2 papers
cs.CL2026
MIL-BERT: Classification of Arbitrarily Large Text with Performance and Explanatory Guarantees
John Cadigan, Dayne Freitag, Eric Yeh
Many text classification decisions are viable based on constituent excerpts alone. Taking inspiration from the field of multiple instance learning, we present an algorithm for trai…
cs.AI2025
Interpolative Decoding: Exploring the Spectrum of Personality Traits in LLMs
Eric Yeh, John Cadigan, Ran Chen +3
Recent research has explored using very large language models (LLMs) as proxies for humans in tasks such as simulation, surveys, and studies. While LLMs do not possess a human psyc…