{"list":"other","total":51,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"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":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"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":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"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":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"2308.10248","title":"Steering Language Models With Activation Engineering","created":"2023-08-20","cited_by_count":922},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"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":"2401.05566","title":"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training","created":"2024-01-10","cited_by_count":529},{"id":"1903.08855","title":"Linguistic Knowledge and Transferability of Contextual Representations","created":"2019-03-21","cited_by_count":383},{"id":"2507.21509","title":"Persona Vectors: Monitoring and Controlling Character Traits in Language Models","created":"2025-07-29","cited_by_count":345},{"id":"2310.02949","title":"Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models","created":"2023-10-04","cited_by_count":297},{"id":"2406.15513","title":"PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference","created":"2024-06-20","cited_by_count":261},{"id":"2308.09124","title":"Linearity of Relation Decoding in Transformer Language Models","created":"2023-08-17","cited_by_count":200},{"id":"2310.20624","title":"LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B","created":"2023-10-31","cited_by_count":195},{"id":"1901.05287","title":"Assessing BERT's Syntactic Abilities","created":"2019-01-16","cited_by_count":192},{"id":"2502.17424","title":"Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs","created":"2025-02-24","cited_by_count":172},{"id":"2406.07358","title":"AI Sandbagging: Language Models can Strategically Underperform on Evaluations","created":"2024-06-11","cited_by_count":145},{"id":"2511.18397","title":"Natural Emergent Misalignment from Reward Hacking in Production RL","created":"2025-11-23","cited_by_count":136},{"id":"2505.23836","title":"Large Language Models Often Know When They Are Being Evaluated","created":"2025-05-28","cited_by_count":128},{"id":"1912.01683","title":"Optimal Policies Tend to Seek Power","created":"2019-12-03","cited_by_count":119},{"id":"2506.11613","title":"Model Organisms for Emergent Misalignment","created":"2025-06-13","cited_by_count":91},{"id":"2506.19823","title":"Persona Features Control Emergent Misalignment","created":"2025-06-24","cited_by_count":86},{"id":"2506.11618","title":"Convergent Linear Representations of Emergent Misalignment","created":"2025-06-13","cited_by_count":71},{"id":"2506.13206","title":"Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models","created":"2025-06-16","cited_by_count":65},{"id":"2506.10805","title":"Detecting High-Stakes Interactions with Activation Probes","created":"2025-06-12","cited_by_count":53},{"id":"2105.07109","title":"The Low-Dimensional Linear Geometry of Contextualized Word Representations","created":"2021-05-15","cited_by_count":40},{"id":"2406.12094","title":"Who's asking? User personas and the mechanics of latent misalignment","created":"2024-06-17","cited_by_count":40},{"id":"2507.16795","title":"Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning","created":"2025-07-22","cited_by_count":39},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33},{"id":"2506.05346","title":"Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets","created":"2025-06-05","cited_by_count":20},{"id":"2511.05408","title":"Steering Language Models with Weight Arithmetic","created":"2025-11-07","cited_by_count":20},{"id":"2510.11288","title":"Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs","created":"2025-10-13","cited_by_count":17},{"id":"2508.06249","title":"In-Training Defenses against Emergent Misalignment in Language Models","created":"2025-08-08","cited_by_count":15},{"id":"2603.04069","title":"Monitoring Emergent Reward Hacking During Generation via Internal Activations","created":"2026-03-04","cited_by_count":14},{"id":"2605.00842","title":"Understanding Emergent Misalignment via Feature Superposition Geometry","created":"2026-04-07","cited_by_count":7},{"id":"2602.16931","title":"Narrow Fine-Tuning Erodes Safety Alignment in Vision-Language Agents","created":"2026-02-18","cited_by_count":6},{"id":"2603.20957","title":"Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models","created":"2026-03-21","cited_by_count":6},{"id":"2601.23081","title":"Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures","created":"2026-01-30","cited_by_count":5}],"next_cursor":null}