{"list":"other","total":59,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1903.02428","title":"Fast Graph Representation Learning with PyTorch Geometric","created":"2019-03-06","cited_by_count":2434},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"2406.12793","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","created":"2024-06-18","cited_by_count":1121},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"id":"2212.03827","title":"Discovering Latent Knowledge in Language Models Without Supervision","created":"2022-12-07","cited_by_count":767},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650},{"id":"1909.03368","title":"Designing and Interpreting Probes with Control Tasks","created":"2019-09-08","cited_by_count":640},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553},{"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":"2408.05147","title":"Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2","created":"2024-08-09","cited_by_count":394},{"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":"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":"2003.12298","title":"Information-Theoretic Probing with Minimum Description Length","created":"2020-03-27","cited_by_count":232},{"id":"2004.03061","title":"Information-Theoretic Probing for Linguistic Structure","created":"2020-04-07","cited_by_count":207},{"id":"1904.12787","title":"Graph Matching Networks for Learning the Similarity of Graph Structured Objects","created":"2019-04-29","cited_by_count":205},{"id":"2406.11944","title":"Transcoders Find Interpretable LLM Feature Circuits","created":"2024-06-17","cited_by_count":200},{"id":"2404.16014","title":"Improving Dictionary Learning with Gated Sparse Autoencoders","created":"2024-04-24","cited_by_count":179},{"id":"2501.16496","title":"Open Problems in Mechanistic Interpretability","created":"2025-01-27","cited_by_count":179},{"id":"2109.04404","title":"All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality","created":"2021-09-09","cited_by_count":156},{"id":"2407.14679","title":"Compact Language Models via Pruning and Knowledge Distillation","created":"2024-07-19","cited_by_count":148},{"id":"1905.11833","title":"Interpreting and improving natural-language processing (in machines) with natural language-processing (in the brain)","created":"2019-05-28","cited_by_count":128},{"id":"2409.17504","title":"HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection","created":"2024-09-26","cited_by_count":99},{"id":"2403.06448","title":"Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models","created":"2024-03-11","cited_by_count":86},{"id":"2401.12255","title":"Instructional Fingerprinting of Large Language Models","created":"2024-01-21","cited_by_count":68},{"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":"2402.16880","title":"BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation","created":"2024-02-18","cited_by_count":45},{"id":"2406.17759","title":"Interpreting Attention Layer Outputs with Sparse Autoencoders","created":"2024-06-25","cited_by_count":43},{"id":"2410.08201","title":"Efficient Dictionary Learning with Switch Sparse Autoencoders","created":"2024-10-10","cited_by_count":39},{"id":"2407.10887","title":"Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique","created":"2024-07-15","cited_by_count":37},{"id":"2401.17671","title":"Contextual Feature Extraction Hierarchies Converge in Large Language Models and the Brain","created":"2024-01-31","cited_by_count":32},{"id":"2311.00306","title":"Probing Explicit and Implicit Gender Bias through LLM Conditional Text Generation","created":"2023-11-01","cited_by_count":31},{"id":"2305.11169","title":"Emergent Representations of Program Semantics in Language Models Trained on Programs","created":"2023-05-18","cited_by_count":30},{"id":"2410.11988","title":"DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models","created":"2024-10-15","cited_by_count":24},{"id":"2406.06950","title":"A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation","created":"2024-06-11","cited_by_count":21},{"id":"2504.07863","title":"Robust Hallucination Detection in LLMs via Adaptive Token Selection","created":"2025-04-10","cited_by_count":19},{"id":"2410.11516","title":"TopoLM: brain-like spatio-functional organization in a topographic language model","created":"2024-10-15","cited_by_count":12},{"id":"2405.17992","title":"fMRI predictors based on language models of increasing complexity recover brain left lateralization","created":"2024-05-28","cited_by_count":8},{"id":"2301.00148","title":"Mapping effective connectivity by virtually perturbing a surrogate brain","created":"2022-12-31","cited_by_count":6},{"id":"2502.20408","title":"Brain-Inspired Exploration of Functional Networks and Key Neurons in Large Language Models","created":"2025-02-13","cited_by_count":5},{"id":"2410.19542","title":"Brain-like Functional Organization within Large Language Models","created":"2024-10-25","cited_by_count":3}],"next_cursor":null}