{"total":152,"rows":[{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601,"area":null},{"id":"2401.11817","title":"Hallucination is Inevitable: An Innate Limitation of Large Language Models","created":"2024-01-22","cited_by_count":332,"area":null},{"id":"2205.11508","title":"Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods","created":"2022-05-23","cited_by_count":149,"area":null},{"id":"2406.16838","title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2207.10551","title":"Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?","created":"2022-07-21","cited_by_count":103,"area":null},{"id":"2102.11972","title":"Do Transformer Modifications Transfer Across Implementations and Applications?","created":"2021-02-23","cited_by_count":87,"area":null},{"id":"2308.01222","title":"Calibration in Deep Learning: A Survey of the State-of-the-Art","created":"2023-08-02","cited_by_count":75,"area":null},{"id":"2107.05768","title":"Combiner: Full Attention Transformer with Sparse Computation Cost","created":"2021-07-12","cited_by_count":64,"area":null},{"id":"2412.16145","title":"Offline Reinforcement Learning for LLM Multi-Step Reasoning","created":"2024-12-20","cited_by_count":54,"area":"lr"},{"id":"2107.11317","title":"Mixed SIGNals: Sign Language Production via a Mixture of Motion Primitives","created":"2021-07-23","cited_by_count":50,"area":null},{"id":"2510.06265","title":"Large Language Models Hallucination: A Comprehensive Survey","created":"2025-10-05","cited_by_count":49,"area":null},{"id":"2302.14383","title":"Linear Spaces of Meanings: Compositional Structures in Vision-Language Models","created":"2023-02-28","cited_by_count":48,"area":"mllm"},{"id":"2407.14937","title":"Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)","created":"2024-07-20","cited_by_count":46,"area":"safety"},{"id":"2104.06893","title":"I Wish I Would Have Loved This One, But I Didn't -- A Multilingual Dataset for Counterfactual Detection in Product Reviews","created":"2021-04-14","cited_by_count":45,"area":null},{"id":"2212.01349","title":"Nonparametric Masked Language Modeling","created":"2022-12-02","cited_by_count":40,"area":null},{"id":"2403.09539","title":"Logits of API-Protected LLMs Leak Proprietary Information","created":"2024-03-14","cited_by_count":40,"area":null},{"id":"2405.17767","title":"Linguistic Collapse: Neural Collapse in (Large) Language Models","created":"2024-05-28","cited_by_count":38,"area":null},{"id":"2507.08802","title":"The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?","created":"2025-07-11","cited_by_count":37,"area":"mechinterp"},{"id":"2510.15511","title":"Language Models are Injective and Hence Invertible","created":"2025-10-17","cited_by_count":35,"area":null},{"id":"2310.01693","title":"Closing the Curious Case of Neural Text Degeneration","created":"2023-10-02","cited_by_count":32,"area":null},{"id":"2404.14994","title":"Transformers Can Represent $n$-gram Language Models","created":"2024-04-23","cited_by_count":32,"area":null},{"id":"2505.18830","title":"On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization","created":"2025-05-24","cited_by_count":31,"area":"lr"},{"id":"2301.02828","title":"Why do Nearest Neighbor Language Models Work?","created":"2023-01-07","cited_by_count":29,"area":"rag"},{"id":"2509.14786","title":"Pre-training under infinite compute","created":"2025-09-18","cited_by_count":29,"area":null},{"id":"2109.03127","title":"Rare Tokens Degenerate All Tokens: Improving Neural Text Generation via Adaptive Gradient Gating for Rare Token Embeddings","created":"2021-09-07","cited_by_count":27,"area":null},{"id":"2101.09048","title":"Selfish Sparse RNN Training","created":"2021-01-22","cited_by_count":26,"area":null},{"id":"2206.06178","title":"Efficient recurrent architectures through activity sparsity and sparse back-propagation through time","created":"2022-06-13","cited_by_count":26,"area":null},{"id":"2408.15417","title":"Implicit Geometry of Next-token Prediction: From Language Sparsity Patterns to Model Representations","created":"2024-08-27","cited_by_count":24,"area":null},{"id":"2303.05759","title":"An Overview on Language Models: Recent Developments and Outlook","created":"2023-03-10","cited_by_count":22,"area":null},{"id":"2404.07647","title":"Why do small language models underperform? Studying Language Model Saturation via the Softmax Bottleneck","created":"2024-04-11","cited_by_count":21,"area":null},{"id":"2406.04289","title":"What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages","created":"2024-06-06","cited_by_count":20,"area":null},{"id":"2510.22980","title":"How Muon's Spectral Design Benefits Generalization: A Study on Imbalanced Data","created":"2025-10-27","cited_by_count":19,"area":null},{"id":"2210.08471","title":"Improving Semantic Matching through Dependency-Enhanced Pre-trained Model with Adaptive Fusion","created":"2022-10-16","cited_by_count":18,"area":null},{"id":"2404.08458","title":"On the Independence Assumption in Neurosymbolic Learning","created":"2024-04-12","cited_by_count":18,"area":null},{"id":"2104.01853","title":"Rethinking Perturbations in Encoder-Decoders for Fast Training","created":"2021-04-05","cited_by_count":17,"area":null},{"id":"2412.14352","title":"A Survey on LLM Inference-Time Self-Improvement","created":"2024-12-18","cited_by_count":17,"area":"synth"},{"id":"2105.03928","title":"Which transformer architecture fits my data? A vocabulary bottleneck in self-attention","created":"2021-05-09","cited_by_count":16,"area":null},{"id":"2411.18553","title":"Retrofitting Large Language Models with Dynamic Tokenization","created":"2024-11-27","cited_by_count":16,"area":null},{"id":"2203.06462","title":"Low-Rank Softmax Can Have Unargmaxable Classes in Theory but Rarely in Practice","created":"2022-03-12","cited_by_count":15,"area":null},{"id":"2211.10265","title":"Context Variance Evaluation of Pretrained Language Models for Prompt-based Biomedical Knowledge Probing","created":"2022-11-18","cited_by_count":15,"area":null},{"id":"2210.05043","title":"Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling","created":"2022-10-10","cited_by_count":14,"area":null},{"id":"2304.13539","title":"Tensor Decomposition for Model Reduction in Neural Networks: A Review","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2306.04039","title":"Revisiting Neural Retrieval on Accelerators","created":"2023-06-06","cited_by_count":14,"area":null},{"id":"2604.25783","title":"Subliminal Steering: Stronger Encoding of Hidden Signals","created":"2026-04-28","cited_by_count":14,"area":"mechinterp"},{"id":"2406.17642","title":"Banishing LLM Hallucinations Requires Rethinking Generalization","created":"2024-06-25","cited_by_count":13,"area":"lr"},{"id":"2310.10443","title":"Taming the Sigmoid Bottleneck: Provably Argmaxable Sparse Multi-Label Classification","created":"2023-10-16","cited_by_count":11,"area":null},{"id":"2302.02060","title":"Representation Deficiency in Masked Language Modeling","created":"2023-02-04","cited_by_count":10,"area":null},{"id":"2510.03669","title":"Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning","created":"2025-10-04","cited_by_count":10,"area":"lr"},{"id":"2505.13111","title":"Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation","created":"2025-05-19","cited_by_count":9,"area":"distill"},{"id":"2506.17090","title":"Better Language Model Inversion by Compactly Representing Next-Token Distributions","created":"2025-06-20","cited_by_count":9,"area":null},{"id":"2510.24966","title":"Sequences of Logits Reveal the Low Rank Structure of Language Models","created":"2025-10-28","cited_by_count":9,"area":null},{"id":"2511.11346","title":"Fast and Expressive Multi-Byte Prediction with Probabilistic Circuits","created":"2025-11-14","cited_by_count":9,"area":null},{"id":"2603.10145","title":"Lost in Backpropagation: The LM Head is a Gradient Bottleneck","created":"2026-03-10","cited_by_count":9,"area":null},{"id":"2305.12289","title":"Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond","created":"2023-05-20","cited_by_count":8,"area":null},{"id":"2602.11683","title":"ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces","created":"2026-02-12","cited_by_count":8,"area":"lr"},{"id":"2103.01819","title":"The Rediscovery Hypothesis: Language Models Need to Meet Linguistics","created":"2021-03-02","cited_by_count":7,"area":null},{"id":"2406.00046","title":"Hate Speech Detection with Generalizable Target-aware Fairness","created":"2024-05-28","cited_by_count":7,"area":null},{"id":"2410.03968","title":"Decoding Game: On Minimax Optimality of Heuristic Text Generation Strategies","created":"2024-10-04","cited_by_count":7,"area":null},{"id":"2410.11451","title":"Tending Towards Stability: Convergence Challenges in Small Language Models","created":"2024-10-15","cited_by_count":7,"area":null},{"id":"2505.19261","title":"Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning","created":"2025-05-25","cited_by_count":7,"area":"diffusion"},{"id":"2506.03700","title":"AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism","created":"2025-06-04","cited_by_count":7,"area":"lr"},{"id":"2508.17821","title":"Limitations of Normalization in Attention Mechanism","created":"2025-08-25","cited_by_count":7,"area":null},{"id":"2103.11399","title":"Learning Calibrated-Guidance for Object Detection in Aerial Images","created":"2021-03-21","cited_by_count":6,"area":null},{"id":"2204.10670","title":"Paramixer: Parameterizing Mixing Links in Sparse Factors Works Better than Dot-Product Self-Attention","created":"2022-04-22","cited_by_count":6,"area":null},{"id":"2305.04782","title":"HistAlign: Improving Context Dependency in Language Generation by Aligning with History","created":"2023-05-08","cited_by_count":6,"area":null},{"id":"2606.00831","title":"Subliminal Learning is a LoRA Artifact","created":"2026-05-30","cited_by_count":6,"area":null},{"id":"2212.11791","title":"Training Integer-Only Deep Recurrent Neural Networks","created":"2022-12-22","cited_by_count":5,"area":null},{"id":"2403.17677","title":"Onboard deep lossless and near-lossless predictive coding of hyperspectral images with line-based attention","created":"2024-03-26","cited_by_count":5,"area":null},{"id":"2405.19222","title":"Lower Bounds on the Expressivity of Recurrent Neural Language Models","created":"2024-05-29","cited_by_count":4,"area":null},{"id":"2406.10267","title":"Unused information in token probability distribution of generative LLM: improving LLM reading comprehension through calculation of expected values","created":"2024-06-11","cited_by_count":4,"area":null},{"id":"2103.15330","title":"Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications","created":"2021-03-29","cited_by_count":3,"area":null},{"id":"2109.09828","title":"iRNN: Integer-only Recurrent Neural Network","created":"2021-09-20","cited_by_count":3,"area":null},{"id":"2110.05409","title":"Breaking the Softmax Bottleneck for Sequential Recommender Systems with Dropout and Decoupling","created":"2021-10-11","cited_by_count":3,"area":null},{"id":"2310.13593","title":"Learning with Unmasked Tokens Drives Stronger Vision Learners","created":"2023-10-20","cited_by_count":3,"area":null},{"id":"2407.04615","title":"On the Low-Rank Parametrization of Reward Models for Controlled Language Generation","created":"2024-07-05","cited_by_count":3,"area":"alignment"},{"id":"2407.15462","title":"Retrieval with Learned Similarities","created":"2024-07-22","cited_by_count":3,"area":null},{"id":"2409.19984","title":"CONTESTS: a Framework for Consistency Testing of Span Probabilities in Language Models","created":"2024-09-30","cited_by_count":3,"area":null},{"id":"2507.18838","title":"Flow Stochastic Segmentation Networks","created":"2025-07-24","cited_by_count":3,"area":null},{"id":"2601.06160","title":"Student Guides Teacher: Weak-to-Strong Inference via Spectral Orthogonal Exploration","created":"2026-01-06","cited_by_count":3,"area":"lr"},{"id":"2101.00153","title":"Graphmax for Text Generation","created":"2021-01-01","cited_by_count":2,"area":null},{"id":"2105.03641","title":"Diversifying Neural Text Generation with Part-of-Speech Guided Softmax and Sampling","created":"2021-05-08","cited_by_count":2,"area":null},{"id":"2110.13229","title":"Distributionally Robust Recurrent Decoders with Random Network Distillation","created":"2021-10-25","cited_by_count":2,"area":null},{"id":"2310.14079","title":"To Copy, or not to Copy; That is a Critical Issue of the Output Softmax Layer in Neural Sequential Recommenders","created":"2023-10-21","cited_by_count":2,"area":null},{"id":"2311.07625","title":"Activity Sparsity Complements Weight Sparsity for Efficient RNN Inference","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2311.09615","title":"On Retrieval Augmentation and the Limitations of Language Model Training","created":"2023-11-16","cited_by_count":2,"area":null},{"id":"2403.11173","title":"Multi-Objective Evolutionary Neural Architecture Search for Recurrent Neural Networks","created":"2024-03-17","cited_by_count":2,"area":null},{"id":"2505.08348","title":"Geometry of Semantics in Next-Token Prediction: How Optimization Implicitly Organizes Linguistic Representations","created":"2025-05-13","cited_by_count":2,"area":null},{"id":"2506.17748","title":"HIDE and Seek: Detecting Hallucinations in Language Models via Decoupled Representations","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2507.10419","title":"Multiple Choice Learning of Low-Rank Adapters for Language Modeling","created":"2025-07-14","cited_by_count":2,"area":null},{"id":"2601.02543","title":"Normalized Conditional Mutual Information Surrogate Loss for Deep Neural Classifiers","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2601.12011","title":"Why Loss Re-weighting Works If You Stop Early: Training Dynamics of Unconstrained Features","created":"2026-01-17","cited_by_count":2,"area":null},{"id":"2601.22040","title":"Leviathan: Decoupling Input and Output Representations in Language Models","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2602.22255","title":"Deep Sequence Modeling with Quantum Dynamics: Language as a Wave Function","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2105.14214","title":"Predictive Representation Learning for Language Modeling","created":"2021-05-29","cited_by_count":1,"area":null},{"id":"2111.01992","title":"Leveraging Advantages of Interactive and Non-Interactive Models for Vector-Based Cross-Lingual Information Retrieval","created":"2021-11-03","cited_by_count":1,"area":null},{"id":"2203.10256","title":"Dependency-based Mixture Language Models","created":"2022-03-19","cited_by_count":1,"area":null},{"id":"2211.03270","title":"Reconciliation of Pre-trained Models and Prototypical Neural Networks in Few-shot Named Entity Recognition","created":"2022-11-07","cited_by_count":1,"area":null},{"id":"2302.02908","title":"LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Retrieval","created":"2023-02-06","cited_by_count":1,"area":null},{"id":"2312.10925","title":"Delving Deeper Into Astromorphic Transformers","created":"2023-12-18","cited_by_count":1,"area":null},{"id":"2402.15814","title":"On Efficiently Representing Regular Languages as RNNs","created":"2024-02-24","cited_by_count":1,"area":null}],"next_cursor":"100"}