{"list":"other","total":45,"rows":[{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"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":"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":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2307.04657","title":"BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset","created":"2023-07-10","cited_by_count":860},{"id":"2303.08896","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","created":"2023-03-15","cited_by_count":810},{"id":"2310.04451","title":"AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models","created":"2023-10-03","cited_by_count":785},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716},{"id":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712},{"id":"2310.06452","title":"Understanding the Effects of RLHF on LLM Generalisation and Diversity","created":"2023-10-10","cited_by_count":396},{"id":"2406.12845","title":"Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts","created":"2024-06-18","cited_by_count":376},{"id":"2310.10501","title":"NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails","created":"2023-10-16","cited_by_count":365},{"id":"2208.03274","title":"A Holistic Approach to Undesired Content Detection in the Real World","created":"2022-08-05","cited_by_count":356},{"id":"2305.17493","title":"The Curse of Recursion: Training on Generated Data Makes Models Forget","created":"2023-05-27","cited_by_count":356},{"id":"2501.00656","title":"2 OLMo 2 Furious","created":"2024-12-31","cited_by_count":340},{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334},{"id":"2402.03744","title":"INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection","created":"2024-02-06","cited_by_count":323},{"id":"2401.00396","title":"RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models","created":"2023-12-31","cited_by_count":283},{"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":"2312.00506","title":"Generative artificial intelligence enhances creativity but reduces the diversity of novel content","created":"2023-12-01","cited_by_count":167},{"id":"2310.15140","title":"AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models","created":"2023-10-23","cited_by_count":111},{"id":"2311.09807","title":"The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text","created":"2023-11-16","cited_by_count":100},{"id":"2411.02193","title":"Improving Steering Vectors by Targeting Sparse Autoencoder Features","created":"2024-11-04","cited_by_count":92},{"id":"2410.02832","title":"FlipAttack: Jailbreak LLMs via Flipping","created":"2024-10-02","cited_by_count":80},{"id":"2404.05090","title":"How Bad is Training on Synthetic Data? A Statistical Analysis of Language Model Collapse","created":"2024-04-07","cited_by_count":79},{"id":"2410.07471","title":"SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection","created":"2024-10-09","cited_by_count":64},{"id":"2505.00047","title":"Base Models Beat Aligned Models at Randomness and Creativity","created":"2025-04-30","cited_by_count":51},{"id":"2403.00553","title":"Standardizing the Measurement of Text Diversity: A Tool and a Comparative Analysis of Scores","created":"2024-03-01","cited_by_count":50},{"id":"2408.11491","title":"SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering","created":"2024-08-21","cited_by_count":50},{"id":"2502.12446","title":"Multi-Attribute Steering of Language Models via Targeted Intervention","created":"2025-02-18","cited_by_count":46},{"id":"2504.04635","title":"Steering off Course: Reliability Challenges in Steering Language Models","created":"2025-04-06","cited_by_count":34},{"id":"2405.13012","title":"Divergent Creativity in Humans and Large Language Models","created":"2024-05-13","cited_by_count":31},{"id":"2502.03708","title":"Toward universal steering and monitoring of AI models","created":"2025-02-06","cited_by_count":30},{"id":"2505.20322","title":"Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms","created":"2025-05-23","cited_by_count":24},{"id":"2405.18822","title":"Toxicity Detection for Free","created":"2024-05-29","cited_by_count":15},{"id":"2505.12831","title":"Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering","created":"2025-05-19","cited_by_count":13},{"id":"2505.16245","title":"Diverse, not Short: A Length-Controlled Data Selection Strategy for Improving Response Diversity of Language Models","created":"2025-05-22","cited_by_count":9},{"id":"2602.02343","title":"Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics","created":"2026-02-02","cited_by_count":9},{"id":"2504.15548","title":"LLM-based Semantic Augmentation for Harmful Content Detection","created":"2025-04-22","cited_by_count":7},{"id":"2507.18043","title":"GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs","created":"2025-07-24","cited_by_count":6}],"next_cursor":null}