{"total":42,"rows":[{"id":"2506.16640","title":"Long-Context Generalization with Sparse Attention","created":"2025-06-19","cited_by_count":21,"area":null},{"id":"2508.07479","title":"Positional Biases Shift as Inputs Approach Context Window Limits","created":"2025-08-10","cited_by_count":9,"area":null},{"id":"2510.10276","title":"Lost in the Middle: An Emergent Property from Information Retrieval Demands in LLMs","created":"2025-10-11","cited_by_count":9,"area":null},{"id":"2506.15507","title":"Over-squashing in Spatiotemporal Graph Neural Networks","created":"2025-06-18","cited_by_count":6,"area":null},{"id":"2505.16134","title":"Beyond Early-Token Bias: Model-Specific and Language-Specific Position Effects in Multilingual LLMs","created":"2025-05-22","cited_by_count":5,"area":null},{"id":"2506.14092","title":"Fragile Preferences: A Deep Dive Into Order Effects in Large Language Models","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2511.09146","title":"DoPE: Denoising Rotary Position Embedding","created":"2025-11-12","cited_by_count":5,"area":null},{"id":"2602.16837","title":"A Structural Theory of Position Bias in Transformers","created":"2026-02-18","cited_by_count":5,"area":null},{"id":"2504.04372","title":"Assessing the Impact of Code Changes on the Fault Localizability of Large Language Models","created":"2025-04-06","cited_by_count":4,"area":null},{"id":"2603.10123","title":"Lost in the Middle at Birth: An Exact Theory of Transformer Position Bias","created":"2026-03-10","cited_by_count":4,"area":null},{"id":"2508.15815","title":"User-Assistant Bias in LLMs","created":"2025-08-16","cited_by_count":3,"area":null},{"id":"2605.00226","title":"Why Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actions","created":"2026-04-30","cited_by_count":3,"area":null},{"id":"2505.13353","title":"Sense and Sensitivity: Examining the Influence of Semantic Recall on Long Context Code Understanding","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2509.17105","title":"GRPOformer: Advancing Hyperparameter Optimization via Group Relative Policy Optimization","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2511.00180","title":"ParaScopes: What do Language Models Activations Encode About Future Text?","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2607.07678","title":"How Data Shapes RoPE Frequency Usage: From Positional Scale Matching to Length Generalization","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2505.08739","title":"Probability Consistency in Large Language Models: Theoretical Foundations Meet Empirical Discrepancies","created":"2025-05-13","cited_by_count":1,"area":null},{"id":"2509.21042","title":"LayerNorm Induces Recency Bias in Transformer Decoders","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2512.09182","title":"Understanding the Failure Modes of Transformers through the Lens of Graph Neural Networks","created":"2025-12-09","cited_by_count":1,"area":null},{"id":"2601.04098","title":"Layer-wise Positional Bias in Short-Context Language Modeling","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2601.05879","title":"Gender Bias in LLMs: Preliminary Evidence from Shared Parenting Scenario in Czech Family Law","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2601.11920","title":"Enhancing LLM-Based Data Annotation with Error Decomposition","created":"2026-01-17","cited_by_count":1,"area":null},{"id":"2604.19777","title":"Self-Describing Structured Data with Dual-Layer Guidance: A Lightweight Alternative to RAG for Precision Retrieval in Large-Scale LLM Knowledge Navigation","created":"2026-03-28","cited_by_count":1,"area":null},{"id":"2605.08716","title":"Bias by Necessity: Impossibility Theorems for Sequential Processing with Convergent AI and Human Validation","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2508.17126","title":"Token Homogenization under Positional Bias","created":"2025-08-23","cited_by_count":0,"area":null},{"id":"2510.02629","title":"Evaluation Framework for Highlight Explanations of Context Utilisation in Language Models","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2510.08774","title":"Struc-EMB: The Potential of Structure-Aware Encoding in Language Embeddings","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2510.22752","title":"Beyond Semantics: How Temporal Biases Shape Retrieval in Transformer and State-Space Models","created":"2025-10-26","cited_by_count":0,"area":null},{"id":"2601.14522","title":"On the Runway Cascade of Transformers for Language Modeling","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2603.16749","title":"Probing Cultural Signals in Large Language Models through Author Profiling","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.25665","title":"LLM-ReSum: A Framework for LLM Reflective Summarization through Self-Evaluation","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.08539","title":"Continuity Laws for Sequential Models","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.09213","title":"Kinetic theory for Transformers and the lost-in-the-middle phenomenon","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.08105","title":"A Unifying View of Attention Sinks: From Mechanisms to Architectural Interventions","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2606.29139","title":"How Token Influence Decays with Distance: A Green-Function View of Trained Language Models","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.01464","title":"Comparing Architectures for Supervised Political Scaling","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.03711","title":"Attention is Case-Sensitive","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.07798","title":"Climate-ModernBERT: Revisiting Corpus Composition for Domain-Adaptive Continued Pretraining","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.09085","title":"It's Not RoPE that Creates Sinks: The Role of Self-Concentration and Value-Non-Mixing in Attention","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.26718","title":"The Sirens' Song: When Proximal Background Context Overshadows Distant Evidence","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.38109","title":"How Local Mixing Encodes Relative Position in Global NoPE Attention","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.16349","title":"RIFT: Token Influence Follows the Path of Least Resistance","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}