{"list":"other","total":75,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"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":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"id":"1912.02164","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","created":"2019-12-04","cited_by_count":799},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716},{"id":"1511.06732","title":"Sequence Level Training with Recurrent Neural Networks","created":"2015-11-20","cited_by_count":576},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553},{"id":"2105.03023","title":"DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts","created":"2021-05-07","cited_by_count":441},{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435},{"id":"1512.09300","title":"Autoencoding beyond pixels using a learned similarity metric","created":"2015-12-31","cited_by_count":407},{"id":"2407.14435","title":"Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders","created":"2024-07-19","cited_by_count":300},{"id":"2402.17762","title":"Massive Activations in Large Language Models","created":"2024-02-27","cited_by_count":294},{"id":"2404.02060","title":"Long-context LLMs Struggle with Long In-context Learning","created":"2024-04-02","cited_by_count":286},{"id":"2009.05041","title":"Understanding the Role of Individual Units in a Deep Neural Network","created":"2020-09-10","cited_by_count":255},{"id":"2311.06668","title":"In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering","created":"2023-11-11","cited_by_count":245},{"id":"1906.04284","title":"Analyzing the Structure of Attention in a Transformer Language Model","created":"2019-06-07","cited_by_count":243},{"id":"2501.17148","title":"AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders","created":"2025-01-28","cited_by_count":218},{"id":"1312.5663","title":"k-Sparse Autoencoders","created":"2013-12-19","cited_by_count":215},{"id":"2404.16014","title":"Improving Dictionary Learning with Gated Sparse Autoencoders","created":"2024-04-24","cited_by_count":179},{"id":"2006.14032","title":"Compositional Explanations of Neurons","created":"2020-06-24","cited_by_count":172},{"id":"2205.03401","title":"The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning","created":"2022-05-06","cited_by_count":169},{"id":"1909.00015","title":"Adaptively Sparse Transformers","created":"2019-08-30","cited_by_count":155},{"id":"2304.00740","title":"Inspecting and Editing Knowledge Representations in Language Models","created":"2023-04-03","cited_by_count":141},{"id":"2201.05337","title":"A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models","created":"2022-01-14","cited_by_count":129},{"id":"2012.11635","title":"A Distributional Approach to Controlled Text Generation","created":"2020-12-21","cited_by_count":119},{"id":"2103.15949","title":"Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors","created":"2021-03-29","cited_by_count":108},{"id":"2401.03729","title":"The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performance","created":"2024-01-08","cited_by_count":100},{"id":"2411.11296","title":"Steering Language Model Refusal with Sparse Autoencoders","created":"2024-11-18","cited_by_count":95},{"id":"2411.02193","title":"Improving Steering Vectors by Targeting Sparse Autoencoder Features","created":"2024-11-04","cited_by_count":92},{"id":"2311.02262","title":"Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs","created":"2023-11-03","cited_by_count":91},{"id":"2505.20063","title":"SAEs Are Good for Steering -- If You Select the Right Features","created":"2025-05-26","cited_by_count":78},{"id":"2210.01892","title":"Polysemanticity and Capacity in Neural Networks","created":"2022-10-04","cited_by_count":77},{"id":"2305.12798","title":"Word Embeddings Are Steers for Language Models","created":"2023-05-22","cited_by_count":70},{"id":"2203.13299","title":"Mix and Match: Learning-free Controllable Text Generation using Energy Language Models","created":"2022-03-24","cited_by_count":66},{"id":"2112.08348","title":"Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts","created":"2021-12-15","cited_by_count":64},{"id":"2410.15999","title":"Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering","created":"2024-10-21","cited_by_count":63},{"id":"2502.03714","title":"Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment","created":"2025-02-06","cited_by_count":62},{"id":"2502.12446","title":"Multi-Attribute Steering of Language Models via Targeted Intervention","created":"2025-02-18","cited_by_count":46},{"id":"2503.18878","title":"I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders","created":"2025-03-24","cited_by_count":45},{"id":"2504.14492","title":"FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering","created":"2025-04-20","cited_by_count":40},{"id":"2502.11356","title":"SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models","created":"2025-02-17","cited_by_count":34},{"id":"2502.03708","title":"Toward universal steering and monitoring of AI models","created":"2025-02-06","cited_by_count":30},{"id":"2410.05459","title":"From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency","created":"2024-10-07","cited_by_count":29},{"id":"2502.18862","title":"One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs","created":"2025-02-26","cited_by_count":29},{"id":"2505.16188","title":"SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models","created":"2025-05-22","cited_by_count":29},{"id":"2502.04382","title":"Sparse Autoencoders for Hypothesis Generation","created":"2025-02-05","cited_by_count":26},{"id":"1702.02429","title":"Trainable Greedy Decoding for Neural Machine Translation","created":"2017-02-08","cited_by_count":23},{"id":"2502.15576","title":"Interpreting and Steering LLMs with Mutual Information-based Explanations on Sparse Autoencoders","created":"2025-02-21","cited_by_count":21},{"id":"2505.12025","title":"Spotlight Your Instructions: Instruction-following with Dynamic Attention Steering","created":"2025-05-17","cited_by_count":21},{"id":"1402.3337","title":"Zero-bias autoencoders and the benefits of co-adapting features","created":"2014-02-13","cited_by_count":15},{"id":"2410.01280","title":"Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models","created":"2024-10-02","cited_by_count":15},{"id":"2601.03595","title":"Controllable LLM Reasoning via Sparse Autoencoder-Based Steering","created":"2026-01-07","cited_by_count":15},{"id":"2505.05111","title":"Unveiling Language-Specific Features in Large Language Models via Sparse Autoencoders","created":"2025-05-08","cited_by_count":13},{"id":"2507.13410","title":"Causal Language Control in Multilingual Transformers via Sparse Feature Steering","created":"2025-07-17","cited_by_count":12},{"id":"2508.12535","title":"CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features","created":"2025-08-18","cited_by_count":12},{"id":"2509.23799","title":"Enhancing LLM Steering through Sparse Autoencoder-Based Vector Refinement","created":"2025-09-28","cited_by_count":10},{"id":"2512.24574","title":"Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time","created":"2025-12-31","cited_by_count":10},{"id":"2505.15038","title":"Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering","created":"2025-05-21","cited_by_count":9},{"id":"2502.01179","title":"Joint Localization and Activation Editing for Low-Resource Fine-Tuning","created":"2025-02-03","cited_by_count":8},{"id":"2602.00333","title":"Efficient and accurate steering of Large Language Models through attention-guided feature learning","created":"2026-01-30","cited_by_count":8},{"id":"2406.15275","title":"How language models extrapolate outside the training data: A case study in Textualized Gridworld","created":"2024-06-21","cited_by_count":7},{"id":"2510.05498","title":"Prototype-Based Dynamic Steering for Large Language Models","created":"2025-10-07","cited_by_count":6},{"id":"2512.10805","title":"Interpretable and Steerable Concept Bottleneck Sparse Autoencoders","created":"2025-12-11","cited_by_count":6},{"id":"2510.01246","title":"A Comparative Analysis of Sparse Autoencoder and Activation Difference in Language Model Steering","created":"2025-09-24","cited_by_count":4},{"id":"2603.03031","title":"Step-Level Sparse Autoencoder for Reasoning Process Interpretation","created":"2026-03-03","cited_by_count":3}],"next_cursor":null}