{"list":"other","total":64,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"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":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"2312.06681","title":"Steering Llama 2 via Contrastive Activation Addition","created":"2023-12-09","cited_by_count":1085},{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2308.10248","title":"Steering Language Models With Activation Engineering","created":"2023-08-20","cited_by_count":922},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546},{"id":"2404.01318","title":"JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models","created":"2024-03-28","cited_by_count":536},{"id":"2308.01263","title":"XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models","created":"2023-08-02","cited_by_count":505},{"id":"2406.05946","title":"Safety Alignment Should Be Made More Than Just a Few Tokens Deep","created":"2024-06-10","cited_by_count":472},{"id":"2310.03684","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","created":"2023-10-05","cited_by_count":469},{"id":"2404.01833","title":"Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack","created":"2024-04-02","cited_by_count":390},{"id":"2402.10260","title":"A StrongREJECT for Empty Jailbreaks","created":"2024-02-15","cited_by_count":385},{"id":"2507.21509","title":"Persona Vectors: Monitoring and Controlling Character Traits in Language Models","created":"2025-07-29","cited_by_count":345},{"id":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322},{"id":"2412.16339","title":"Deliberative Alignment: Reasoning Enables Safer Language Models","created":"2024-12-20","cited_by_count":308},{"id":"2311.08268","title":"A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily","created":"2023-11-14","cited_by_count":259},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258},{"id":"2405.20947","title":"OR-Bench: An Over-Refusal Benchmark for Large Language Models","created":"2024-05-31","cited_by_count":244},{"id":"2205.05124","title":"Extracting Latent Steering Vectors from Pretrained Language Models","created":"2022-05-10","cited_by_count":225},{"id":"2406.18510","title":"WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models","created":"2024-06-26","cited_by_count":223},{"id":"2501.17148","title":"AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders","created":"2025-01-28","cited_by_count":218},{"id":"2409.05907","title":"Programming Refusal with Conditional Activation Steering","created":"2024-09-06","cited_by_count":206},{"id":"2404.03592","title":"ReFT: Representation Finetuning for Language Models","created":"2024-04-04","cited_by_count":197},{"id":"2501.18837","title":"Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming","created":"2025-01-31","cited_by_count":181},{"id":"2407.15549","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","created":"2024-07-22","cited_by_count":173},{"id":"2510.05179","title":"Agentic Misalignment: How LLMs Could Be Insider Threats","created":"2025-10-05","cited_by_count":158},{"id":"2306.14870","title":"Composing Parameter-Efficient Modules with Arithmetic Operations","created":"2023-06-26","cited_by_count":156},{"id":"2408.15221","title":"LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet","created":"2024-08-27","cited_by_count":151},{"id":"2407.12404","title":"Analyzing the Generalization and Reliability of Steering Vectors","created":"2024-07-17","cited_by_count":143},{"id":"2505.23836","title":"Large Language Models Often Know When They Are Being Evaluated","created":"2025-05-28","cited_by_count":128},{"id":"2405.16833","title":"Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models","created":"2024-05-27","cited_by_count":125},{"id":"2406.00045","title":"Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization","created":"2024-05-28","cited_by_count":118},{"id":"2402.11746","title":"Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic","created":"2024-02-19","cited_by_count":112},{"id":"2410.10700","title":"LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts","created":"2024-10-14","cited_by_count":86},{"id":"2407.11969","title":"Does Refusal Training in LLMs Generalize to the Past Tense?","created":"2024-07-16","cited_by_count":79},{"id":"2403.07865","title":"CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion","created":"2024-03-12","cited_by_count":76},{"id":"2412.03556","title":"Best-of-N Jailbreaking","created":"2024-12-04","cited_by_count":76},{"id":"2402.10962","title":"Measuring and Controlling Instruction (In)Stability in Language Model Dialogs","created":"2024-02-13","cited_by_count":53},{"id":"2506.07022","title":"AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint","created":"2025-06-08","cited_by_count":49},{"id":"2406.15518","title":"Steering Without Side Effects: Improving Post-Deployment Control of Language Models","created":"2024-06-21","cited_by_count":46},{"id":"2601.04603","title":"Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks","created":"2026-01-08","cited_by_count":41},{"id":"2504.09466","title":"AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender","created":"2025-04-13","cited_by_count":38},{"id":"2601.10160","title":"Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment","created":"2026-01-15","cited_by_count":33},{"id":"2605.02087","title":"Model Spec Midtraining: Improving How Alignment Training Generalizes","created":"2026-05-03","cited_by_count":20},{"id":"2512.02445","title":"When Refusals Fail: Unstable Safety Mechanisms in Long-Context LLM Agents","created":"2025-12-02","cited_by_count":15},{"id":"1706.03200","title":"Critical Hyper-Parameters: No Random, No Cry","created":"2017-06-10","cited_by_count":8},{"id":"2505.19773","title":"What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMs","created":"2025-05-26","cited_by_count":8},{"id":"2506.00166","title":"Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment","created":"2025-05-30","cited_by_count":6},{"id":"2605.03907","title":"Steer Like the LLM: Activation Steering that Mimics Prompting","created":"2026-05-05","cited_by_count":5},{"id":"2607.26654","title":"Constitutional Midtraining: Content Presence Drives Alignment Gains","created":"2026-07-29","cited_by_count":4},{"id":"2606.06519","title":"SafeGene: Reusable Adapters for Transferable Safety Alignment","created":"2026-06-02","cited_by_count":1},{"id":"2606.15420","title":"Constitutional Value Potentials: reading and steering internal priority margins in language models","created":"2026-06-13","cited_by_count":1}],"next_cursor":null}