31 citations · 44 across the 18 of their papers we have counts for
10 papers · 1 filter
PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization
Han Jiang, Dongyao Zhu, Xiaoyuan Yi +3
In-Context Learning has shown great potential for aligning Large Language Models (LLMs) with human values, helping reduce harmful outputs and accommodate diverse preferences withou…
CAReDiO: Cultural Alignment via Representativeness and Distinctiveness Guided Data Optimization
Jing Yao, Xiaoyuan Yi, Jindong Wang +2
As Large Language Models (LLMs) are deployed across diverse regions, aligning them with pluralistic cultures is crucial for improving user engagement and mitigating cultural confli…
CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses
Jing Yao, Xiaoyuan Yi, Xing Xie
The rapid progress in Large Language Models (LLMs) poses potential risks such as generating unethical content. Assessing LLMs' values can help expose their misalignment, but relies…
Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing
Han Jiang, Xiaoyuan Yi, Zhihua Wei +3
Warning: Contains harmful model outputs. Despite significant advancements, the propensity of Large Language Models (LLMs) to generate harmful and unethical content poses critical c…
ToViLaG: Your Visual-Language Generative Model is Also An Evildoer
Xinpeng Wang, Xiaoyuan Yi, Han Jiang +3
Warning: this paper includes model outputs showing offensive content. Recent large-scale Visual-Language Generative Models (VLGMs) have achieved unprecedented improvement in multim…
CDEval: A Benchmark for Measuring the Cultural Dimensions of Large Language Models
Yuhang Wang, Yanxu Zhu, Chao Kong +4
As the scaling of Large Language Models (LLMs) has dramatically enhanced their capabilities, there has been a growing focus on the alignment problem to ensure their responsible and…
Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning
Shitong Duan, Xiaoyuan Yi, Peng Zhang +3
Large Language Models (LLMs) have made unprecedented breakthroughs, yet their increasing integration into everyday life might raise societal risks due to generated unethical conten…
KEST: Kernel Distance Based Efficient Self-Training for Improving Controllable Text Generation
Yuxi Feng, Xiaoyuan Yi, Laks V. S. Lakshmanan +1
Self-training (ST) has come to fruition in language understanding tasks by producing pseudo labels, which reduces the labeling bottleneck of language model fine-tuning. Nevertheles…
Evade the Trap of Mediocrity: Promoting Diversity and Novelty in Text Generation via Concentrating Attention
Wenhao Li, Xiaoyuan Yi, Jinyi Hu +2
Recently, powerful Transformer architectures have proven superior in generating high-quality sentences. Nevertheless, these models tend to produce dull high-frequency phrases, seve…
Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization
Zonghan Yang, Xiaoyuan Yi, Peng Li +2
Warning: this paper contains model outputs exhibiting offensiveness and biases. Recently pre-trained language models (PLMs) have prospered in various natural language generation (N…