6 papers
Silicon Sampling via Cross-Survey Transfer
Chan-Tung Ku, Chan Hsu, Pei-Cing Huang +3
Silicon sampling-using large language models (LLMs) to simulate human survey respondents-has emerged as a promising approach for augmenting traditional survey research. However, mo…
ADVENT: LLM-Driven Automatic Predicate Invention for ILP
Tingting Yu, Pei-Cing Huang, Chan Hsu +2
Predicate invention (PI), the creation of new predicates to extend the hypothesis space, remains a critical bottleneck in Inductive Logic Programming (ILP). Existing methods rely o…
Latent Confidence Alignment for LLM Self-Assessment
Ting-Yu Chen, Tingting Yu, Pei-Cing Huang +3
Confidence calibration in large language models (LLMs) is commonly evaluated by comparing predicted confidence with observed accuracy. However, such approaches do not model item di…
ForEx: A Formal Verification Framework for Explainable Reasoning in Logical Fallacy Detection and Annotation
Pei-Cing Huang, Chienyu Liu, Chan Hsu +3
Current evaluations of Large Language Models (LLMs) on logical fallacy detection focus on predicted labels, but do not establish whether those labels are supported by the reasoning…
Towards Simulating Social Influence Dynamics with LLM-based Multi-agents
Hsien-Tsung Lin, Pei-Cing Huang, Chan-Tung Ku +3
Recent advancements in Large Language Models offer promising capabilities to simulate complex human social interactions. We investigate whether LLM-based multi-agent simulations ca…
CodEv: An Automated Grading Framework Leveraging Large Language Models for Consistent and Constructive Feedback
En-Qi Tseng, Pei-Cing Huang, Chan Hsu +3
Grading programming assignments is crucial for guiding students to improve their programming skills and coding styles. This study presents an automated grading framework, CodEv, wh…