7 papers
Strategy-Induct: Task-Level Strategy Induction for Instruction Generation
Po-Chun Chen, Hen-Hsen Huang, Hsin-Hsi Chen
Designing effective task-level prompts is crucial for improving the performance of Large Language Models (LLMs). While prior work on instruction induction demonstrates that LLMs ca…
Personalized Graph-Empowered Large Language Model for Proactive Information Access
Chia Cheng Chang, An-Zi Yen, Hen-Hsen Huang +1
Since individuals may struggle to recall all life details and often confuse events, establishing a system to assist users in recalling forgotten experiences is essential. While num…
Diverge to Induce Prompting: Multi-Rationale Induction for Zero-Shot Reasoning
Po-Chun Chen, Hen-Hsen Huang, Hsin-Hsi Chen
To address the instability of unguided reasoning paths in standard Chain-of-Thought prompting, recent methods guide large language models (LLMs) by first eliciting a single reasoni…
Visual Lifelog Retrieval through Captioning-Enhanced Interpretation
Yu-Fei Shih, An-Zi Yen, Hen-Hsen Huang +1
People often struggle to remember specific details of past experiences, which can lead to the need to revisit these memories. Consequently, lifelog retrieval has emerged as a cruci…
Do Before You Judge: Self-Reference as a Pathway to Better LLM Evaluation
Wei-Hsiang Lin, Sheng-Lun Wei, Hen-Hsen Huang +1
LLM-as-Judge frameworks are increasingly popular for AI evaluation, yet research findings on the relationship between models' generation and judgment abilities remain inconsistent.…
Diagnosing Model Editing via Knowledge Spectrum
Tsung-Hsuan Pan, Chung-Chi Chen, Hen-Hsen Huang +1
Model editing, the process of efficiently modifying factual knowledge in pre-trained language models, is critical for maintaining their accuracy and relevance. However, existing ed…