4 papers
Prune, Interpret, Evaluate: A Cross-Layer Transcoder-Native Framework for Efficient Circuit Discovery via Feature Attribution
Qinhao Chen, Linyang He, Nima Mesgarani
Existing feature-interpretation pipelines typically operate on uniformly sampled units or exhaustive feature sets, incurring massive costs on units irrelevant to target behaviors.…
Evaluating 21st-Century Competencies in Postsecondary Curricula with Large Language Models: Performance Benchmarking and Reasoning-Based Prompting Strategies
Zhen Xu, Xin Guan, Chenxi Shi +2
The growing emphasis on 21st-century competencies in postsecondary education, intensified by the transformative impact of generative AI, underscores the need to evaluate how these…
Whose Personae? Synthetic Persona Experiments in LLM Research and Pathways to Transparency
Jan Batzner, Volker Stocker, Bingjun Tang +4
Synthetic personae experiments have become a prominent method in Large Language Model alignment research, yet the representativeness and ecological validity of these personae vary…
PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowcharts
Ming Zhang, Yuhui Wang, Yujiong Shen +16
Process-driven dialogue systems, which operate under strict predefined process constraints, are essential in customer service and equipment maintenance scenarios. Although Large La…