{"list":"other","total":62,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"1807.03888","title":"A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks","created":"2018-07-10","cited_by_count":1485},{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"1706.02690","title":"Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks","created":"2017-06-08","cited_by_count":1328},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207},{"id":"1812.04606","title":"Deep Anomaly Detection with Outlier Exposure","created":"2018-12-11","cited_by_count":942},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"id":"1909.00512","title":"How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings","created":"2019-09-02","cited_by_count":784},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"1703.04009","title":"Automated Hate Speech Detection and the Problem of Offensive Language","created":"2017-03-11","cited_by_count":736},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"2304.07327","title":"OpenAssistant Conversations -- Democratizing Large Language Model Alignment","created":"2023-04-14","cited_by_count":721},{"id":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651},{"id":"2306.05499","title":"Prompt Injection attack against LLM-integrated Applications","created":"2023-06-08","cited_by_count":605},{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561},{"id":"1511.06233","title":"Towards Open Set Deep Networks","created":"2015-11-19","cited_by_count":538},{"id":"2305.13860","title":"Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study","created":"2023-05-23","cited_by_count":498},{"id":"2111.12797","title":"ReAct: Out-of-distribution Detection With Rectified Activations","created":"2021-11-24","cited_by_count":486},{"id":"1906.02845","title":"Likelihood Ratios for Out-of-Distribution Detection","created":"2019-06-07","cited_by_count":453},{"id":"2310.06987","title":"Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation","created":"2023-10-10","cited_by_count":451},{"id":"2002.11297","title":"Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data","created":"2020-02-26","cited_by_count":408},{"id":"2203.10807","title":"ViM: Out-Of-Distribution with Virtual-logit Matching","created":"2022-03-21","cited_by_count":405},{"id":"1903.04561","title":"Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification","created":"2019-03-11","cited_by_count":404},{"id":"2402.12354","title":"LoRA+: Efficient Low Rank Adaptation of Large Models","created":"2024-02-19","cited_by_count":377},{"id":"2106.03004","title":"Exploring the Limits of Out-of-Distribution Detection","created":"2021-06-06","cited_by_count":283},{"id":"2402.05044","title":"SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models","created":"2024-02-07","cited_by_count":228},{"id":"2211.13445","title":"Delving into Out-of-Distribution Detection with Vision-Language Representations","created":"2022-11-24","cited_by_count":216},{"id":"1903.08983","title":"SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval)","created":"2019-03-19","cited_by_count":207},{"id":"2209.15558","title":"Out-of-Distribution Detection and Selective Generation for Conditional Language Models","created":"2022-09-30","cited_by_count":197},{"id":"1811.04110","title":"Reducing Network Agnostophobia","created":"2018-11-09","cited_by_count":165},{"id":"2006.15207","title":"ATOM: Robustifying Out-of-distribution Detection Using Outlier Mining","created":"2020-06-26","cited_by_count":116},{"id":"2006.09273","title":"Density of States Estimation for Out-of-Distribution Detection","created":"2020-06-16","cited_by_count":74},{"id":"2101.03778","title":"Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection","created":"2021-01-11","cited_by_count":70},{"id":"1909.12180","title":"Towards neural networks that provably know when they don't know","created":"2019-09-26","cited_by_count":69},{"id":"2309.14888","title":"Nearest Neighbor Guidance for Out-of-Distribution Detection","created":"2023-09-26","cited_by_count":64},{"id":"2312.11536","title":"Fast Decision Boundary based Out-of-Distribution Detector","created":"2023-12-15","cited_by_count":49},{"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},{"id":"2409.17270","title":"Proof of Thought : Neurosymbolic Program Synthesis allows Robust and Interpretable Reasoning","created":"2024-09-25","cited_by_count":19},{"id":"2308.10261","title":"How Good Are LLMs at Out-of-Distribution Detection?","created":"2023-08-20","cited_by_count":17},{"id":"2404.08679","title":"Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detector","created":"2024-04-07","cited_by_count":11},{"id":"2505.20047","title":"Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks","created":"2025-05-26","cited_by_count":10},{"id":"2410.01322","title":"Forte : Finding Outliers with Representation Typicality Estimation","created":"2024-10-02","cited_by_count":9},{"id":"2503.08023","title":"AdaSCALE: Adaptive Scaling for OOD Detection","created":"2025-03-11","cited_by_count":7},{"id":"2507.20051","title":"$K^4$: Online Log Anomaly Detection Via Unsupervised Typicality Learning","created":"2025-07-26","cited_by_count":6},{"id":"2509.22631","title":"LABELING COPILOT: A Deep Research Agent for Automated Data Curation in Computer Vision","created":"2025-09-26","cited_by_count":6},{"id":"2409.18235","title":"Visual Concept Networks: A Graph-Based Approach to Detecting Anomalous Data in Deep Neural Networks","created":"2024-09-26","cited_by_count":4},{"id":"2502.03323","title":"Out-of-Distribution Detection using Synthetic Data Generation","created":"2025-02-05","cited_by_count":4},{"id":"2509.14297","title":"A Simple and Efficient Jailbreak Method Exploiting LLMs' Helpfulness","created":"2025-09-17","cited_by_count":4},{"id":"2509.22832","title":"Efficient Fine-Grained GPU Performance Modeling for Distributed Deep Learning of LLM","created":"2025-09-26","cited_by_count":4}],"next_cursor":null}