4 papers
Is This Your Final Answer? Cross-Contextual Consistency as a Measure of LLM Credibility
Siyang Wu, Yibo Jiang, Bryon Aragam
Large language models (LLMs) are powerful black-box systems, making it difficult to discern whether their answers reflect stable internal beliefs or superficial pattern matching. W…
The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them)
Zihao Wang, Yibo Jiang, Jiahao Yu +1
Large language models (LLMs) that integrate multiple input roles (e.g., system instructions, user queries, external tool outputs) are increasingly prevalent in practice. Ensuring t…
The Geometry of Categorical and Hierarchical Concepts in Large Language Models
Kiho Park, Yo Joong Choe, Yibo Jiang +1
The linear representation hypothesis is the informal idea that semantic concepts are encoded as linear directions in the representation spaces of large language models (LLMs). Prev…
Do LLMs dream of elephants (when told not to)? Latent concept association and associative memory in transformers
Yibo Jiang, Goutham Rajendran, Pradeep Ravikumar +1
Large Language Models (LLMs) have the capacity to store and recall facts. Through experimentation with open-source models, we observe that this ability to retrieve facts can be eas…