6 papers
Reinforcement Learning with Promising Tokens for Large Language Models
Jing-Cheng Pang, Liang Lu, Xian Tang +4
Reinforcement learning (RL) has emerged as a key paradigm for aligning and optimizing large language models (LLMs). Standard approaches treat the LLM as the policy and apply RL dir…
Let's Simplify Step by Step: Guiding LLM Towards Multilingual Unsupervised Proficiency-Controlled Sentence Simplification
Jingshen Zhang, Xin Ying Qiu, Lifang Lu +4
Large language models demonstrate limited capability in proficiency-controlled sentence simplification, particularly when simplifying across large readability levels. We propose a…
Rethinking Creativity Evaluation: A Critical Analysis of Existing Creativity Evaluations
Li-Chun Lu, Miri Liu, Pin-Chun Lu +3
We examine, analyze, and compare four representative creativity measures--perplexity, LLM-as-a-Judge, the Creativity Index (CI; measuring n-gram overlap with web corpora), and synt…
BILLY: Steering Large Language Models via Merging Persona Vectors for Creative Generation
Tsung-Min Pai, Jui-I Wang, Li-Chun Lu +3
Multi-LLM systems enhance the creativity of large language models by simulating human collective intelligence but suffer from significant drawbacks, such as high computational cost…
Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks
Chien-yu Huang, Wei-Chih Chen, Shu-wen Yang +77
Multimodal foundation models, such as Gemini and ChatGPT, have revolutionized human-machine interactions by seamlessly integrating various forms of data. Developing a universal spo…
Enhancing the Non-Functional Quality Compliance of LLM-Generated Code through Quality-Aware Preference Learning
Yuan Jiang, Yujian Zhang, Liang Lu +7
Large Language Models (LLMs) have been widely adopted in commercial code completion engines, significantly enhancing coding efficiency and productivity. However, even functionally…