023-03-02","cited_by_count":5,"area":null},{"id":"2307.07002","title":"Classical Out-of-Distribution Detection Methods Benchmark in Text Classification Tasks","created":"2023-07-13","cited_by_count":5,"area":null},{"id":"2307.09455","title":"Pseudo Outlier Exposure for Out-of-Distribution Detection using Pretrained Transformers","created":"2023-07-18","cited_by_count":5,"area":null},{"id":"2310.05083","title":"FLatS: Principled Out-of-Distribution Detection with Feature-Based Likelihood Ratio Score","created":"2023-10-08","cited_by_count":5,"area":null},{"id":"2308.04025","title":"MSAC: Multiple Speech Attribute Control Method for Reliable Speech Emotion Recognition","created":"2023-08-08","cited_by_count":4,"area":null},{"id":"2310.14211","title":"LUNA: A Model-Based Universal Analysis Framework for Large Language Models","created":"2023-10-22","cited_by_count":4,"area":null},{"id":"2311.03663","title":"Principles from Clinical Research for NLP Model Generalization","created":"2023-11-07","cited_by_count":4,"area":null},{"id":"2211.13527","title":"Beyond Mahalanobis-Based Scores for Textual OOD Detection","created":"2022-11-24","cited_by_count":3,"area":null},{"id":"2408.11252","title":"Counterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in Autoregressive Language Models","created":"2024-08-21","cited_by_count":3,"area":null},{"id":"2506.09093","title":"Merging Smarter, Generalizing Better: Enhancing Model Merging on OOD Data","created":"2025-06-10","cited_by_count":3,"area":null},{"id":"2510.01389","title":"INSIGHT: INference-time Sequence Introspection for Generating Help Triggers in Vision-Language-Action Models","created":"2025-10-01","cited_by_count":3,"area":"vla"},{"id":"2210.02857","title":"Time Will Change Things: An Empirical Study on Dynamic Language Understanding in Social Media Classification","created":"2022-10-06","cited_by_count":2,"area":null},{"id":"2211.04250","title":"DetAIL : A Tool to Automatically Detect and Analyze Drift In Language","created":"2022-11-03","cited_by_count":2,"area":null},{"id":"2310.01448","title":"Meta Semantic Template for Evaluation of Large Language Models","created":"2023-10-01","cited_by_count":2,"area":null},{"id":"2311.06549","title":"Zero-Shot Cross-Lingual Sentiment Classification under Distribution Shift: an Exploratory Study","created":"2023-11-11","cited_by_count":2,"area":null},{"id":"2311.13102","title":"Detecting out-of-distribution text using topological features of transformer-based language models","created":"2023-11-22","cited_by_count":2,"area":null},{"id":"2502.12965","title":"Text Classification Under Class Distribution Shift: A Survey","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2506.00418","title":"Dual Debiasing for Noisy In-Context Learning for Text Generation","created":"2025-05-31","cited_by_count":2,"area":null},{"id":"2201.02993","title":"Rethink the Evaluation for Attack Strength of Backdoor Attacks in Natural Language Processing","created":"2022-01-09","cited_by_count":1,"area":"safety"},{"id":"2211.15718","title":"Contrastive Novelty-Augmented Learning: Anticipating Outliers with Large Language Models","created":"2022-11-28","cited_by_count":1,"area":null},{"id":"2305.14104","title":"Out-of-Distribution Generalization in Text Classification: Past, Present, and Future","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2305.18026","title":"Semantic Role Labeling Guided Out-of-distribution Detection","created":"2023-05-29","cited_by_count":1,"area":null},{"id":"2311.08598","title":"$DA^3$: A Distribution-Aware Adversarial Attack against Language Models","created":"2023-11-14","cited_by_count":1,"area":null},{"id":"2406.12915","title":"How Out-of-Distribution Detection Learning Theory Enhances Transformer: Learnability and Reliability","created":"2024-06-13","cited_by_count":1,"area":null},{"id":"2410.23883","title":"'No' Matters: Out-of-Distribution Detection in Multimodality Long Dialogue","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2305.05759","title":"Ranking & Reweighting Improves Group Distributional Robustness","created":"2023-05-09","cited_by_count":0,"area":null},{"id":"2311.10236","title":"Latent Feature-based Data Splits to Improve Generalisation Evaluation: A Hate Speech Detection Case Study","created":"2023-11-16","cited_by_count":0,"area":"safety"},{"id":"2407.00342","title":"KPC-cF: Aspect-Based Sentiment Analysis via Implicit-Feature Alignment with Corpus Filtering","created":"2024-06-29","cited_by_count":0,"area":null},{"id":"2407.09011","title":"One Stone, Four Birds: A Comprehensive Solution for QA System Using Supervised Contrastive Learning","created":"2024-07-12","cited_by_count":0,"area":null},{"id":"2507.12260","title":"Translationese-index: Using Likelihood Ratios for Graded and Generalizable Measurement of Translationese","created":"2025-07-16","cited_by_count":0,"area":null},{"id":"2601.13122","title":"Responsible AI for General-Purpose Systems: Overview, Challenges, and A Path Forward","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2601.14052","title":"Vision Also You Need: Navigating Out-of-Distribution Detection with Multimodal Large Language Model","created":"2026-01-20","cited_by_count":0,"area":"mllm"},{"id":"2605.00269","title":"Useful Features, Backward Scores: OOD in Language-Model Trajectories","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2608.21043","title":"Evidence-Consistent Generative Detection under Scenario-Level Distribution Shift","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.20299","title":"Not All Layers Are Equal: Dynamic Layer Routing for Reliable CLIP OOD Detection","created":"2026-07-30","cited_by_count":0,"area":null}],"next_cursor":null}