14 papers
If LLMs Have Human-Like Attributes, Then So Does Age of Empires II
Adrian de Wynter
Much research has been carried out on large language models (LLMs) and LLM-powered agentic workflows. However, many works within the field state emergence of, ascribe to, or assume…
Foundation-Preserving Adaptation via Generalized Rayleigh-Quotient Optimization
Dongjun Kim, Adrian de Wynter, Huancheng Chen +2
While finetuning effectively adapts foundation models to specialized downstream tasks, it can degrade nontarget capabilities acquired during pretraining. Existing forgetting aware…
The Thin Line Between Comprehension and Persuasion in LLMs
Adrian de Wynter, Tangming Yuan
Large language models (LLMs) are excellent at maintaining high-level, convincing dialogue, but it remains unclear whether their persuasive success reflects genuine understanding of…
The Hrunting of AI: Where and How to Improve English Dialectal Fairness
Wei Li, Adrian de Wynter
It is known that large language models (LLMs) underperform in English dialects, and that improving them is difficult due to data scarcity. In this work we investigate how quality a…
On Meta-Prompting
Adrian de Wynter, Xun Wang, Qilong Gu +1
Modern large language models (LLMs) are capable of interpreting input strings as instructions, or prompts, and carry out tasks based on them. Unlike traditional learners, LLMs cann…
Is In-Context Learning Learning?
Adrian de Wynter
In-context learning (ICL) allows some autoregressive models to solve tasks via next-token prediction and without needing further training. This has led to claims about these model'…