{"total":41,"rows":[{"id":"2510.24684","title":"SPICE: Self-Play In Corpus Environments Improves Reasoning","created":"2025-10-28","cited_by_count":83,"area":null},{"id":"2512.02472","title":"Guided Self-Evolving LLMs with Minimal Human Supervision","created":"2025-12-02","cited_by_count":35,"area":null},{"id":"2604.24827","title":"Incompressible Knowledge Probes: Estimating Black-Box LLM Parameter Counts via Factual Capacity","created":"2026-04-27","cited_by_count":17,"area":null},{"id":"2510.04226","title":"What and Whose Knowledge? Measuring Epistemic Diversity in Large Language Models","created":"2025-10-05","cited_by_count":14,"area":null},{"id":"2508.09494","title":"Learning Facts at Scale with Active Reading","created":"2025-08-13","cited_by_count":13,"area":null},{"id":"2508.15390","title":"Exploiting Vocabulary Frequency Imbalance in Language Model Pre-training","created":"2025-08-21","cited_by_count":7,"area":null},{"id":"2603.04956","title":"WaterSIC: Information-Theoretically (Near) Optimal Linear Layer Quantization","created":"2026-03-05","cited_by_count":7,"area":null},{"id":"2507.21914","title":"Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs","created":"2025-07-29","cited_by_count":5,"area":null},{"id":"2512.16059","title":"ContextLeak: Auditing Leakage in Private In-Context Learning Methods","created":"2025-12-18","cited_by_count":4,"area":null},{"id":"2602.15829","title":"Operationalising the Superficial Alignment Hypothesis via Task Complexity","created":"2026-02-17","cited_by_count":4,"area":null},{"id":"2605.09724","title":"Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds","created":"2026-05-10","cited_by_count":4,"area":null},{"id":"2601.14311","title":"Tracing the Data Trail: A Survey of Data Provenance, Transparency and Traceability in LLMs","created":"2026-01-19","cited_by_count":3,"area":null},{"id":"2601.17480","title":"Unintended Memorization of Sensitive Information in Fine-Tuned Language Models","created":"2026-01-24","cited_by_count":3,"area":null},{"id":"2604.08519","title":"Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2509.25380","title":"Predicting Training Re-evaluation Curves Enables Effective Data Curriculums for LLMs","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2602.08901","title":"Mitigating Memorization Where It Happens","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2602.18733","title":"A Prior-Aware Metric for Efficiently Distinguishing Memorization from Generalization in Large Language Models","created":"2026-02-21","cited_by_count":2,"area":null},{"id":"2507.06056","title":"Data Compressibility Quantifies LLM Memorization","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2509.00303","title":"Access Paths for Efficient Ordering with Large Language Models","created":"2025-08-30","cited_by_count":1,"area":null},{"id":"2603.23562","title":"Synthetic Mixed Training: Scaling Parametric Knowledge Acquisition Beyond RAG","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2605.27564","title":"The Future of Facts: Tracing the Factual Generation-Verification Gap","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2606.12764","title":"Detecting Functional Memorization in Code Language Models","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2607.04969","title":"Train Smarter, Not Longer: Memorization-Guided Data Reuse for Efficient LLM Training","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2607.10034","title":"MLPs are Hebbians: Constructing Efficient Fact-Storing MLPs for Transformers","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2608.16645","title":"Reconstruction: A Blind Benchmark for Recovering Research Ideas from Pre-Publication Bibliographies","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2602.03949","title":"Semantic Rate Distortion and Posterior Design: Compute Constraints, Multimodality, and Strategic Inference","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.12005","title":"LaCy: What Small Language Models Can and Should Learn is Not Just a Question of Loss","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.09981","title":"Large Language Models and Book Summarization: Reading or Remembering, Which Is Better?","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2604.18085","title":"Predicting LLM Compression Degradation from Spectral Statistics","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.09031","title":"Spherical Boltzmann machines: a solvable theory of learning and generation in energy-based models","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.14659","title":"Slower Generalization, Faster Memorization: A Sweet Spot in Algorithmic Learning","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.17164","title":"PromptMN: Pseudo Prompting Language","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.08393","title":"Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.21677","title":"Enhancing SLMs for Sustainable Code Optimization in Radio-Astronomy","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2609.04735","title":"Training Large Language Models for Small-Molecule Design with Synthetic Task Scaling","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.13415","title":"Specification Oracles","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.17571","title":"Where Grokking Happens: Distributed Utility and Fourier Recoding Without a Module Switch","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.32293","title":"TRAP: Understanding and Mitigating Privacy Memorization in Language Models","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.32902","title":"Linger and Lose: Knowledge Collapse in Low-Bit Language Models","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.37891","title":"It's All Training: A Fully Synthetic Single-Stage Recipe for LLMs","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00707","title":"Initialization Improves LLM-Driven Discovery","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}