{"total":25,"rows":[{"id":"2604.03444","title":"Olmo Hybrid: From Theory to Practice and Back","created":"2026-04-03","cited_by_count":22,"area":null},{"id":"2605.13829","title":"Negation Neglect: When models fail to learn negations in training","created":"2026-05-13","cited_by_count":6,"area":null},{"id":"2608.28945","title":"Automated Researchers Can Mitigate Well-characterized Alignment Failures","created":"2026-08-28","cited_by_count":5,"area":null},{"id":"2605.01417","title":"Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks","created":"2026-05-02","cited_by_count":2,"area":null},{"id":"2605.06901","title":"Reflections and New Directions for Human-Centered Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2606.12360","title":"Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2604.14463","title":"Psychological Steering of Large Language Models","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2604.16197","title":"Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuation","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2605.18607","title":"Forecasting Downstream Performance of LLMs With Proxy Metrics","created":"2026-05-18","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":"2607.01567","title":"Scaling Trends for Lie Detector Oversight in Preference Learning","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2608.05224","title":"Small Foundation Models of Human Cognition and Behaviour","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2608.13482","title":"Synthetic Persona Pretraining: Alignment from Token Zero","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2603.27164","title":"daVinci-LLM:Towards the Science of Pretraining","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2606.01260","title":"IndoBias: A Dual Track Culturally Grounded Benchmark for LLMs Bias Evaluation in Indonesian Languages","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.06622","title":"UnpredictaBench: A Benchmark for Evaluating Distributional Randomness in LLMs","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2608.19857","title":"Inadvertent Context Leakage in Language Models","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.29792","title":"TimeBraid: Unifying Time Series and Language for Understanding and Forecasting","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.00767","title":"Pre-training interventions, ex post facto: Grafting model beliefs across checkpoints","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.07168","title":"A theory of platonic representations in language models","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.07518","title":"Harmful SFT Leaves a Continuous Trace in LLM Checkpoint Updates","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.08670","title":"Principled Under Pressure: Post-Training Decides Whether LLMs Act on Their Own Moral Judgment","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.09183","title":"Q-PACE: Dynamic Precision Allocation for Quantization-Aware Training","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.09384","title":"The Persona Hierarchy Model: Understanding Contextual Generalization in Fine-Tuning LLMs","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.12410","title":"Predicting Alignment Generalization with Value Representations","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}