{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"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":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","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":"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":"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":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"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":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"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":"2310.03684","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","created":"2023-10-05","cited_by_count":469},{"id":"2310.06987","title":"Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation","created":"2023-10-10","cited_by_count":451},{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401},{"id":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231},{"id":"2310.10348","title":"Attribution Patching Outperforms Automated Circuit Discovery","created":"2023-10-16","cited_by_count":209},{"id":"2207.00112","title":"Language model compression with weighted low-rank factorization","created":"2022-06-30","cited_by_count":195},{"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":"2310.15154","title":"Linear Representations of Sentiment in Large Language Models","created":"2023-10-23","cited_by_count":163},{"id":"2306.17844","title":"The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks","created":"2023-06-30","cited_by_count":156},{"id":"2402.14811","title":"Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking","created":"2024-02-22","cited_by_count":149},{"id":"2310.03708","title":"Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization","created":"2023-10-05","cited_by_count":124},{"id":"2310.08744","title":"Circuit Component Reuse Across Tasks in Transformer Language Models","created":"2023-10-12","cited_by_count":108},{"id":"2306.11222","title":"LoSparse: Structured Compression of Large Language Models based on Low-Rank and Sparse Approximation","created":"2023-06-20","cited_by_count":104},{"id":"2311.09827","title":"Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking","created":"2023-11-16","cited_by_count":81},{"id":"2405.15071","title":"Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization","created":"2024-05-23","cited_by_count":79},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64},{"id":"2403.15447","title":"Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression","created":"2024-03-18","cited_by_count":57},{"id":"2407.10264","title":"What Makes and Breaks Safety Fine-tuning? A Mechanistic Study","created":"2024-07-14","cited_by_count":55},{"id":"2311.01041","title":"Learn to Refuse: Making Large Language Models More Controllable and Reliable through Knowledge Scope Limitation and Refusal Mechanism","created":"2023-11-02","cited_by_count":33},{"id":"2407.04965","title":"Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression","created":"2024-07-06","cited_by_count":33},{"id":"2411.09003","title":"Refusal in LLMs is an Affine Function","created":"2024-11-13","cited_by_count":29},{"id":"2502.01042","title":"SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals","created":"2025-02-03","cited_by_count":29},{"id":"2201.08542","title":"Can Model Compression Improve NLP Fairness","created":"2022-01-21","cited_by_count":20},{"id":"2405.04156","title":"How does GPT-2 Predict Acronyms? Extracting and Understanding a Circuit via Mechanistic Interpretability","created":"2024-05-07","cited_by_count":14},{"id":"2401.00996","title":"Safety and Performance, Why Not Both? Bi-Objective Optimized Model Compression against Heterogeneous Attacks Toward AI Software Deployment","created":"2024-01-02","cited_by_count":4},{"id":"2503.01896","title":"Neuroplasticity and Corruption in Model Mechanisms: A Case Study Of Indirect Object Identification","created":"2025-02-27","cited_by_count":3}],"next_cursor":null}