{"list":"other","total":62,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"2211.00593","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","created":"2022-11-01","cited_by_count":1165},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"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":"2312.02119","title":"Tree of Attacks: Jailbreaking Black-Box LLMs Automatically","created":"2023-12-04","cited_by_count":672},{"id":"2309.10253","title":"GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts","created":"2023-09-19","cited_by_count":560},{"id":"2404.01318","title":"JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models","created":"2024-03-28","cited_by_count":536},{"id":"2203.14680","title":"Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space","created":"2022-03-28","cited_by_count":532},{"id":"2308.03825","title":"\"Do Anything Now\": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models","created":"2023-08-07","cited_by_count":489},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422},{"id":"2311.03191","title":"DeepInception: Hypnotize Large Language Model to Be Jailbreaker","created":"2023-11-06","cited_by_count":367},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"id":"1906.04284","title":"Analyzing the Structure of Attention in a Transformer Language Model","created":"2019-06-07","cited_by_count":243},{"id":"2407.04295","title":"Jailbreak Attacks and Defenses Against Large Language Models: A Survey","created":"2024-07-05","cited_by_count":230},{"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":"2307.08715","title":"MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots","created":"2023-07-16","cited_by_count":183},{"id":"1801.06889","title":"Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers","created":"2018-01-21","cited_by_count":117},{"id":"2404.08676","title":"ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming","created":"2024-04-06","cited_by_count":98},{"id":"2310.12505","title":"Attack Prompt Generation for Red Teaming and Defending Large Language Models","created":"2023-10-19","cited_by_count":76},{"id":"2208.07852","title":"Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Models","created":"2022-08-16","cited_by_count":70},{"id":"2406.10794","title":"Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis","created":"2024-06-16","cited_by_count":64},{"id":"1710.06501","title":"Do Convolutional Neural Networks Learn Class Hierarchy?","created":"2017-10-17","cited_by_count":61},{"id":"2305.03210","title":"AttentionViz: A Global View of Transformer Attention","created":"2023-05-04","cited_by_count":50},{"id":"2009.07053","title":"Attention Flows: Analyzing and Comparing Attention Mechanisms in Language Models","created":"2020-09-03","cited_by_count":49},{"id":"2204.09274","title":"Causality-based Neural Network Repair","created":"2022-04-20","cited_by_count":47},{"id":"1710.10777","title":"Understanding Hidden Memories of Recurrent Neural Networks","created":"2017-10-30","cited_by_count":44},{"id":"2401.16765","title":"A Cross-Language Investigation into Jailbreak Attacks in Large Language Models","created":"2024-01-30","cited_by_count":41},{"id":"2406.09289","title":"Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models","created":"2024-06-13","cited_by_count":37},{"id":"1702.01226","title":"Towards Better Analysis of Machine Learning Models: A Visual Analytics Perspective","created":"2017-02-04","cited_by_count":36},{"id":"2406.09265","title":"Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs","created":"2024-06-13","cited_by_count":33},{"id":"2305.13417","title":"VISIT: Visualizing and Interpreting the Semantic Information Flow of Transformers","created":"2023-05-22","cited_by_count":32},{"id":"2001.09395","title":"Analyzing the Noise Robustness of Deep Neural Networks","created":"2020-01-26","cited_by_count":31},{"id":"2310.05771","title":"Foundation Models Meet Visualizations: Challenges and Opportunities","created":"2023-10-09","cited_by_count":31},{"id":"2410.23743","title":"What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective","created":"2024-10-31","cited_by_count":29},{"id":"2103.14625","title":"Dodrio: Exploring Transformer Models with Interactive Visualization","created":"2021-03-26","cited_by_count":28},{"id":"2312.04782","title":"Make Them Spill the Beans! Coercive Knowledge Extraction from (Production) LLMs","created":"2023-12-08","cited_by_count":27},{"id":"2307.07712","title":"Visual Analytics For Machine Learning: A Data Perspective Survey","created":"2023-07-15","cited_by_count":25},{"id":"1907.07296","title":"Explaining Vulnerabilities to Adversarial Machine Learning through Visual Analytics","created":"2019-07-17","cited_by_count":24},{"id":"2411.11114","title":"JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit","created":"2024-11-17","cited_by_count":22},{"id":"2101.00196","title":"On Explaining Your Explanations of BERT: An Empirical Study with Sequence Classification","created":"2021-01-01","cited_by_count":21},{"id":"2206.09355","title":"A Unified Understanding of Deep NLP Models for Text Classification","created":"2022-06-19","cited_by_count":18},{"id":"2408.04619","title":"Transformer Explainer: Learning LLM Transformers with Interactive Visual Explanation and Experimentation","created":"2024-08-08","cited_by_count":10},{"id":"2404.08793","title":"JailbreakLens: Visual Analysis of Jailbreak Attacks Against Large Language Models","created":"2024-04-12","cited_by_count":7},{"id":"2507.21141","title":"The Geometry of Harmfulness in LLMs through Subconcept Probing","created":"2025-07-23","cited_by_count":7},{"id":"2208.08010","title":"ShortcutLens: A Visual Analytics Approach for Exploring Shortcuts in Natural Language Understanding Dataset","created":"2022-08-17","cited_by_count":6},{"id":"2303.02814","title":"Visual Analytics of Neuron Vulnerability to Adversarial Attacks on Convolutional Neural Networks","created":"2023-03-06","cited_by_count":4},{"id":"2305.11364","title":"Visualizing Linguistic Diversity of Text Datasets Synthesized by Large Language Models","created":"2023-05-19","cited_by_count":4},{"id":"2103.14414","title":"HyperSec: Visual Analytics for blockchain security monitoring","created":"2021-03-26","cited_by_count":2},{"id":"2112.10354","title":"Systematic Literature Review on Cyber Situational Awareness Visualizations","created":"2021-12-20","cited_by_count":2},{"id":"2310.01870","title":"DeepDecipher: Accessing and Investigating Neuron Activation in Large Language Models","created":"2023-10-03","cited_by_count":2},{"id":"2311.13656","title":"Panda or not Panda? Understanding Adversarial Attacks with Interactive Visualization","created":"2023-11-22","cited_by_count":2},{"id":"2407.03045","title":"JailbreakHunter: A Visual Analytics Approach for Jailbreak Prompts Discovery from Large-Scale Human-LLM Conversational Datasets","created":"2024-07-03","cited_by_count":2},{"id":"2409.02485","title":"Adversarial Attacks on Machine Learning-Aided Visualizations","created":"2024-09-04","cited_by_count":2},{"id":"2003.03610","title":"Conceptual Model of Visual Analytics for Hands-on Cybersecurity Training","created":"2020-03-07","cited_by_count":1}],"next_cursor":null}