Reflections on the Reproducibility of Commercial LLM Performance in Empirical Software Engineering Studies
"研究方法" 相关文章
Why do explanations fail? A typology and discussion on failures in XAI
A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models
Literature Notes
How Much Speculation About LLMs' Limits Is Optimal?
Synthesizing Standalone World-Models, Part 3: Dataset-Assembly
Mind, Culture & Visual Illusions: Dorsa Amir and Chaz Firestone on Visual Illusions
Overhearing LLM Agents: A Survey, Taxonomy, and Roadmap
Understanding the Process of Human-AI Value Alignment
We're Still Doing It (All) Wrong: Recommender Systems, Fifteen Years Later
我退订了 ChatGPT Plus，因为我发现了文科生的 Cursor
The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis
AI能提出诺贝尔奖级别的创意吗？新研究给出了答案
Agent foundations: not really math, not really science
How we spent our first two weeks as an independent AI safety research group
Modeling Interactive Narrative Systems: A Formal Approach
Unjournal evaluation of "Towards best practices in AGI safety & governance" (2023), quick take
The Term 'Agent' Has Been Diluted Beyond Utility and Requires Redefinition
Reproducibility of Machine Learning-Based Fault Detection and Diagnosis for HVAC Systems in Buildings: An Empirical Study
论文润色指令大全！
