{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"1503.02406","title":"Deep Learning and the Information Bottleneck Principle","created":"2015-03-09","cited_by_count":802},{"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":"2305.13300","title":"Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts","created":"2023-05-22","cited_by_count":341},{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334},{"id":"2310.02207","title":"Language Models Represent Space and Time","created":"2023-10-03","cited_by_count":316},{"id":"2306.05540","title":"DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text","created":"2023-05-23","cited_by_count":210},{"id":"2310.16218","title":"Knowledge Editing for Large Language Models: A Survey","created":"2023-10-24","cited_by_count":194},{"id":"2309.13788","title":"Can LLM-Generated Misinformation Be Detected?","created":"2023-09-25","cited_by_count":177},{"id":"2308.08742","title":"PMET: Precise Model Editing in a Transformer","created":"2023-08-17","cited_by_count":173},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163},{"id":"2407.20311","title":"Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process","created":"2024-07-29","cited_by_count":108},{"id":"2311.05656","title":"Combating Misinformation in the Age of LLMs: Opportunities and Challenges","created":"2023-11-09","cited_by_count":95},{"id":"2406.00799","title":"Get my drift? Catching LLM Task Drift with Activation Deltas","created":"2024-06-02","cited_by_count":72},{"id":"2409.03752","title":"Attention Heads of Large Language Models: A Survey","created":"2024-09-05","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":"2311.04661","title":"Massive Editing for Large Language Models via Meta Learning","created":"2023-11-08","cited_by_count":63},{"id":"1802.10399","title":"Compressing Neural Networks using the Variational Information Bottleneck","created":"2018-02-28","cited_by_count":59},{"id":"2410.19750","title":"The Geometry of Concepts: Sparse Autoencoder Feature Structure","created":"2024-10-10","cited_by_count":52},{"id":"2504.02956","title":"Understanding Aha Moments: from External Observations to Internal Mechanisms","created":"2025-04-03","cited_by_count":50},{"id":"1804.08071","title":"Decoupled Networks","created":"2018-04-22","cited_by_count":45},{"id":"2402.10426","title":"DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection","created":"2024-02-16","cited_by_count":41},{"id":"2410.06331","title":"Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing","created":"2024-10-08","cited_by_count":37},{"id":"2504.14218","title":"Understanding the Repeat Curse in Large Language Models from a Feature Perspective","created":"2025-04-19","cited_by_count":37},{"id":"2404.00492","title":"Multi-hop Question Answering under Temporal Knowledge Editing","created":"2024-03-30","cited_by_count":36},{"id":"2502.12904","title":"Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements","created":"2025-02-18","cited_by_count":32},{"id":"2403.18249","title":"Exploring the Deceptive Power of LLM-Generated Fake News: A Study of Real-World Detection Challenges","created":"2024-03-27","cited_by_count":30},{"id":"2211.13290","title":"SEAT: Stable and Explainable Attention","created":"2022-11-23","cited_by_count":25},{"id":"2502.06852","title":"EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification","created":"2025-02-07","cited_by_count":21},{"id":"2312.04333","title":"Is Bigger and Deeper Always Better? Probing LLaMA Across Scales and Layers","created":"2023-12-07","cited_by_count":20},{"id":"2309.08674","title":"Fake News Detectors are Biased against Texts Generated by Large Language Models","created":"2023-09-15","cited_by_count":18},{"id":"2304.03659","title":"Probing Conceptual Understanding of Large Visual-Language Models","created":"2023-04-07","cited_by_count":17},{"id":"2503.00724","title":"Unmasking Digital Falsehoods: A Comparative Analysis of LLM-Based Misinformation Detection Strategies","created":"2025-03-02","cited_by_count":16},{"id":"2505.16557","title":"Is Your LLM-Based Multi-Agent a Reliable Real-World Planner? Exploring Fraud Detection in Travel Planning","created":"2025-05-22","cited_by_count":15},{"id":"2204.06201","title":"Probing for Constituency Structure in Neural Language Models","created":"2022-04-13","cited_by_count":14},{"id":"2502.17899","title":"Can Large Language Models Identify Implicit Suicidal Ideation? An Empirical Evaluation","created":"2025-02-25","cited_by_count":13},{"id":"2505.17712","title":"Understanding How Value Neurons Shape the Generation of Specified Values in LLMs","created":"2025-05-23","cited_by_count":13},{"id":"2506.00894","title":"CODEMENV: Benchmarking Large Language Models on Code Migration","created":"2025-06-01","cited_by_count":13},{"id":"2311.17983","title":"Improving Interpretation Faithfulness for Vision Transformers","created":"2023-11-29","cited_by_count":12},{"id":"2405.15452","title":"Leveraging Logical Rules in Knowledge Editing: A Cherry on the Top","created":"2024-05-24","cited_by_count":12},{"id":"2409.14459","title":"Exploring Multilingual Probing in Large Language Models: A Cross-Language Analysis","created":"2024-09-22","cited_by_count":12},{"id":"2410.03595","title":"Understanding Reasoning in Chain-of-Thought from the Hopfieldian View","created":"2024-10-04","cited_by_count":11},{"id":"2502.09022","title":"Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning","created":"2025-02-13","cited_by_count":11},{"id":"2409.12257","title":"MQA-KEAL: Multi-hop Question Answering under Knowledge Editing for Arabic Language","created":"2024-09-18","cited_by_count":9},{"id":"2506.00829","title":"COMPKE: Complex Question Answering under Knowledge Editing","created":"2025-06-01","cited_by_count":6},{"id":"2406.02335","title":"Probing the Category of Verbal Aspect in Transformer Language Models","created":"2024-06-04","cited_by_count":5},{"id":"2207.03569","title":"Enhanced brain structure-function tethering in transmodal cortex revealed by high-frequency eigenmodes","created":"2022-07-07","cited_by_count":3},{"id":"2412.20637","title":"Knowledge Editing for Large Language Model with Knowledge Neuronal Ensemble","created":"2024-12-30","cited_by_count":3},{"id":"2202.12992","title":"Decomposing past and future: Integrated information decomposition based on shared probability mass exclusions","created":"2022-02-25","cited_by_count":2},{"id":"2410.12011","title":"Pixology: Probing the Linguistic and Visual Capabilities of Pixel-based Language Models","created":"2024-10-15","cited_by_count":2}],"next_cursor":null}