{"total":79,"rows":[{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420,"area":"safety"},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026,"area":"safety"},{"id":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729,"area":"alignment"},{"id":"2305.16934","title":"On Evaluating Adversarial Robustness of Large Vision-Language Models","created":"2023-05-26","cited_by_count":284,"area":"mllm"},{"id":"2201.05955","title":"WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation","created":"2022-01-16","cited_by_count":202,"area":null},{"id":"2306.09442","title":"Explore, Establish, Exploit: Red Teaming Language Models from Scratch","created":"2023-06-15","cited_by_count":114,"area":"safety"},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2504.08165","title":"Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora","created":"2025-04-10","cited_by_count":88,"area":null},{"id":"2205.01663","title":"Adversarial Training for High-Stakes Reliability","created":"2022-05-03","cited_by_count":60,"area":null},{"id":"2203.12942","title":"Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets","created":"2022-03-24","cited_by_count":54,"area":null},{"id":"2301.12868","title":"On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codex","created":"2023-01-30","cited_by_count":41,"area":null},{"id":"2107.07261","title":"Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills","created":"2021-07-15","cited_by_count":39,"area":null},{"id":"2305.17444","title":"Query-Efficient Black-Box Red Teaming via Bayesian Optimization","created":"2023-05-27","cited_by_count":32,"area":"safety"},{"id":"2112.09062","title":"Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistants","created":"2021-12-16","cited_by_count":31,"area":null},{"id":"2110.07596","title":"Retrieval-guided Counterfactual Generation for QA","created":"2021-10-14","cited_by_count":29,"area":null},{"id":"2404.13968","title":"Protecting Your LLMs with Information Bottleneck","created":"2024-04-22","cited_by_count":29,"area":"safety"},{"id":"2210.03992","title":"Generative Language Models for Paragraph-Level Question Generation","created":"2022-10-08","cited_by_count":28,"area":null},{"id":"2410.17952","title":"SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains","created":"2024-10-23","cited_by_count":28,"area":"rag"},{"id":"2211.08264","title":"QAmeleon: Multilingual QA with Only 5 Examples","created":"2022-11-15","cited_by_count":25,"area":null},{"id":"2210.04873","title":"CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation","created":"2022-10-10","cited_by_count":24,"area":null},{"id":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"area":null},{"id":"2106.08190","title":"Question Answering Infused Pre-training of General-Purpose Contextualized Representations","created":"2021-06-15","cited_by_count":19,"area":null},{"id":"2406.09250","title":"MirrorCheck: Efficient Adversarial Defense for Vision-Language Models","created":"2024-06-13","cited_by_count":19,"area":"mllm"},{"id":"2405.09113","title":"Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization","created":"2024-05-15","cited_by_count":18,"area":"safety"},{"id":"2310.00322","title":"Evolving Diverse Red-team Language Models in Multi-round Multi-agent Games","created":"2023-09-30","cited_by_count":17,"area":"agents"},{"id":"2204.01906","title":"Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks","created":"2022-04-05","cited_by_count":16,"area":null},{"id":"2305.17002","title":"An Empirical Comparison of LM-based Question and Answer Generation Methods","created":"2023-05-26","cited_by_count":15,"area":null},{"id":"2504.11373","title":"Cancer-Myth: Evaluating Large Language Models on Patient Questions with False Presuppositions","created":"2025-04-15","cited_by_count":15,"area":null},{"id":"2208.03197","title":"Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey","created":"2022-08-05","cited_by_count":14,"area":null},{"id":"2403.19559","title":"Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset","created":"2024-03-28","cited_by_count":13,"area":null},{"id":"2212.10002","title":"Defending Against Disinformation Attacks in Open-Domain Question Answering","created":"2022-12-20","cited_by_count":12,"area":null},{"id":"2310.09624","title":"ASSERT: Automated Safety Scenario Red Teaming for Evaluating the Robustness of Large Language Models","created":"2023-10-14","cited_by_count":12,"area":"safety"},{"id":"2305.17416","title":"A Practical Toolkit for Multilingual Question and Answer Generation","created":"2023-05-27","cited_by_count":10,"area":null},{"id":"2502.15435","title":"Single-pass Detection of Jailbreaking Input in Large Language Models","created":"2025-02-21","cited_by_count":10,"area":"alignment"},{"id":"2309.12426","title":"Can LLMs Augment Low-Resource Reading Comprehension Datasets? Opportunities and Challenges","created":"2023-09-21","cited_by_count":9,"area":null},{"id":"2305.07984","title":"SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples","created":"2023-05-13","cited_by_count":8,"area":null},{"id":"2212.01692","title":"Can In-context Learners Learn a Reasoning Concept from Demonstrations?","created":"2022-12-03","cited_by_count":7,"area":"lr"},{"id":"2310.13505","title":"Robust Training for Conversational Question Answering Models with Reinforced Reformulation Generation","created":"2023-10-20","cited_by_count":7,"area":null},{"id":"2406.16342","title":"Is your benchmark truly adversarial? AdvScore: Evaluating Human-Grounded Adversarialness","created":"2024-06-24","cited_by_count":7,"area":null},{"id":"2407.01137","title":"An Empirical Comparison of Generative Approaches for Product Attribute-Value Identification","created":"2024-07-01","cited_by_count":7,"area":null},{"id":"2304.01922","title":"Resources and Few-shot Learners for In-context Learning in Slavic Languages","created":"2023-04-04","cited_by_count":6,"area":null},{"id":"2305.11603","title":"Attributable and Scalable Opinion Summarization","created":"2023-05-19","cited_by_count":6,"area":null},{"id":"2306.04535","title":"PromptAttack: Probing Dialogue State Trackers with Adversarial Prompts","created":"2023-06-07","cited_by_count":6,"area":"safety"},{"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":"2311.07424","title":"Hallucination Augmented Recitations for Language Models","created":"2023-11-13","cited_by_count":6,"area":null},{"id":"2210.12902","title":"Event-Centric Question Answering via Contrastive Learning and Invertible Event Transformation","created":"2022-10-24","cited_by_count":5,"area":null},{"id":"2302.10291","title":"Can Large Language Models Change User Preference Adversarially?","created":"2023-01-05","cited_by_count":5,"area":"safety"},{"id":"2407.15239","title":"Benchmark Granularity and Model Robustness for Image-Text Retrieval","created":"2024-07-21","cited_by_count":5,"area":"mllm"},{"id":"2601.13518","title":"AgenticRed: Evolving Agentic Systems for Red-Teaming","created":"2026-01-20","cited_by_count":5,"area":"agents"},{"id":"2209.01824","title":"A Survey on Measuring and Mitigating Reasoning Shortcuts in Machine Reading Comprehension","created":"2022-09-05","cited_by_count":4,"area":null},{"id":"2210.13778","title":"IDK-MRC: Unanswerable Questions for Indonesian Machine Reading Comprehension","created":"2022-10-25","cited_by_count":4,"area":null},{"id":"2211.03462","title":"NAPG: Non-Autoregressive Program Generation for Hybrid Tabular-Textual Question Answering","created":"2022-11-07","cited_by_count":4,"area":null},{"id":"2209.02812","title":"Increasing Adverse Drug Events extraction robustness on social media: case study on negation and speculation","created":"2022-09-06","cited_by_count":3,"area":null},{"id":"2305.18503","title":"From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework","created":"2023-05-29","cited_by_count":3,"area":null},{"id":"2310.00892","title":"No Offense Taken: Eliciting Offensiveness from Language Models","created":"2023-10-02","cited_by_count":3,"area":"safety"},{"id":"2502.07164","title":"Does Training on Synthetic Data Make Models Less Robust?","created":"2025-02-11","cited_by_count":3,"area":"synth"},{"id":"2211.08850","title":"Consecutive Question Generation via Dynamic Multitask Learning","created":"2022-11-16","cited_by_count":2,"area":null},{"id":"2211.16971","title":"A Pipeline for Generating, Annotating and Employing Synthetic Data for Real World Question Answering","created":"2022-11-30","cited_by_count":2,"area":null},{"id":"2305.17197","title":"Entailment as Robust Self-Learner","created":"2023-05-26","cited_by_count":2,"area":null},{"id":"2403.08425","title":"Specification Overfitting in Artificial Intelligence","created":"2024-03-13","cited_by_count":2,"area":null},{"id":"2403.09703","title":"Concept-aware Data Construction Improves In-context Learning of Language Models","created":"2024-03-08","cited_by_count":2,"area":null},{"id":"2601.19051","title":"Proactive Hardening of LLM Defenses with HASTE","created":"2026-01-27","cited_by_count":2,"area":"safety"},{"id":"2210.13678","title":"Bridging the Training-Inference Gap for Dense Phrase Retrieval","created":"2022-10-25","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":"2401.11185","title":"How the Advent of Ubiquitous Large Language Models both Stymie and Turbocharge Dynamic Adversarial Question Generation","created":"2024-01-20","cited_by_count":1,"area":null},{"id":"2406.12381","title":"QOG:Question and Options Generation based on Language Model","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2410.18114","title":"Bridging Today and the Future of Humanity: AI Safety in 2024 and Beyond","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2504.01533","title":"LightDefense: A Lightweight Uncertainty-Driven Defense against Jailbreaks via Shifted Token Distribution","created":"2025-04-02","cited_by_count":1,"area":"safety"},{"id":"2506.14587","title":"SCISSOR: Mitigating Semantic Bias through Cluster-Aware Siamese Networks for Robust Classification","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2202.11865","title":"Using calibrator to improve robustness in Machine Reading Comprehension","created":"2022-02-24","cited_by_count":0,"area":null},{"id":"2206.14272","title":"Collecting high-quality adversarial data for machine reading comprehension tasks with humans and models in the loop","created":"2022-06-28","cited_by_count":0,"area":null},{"id":"2207.00187","title":"An Understanding-Oriented Robust Machine Reading Comprehension Model","created":"2022-07-01","cited_by_count":0,"area":null},{"id":"2305.13775","title":"Concept-aware Training Improves In-context Learning Ability of Language Models","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2310.19403","title":"A Lightweight Method to Generate Unanswerable Questions in English","created":"2023-10-30","cited_by_count":0,"area":null},{"id":"2402.02932","title":"Domain Adaptation of Multilingual Semantic Search -- Literature Review","created":"2024-02-05","cited_by_count":0,"area":null},{"id":"2402.03627","title":"Partially Recentralization Softmax Loss for Vision-Language Models Robustness","created":"2024-02-06","cited_by_count":0,"area":"mllm"},{"id":"2404.19316","title":"QLSC: A Query Latent Semantic Calibrator for Robust Extractive Question Answering","created":"2024-04-30","cited_by_count":0,"area":null},{"id":"2409.19766","title":"Towards Robust Extractive Question Answering Models: Rethinking the Training Methodology","created":"2024-09-29","cited_by_count":0,"area":null},{"id":"2605.06835","title":"On Privacy in Data-Space Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metrics","created":"2026-05-07","cited_by_count":0,"area":null}],"next_cursor":null}