Mingyue Liu


pdf bib
Self-Regulated Sample Diversity in Large Language Models
Mingyue Liu | Jonathan Frawley | Sarah Wyer | Hubert P. H. Shum | Sara Uckelman | Sue Black | Chris Willcocks
Findings of the Association for Computational Linguistics: NAACL 2024

Sample diversity depends on the task; within mathematics, precision and determinism are paramount, while storytelling thrives on creativity and surprise. This paper presents a simple self-regulating approach where we adjust sample diversity inference parameters dynamically based on the input prompt—in contrast to existing methods that require expensive and inflexible setups, or maintain static values during inference. Capturing a broad spectrum of sample diversities can be formulated as a straightforward self-supervised inference task, which we find significantly improves the quality of responses generically without model retraining or fine-tuning. In particular, our method demonstrates significant improvement in all supercategories of the MMLU multitask benchmark (GPT-3.5: +4.4%, GPT-4: +1.5%), which captures a large variety of difficult tasks covering STEM, the humanities and social sciences.


pdf bib
Breaking through Inequality of Information Acquisition among Social Classes: A Modest Effort on Measuring “Fun”
Chenghao Xiao | Baicheng Sun | Jindi Wang | Mingyue Liu | Jiayi Feng
Proceedings of the Second Workshop on NLP for Positive Impact (NLP4PI)

With the identification of the inequality encoded in information acquisition among social classes, we propose to leverage a powerful concept that has never been studied as a linguistic construct, “fun”, to deconstruct the inequality. Inspired by theories in sociology, we draw connection between social class and information cocoon, through the lens of fun, and hypothesize the measurement of “how fun one’s dominating social cocoon is” to be an indicator of the social class of an individual. Following this, we propose an NLP framework to combat the issue by measuring how fun one’s information cocoon is, and empower individuals to emancipate from their trapped cocoons. We position our work to be a domain-agnostic framework that can be deployed in a lot of downstream cases, and is one that aims to deconstruct, as opposed to reinforcing, the traditional social structure of beneficiaries.