{"list":"other","total":153,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"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":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"id":"2312.06681","title":"Steering Llama 2 via Contrastive Activation Addition","created":"2023-12-09","cited_by_count":1085},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"1610.08401","title":"Universal adversarial perturbations","created":"2016-10-26","cited_by_count":784},{"id":"2212.03827","title":"Discovering Latent Knowledge in Language Models Without Supervision","created":"2022-12-07","cited_by_count":767},{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"id":"2301.00234","title":"A Survey on In-context Learning","created":"2022-12-31","cited_by_count":721},{"id":"2208.01066","title":"What Can Transformers Learn In-Context? A Case Study of Simple Function Classes","created":"2022-08-01","cited_by_count":715},{"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":"2211.15661","title":"What learning algorithm is in-context learning? Investigations with linear models","created":"2022-11-28","cited_by_count":684},{"id":"2102.07350","title":"Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm","created":"2021-02-15","cited_by_count":606},{"id":"1905.06316","title":"What do you learn from context? Probing for sentence structure in contextualized word representations","created":"2019-05-15","cited_by_count":438},{"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":"2210.13382","title":"Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task","created":"2022-10-24","cited_by_count":431},{"id":"2402.07927","title":"A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications","created":"2024-02-05","cited_by_count":431},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411},{"id":"2304.08467","title":"Learning to Compress Prompts with Gist Tokens","created":"2023-04-17","cited_by_count":390},{"id":"2002.06305","title":"Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping","created":"2020-02-15","cited_by_count":384},{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"id":"2402.03744","title":"INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection","created":"2024-02-06","cited_by_count":323},{"id":"2310.15916","title":"In-Context Learning Creates Task Vectors","created":"2023-10-24","cited_by_count":312},{"id":"2212.09561","title":"Large Language Models are Better Reasoners with Self-Verification","created":"2022-12-19","cited_by_count":307},{"id":"2312.14925","title":"A Survey of Reinforcement Learning from Human Feedback","created":"2023-12-22","cited_by_count":264},{"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":"2410.02707","title":"LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations","created":"2024-10-03","cited_by_count":244},{"id":"2303.04226","title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","created":"2023-03-07","cited_by_count":224},{"id":"2301.07067","title":"Transformers as Algorithms: Generalization and Stability in In-context Learning","created":"2023-01-17","cited_by_count":222},{"id":"2404.15255","title":"How to use and interpret activation patching","created":"2024-04-23","cited_by_count":214},{"id":"2310.10348","title":"Attribution Patching Outperforms Automated Circuit Discovery","created":"2023-10-16","cited_by_count":209},{"id":"2010.00711","title":"A Survey of the State of Explainable AI for Natural Language Processing","created":"2020-10-01","cited_by_count":206},{"id":"2409.05907","title":"Programming Refusal with Conditional Activation Steering","created":"2024-09-06","cited_by_count":206},{"id":"2212.10559","title":"Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers","created":"2022-12-20","cited_by_count":204},{"id":"2404.03592","title":"ReFT: Representation Finetuning for Language Models","created":"2024-04-04","cited_by_count":197},{"id":"2310.05694","title":"A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics","created":"2023-10-09","cited_by_count":163},{"id":"2410.12877","title":"Improving Instruction-Following in Language Models through Activation Steering","created":"2024-10-15","cited_by_count":160},{"id":"2407.12404","title":"Analyzing the Generalization and Reliability of Steering Vectors","created":"2024-07-17","cited_by_count":143},{"id":"2304.00740","title":"Inspecting and Editing Knowledge Representations in Language Models","created":"2023-04-03","cited_by_count":141},{"id":"2106.13314","title":"Promises and Pitfalls of Black-Box Concept Learning Models","created":"2021-06-24","cited_by_count":131},{"id":"2305.06329","title":"Similarity of Neural Network Models: A Survey of Functional and Representational Measures","created":"2023-05-10","cited_by_count":131},{"id":"2303.07895","title":"The Learnability of In-Context Learning","created":"2023-03-14","cited_by_count":127},{"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":"2205.12685","title":"Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations","created":"2022-05-25","cited_by_count":116},{"id":"2411.14257","title":"Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models","created":"2024-11-21","cited_by_count":115},{"id":"2007.15646","title":"Rewriting a Deep Generative Model","created":"2020-07-30","cited_by_count":107},{"id":"2302.06600","title":"Task-Specific Skill Localization in Fine-tuned Language Models","created":"2023-02-13","cited_by_count":105},{"id":"2411.00027","title":"Personalization of Large Language Models: A Survey","created":"2024-10-29","cited_by_count":104},{"id":"2405.14577","title":"Representation Noising: A Defence Mechanism Against Harmful Finetuning","created":"2024-05-23","cited_by_count":96},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92},{"id":"2411.02193","title":"Improving Steering Vectors by Targeting Sparse Autoencoder Features","created":"2024-11-04","cited_by_count":92},{"id":"1710.10686","title":"Regularization for Deep Learning: A Taxonomy","created":"2017-10-29","cited_by_count":91},{"id":"2402.17811","title":"TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space","created":"2024-02-27","cited_by_count":91},{"id":"2401.11206","title":"InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance","created":"2024-01-20","cited_by_count":83},{"id":"2307.00175","title":"Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks","created":"2023-06-30","cited_by_count":78},{"id":"2406.00034","title":"Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories","created":"2024-05-26","cited_by_count":77},{"id":"2312.03813","title":"Improving Activation Steering in Language Models with Mean-Centring","created":"2023-12-06","cited_by_count":68},{"id":"2502.03407","title":"Detecting Strategic Deception Using Linear Probes","created":"2025-02-05","cited_by_count":68},{"id":"2312.17249","title":"Do Androids Know They're Only Dreaming of Electric Sheep?","created":"2023-12-28","cited_by_count":67},{"id":"2402.16061","title":"How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study","created":"2024-02-25","cited_by_count":64},{"id":"2406.05954","title":"Aligning Large Language Models with Representation Editing: A Control Perspective","created":"2024-06-10","cited_by_count":64},{"id":"2410.12299","title":"Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors","created":"2024-10-16","cited_by_count":63},{"id":"2410.15999","title":"Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering","created":"2024-10-21","cited_by_count":63},{"id":"2312.01037","title":"Eliciting Latent Knowledge from Quirky Language Models","created":"2023-12-02","cited_by_count":62},{"id":"2312.03729","title":"Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?","created":"2023-11-27","cited_by_count":62},{"id":"2312.15223","title":"A Survey on Large Language Models for Software Engineering","created":"2023-12-23","cited_by_count":59},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51},{"id":"2406.15334","title":"Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning","created":"2024-06-21","cited_by_count":50},{"id":"2501.00070","title":"ICLR: In-Context Learning of Representations","created":"2024-12-29","cited_by_count":50},{"id":"2402.11917","title":"A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task","created":"2024-02-19","cited_by_count":49},{"id":"2402.13055","title":"Identifying Semantic Induction Heads to Understand In-Context Learning","created":"2024-02-20","cited_by_count":47},{"id":"2310.09573","title":"Self-Detoxifying Language Models via Toxification Reversal","created":"2023-10-14","cited_by_count":46},{"id":"2406.15518","title":"Steering Without Side Effects: Improving Post-Deployment Control of Language Models","created":"2024-06-21","cited_by_count":46},{"id":"2502.02716","title":"A Unified Understanding and Evaluation of Steering Methods","created":"2025-02-04","cited_by_count":46},{"id":"2309.10312","title":"Rigorously Assessing Natural Language Explanations of Neurons","created":"2023-09-19","cited_by_count":45},{"id":"2402.18048","title":"Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension","created":"2024-02-28","cited_by_count":45},{"id":"2402.14433","title":"A Language Model's Guide Through Latent Space","created":"2024-02-22","cited_by_count":43},{"id":"2207.04153","title":"Probing Classifiers are Unreliable for Concept Removal and Detection","created":"2022-07-08","cited_by_count":41},{"id":"2403.05767","title":"Extending Activation Steering to Broad Skills and Multiple Behaviours","created":"2024-03-09","cited_by_count":40}],"next_cursor":"100"}