7 papers
SENECA: Small-Sample Discrete Entropy Estimation via Self-Consistent Missing Mass
Lucas H. McCabe, H. Howie Huang
Discrete entropy estimation is a classic information theory problem, wherein the average information content of a discrete random variable is estimated from samples alone. Naive ap…
Estimating Semantic Alphabet Size for LLM Uncertainty Quantification
Lucas H. McCabe, Rimon Melamed, Thomas Hartvigsen +1
Many black-box techniques for quantifying the uncertainty of large language models (LLMs) rely on repeated LLM sampling, which can be computationally expensive. Therefore, practica…
From Time and Place to Preference: LLM-Driven Geo-Temporal Context in Recommendations
Yejin Kim, Shaghayegh Agah, Mayur Nankani +5
Most recommender systems treat timestamps as numeric or cyclical values, overlooking real-world context such as holidays, events, and seasonal patterns. We propose a scalable frame…
Demystifying optimized prompts in language models
Rimon Melamed, Lucas H. McCabe, H. Howie Huang
Modern language models (LMs) are not robust to out-of-distribution inputs. Machine generated (``optimized'') prompts can be used to modulate LM outputs and induce specific behavior…
Predicting Movie Hits Before They Happen with LLMs
Shaghayegh Agah, Yejin Kim, Neeraj Sharma +4
Addressing the cold-start issue in content recommendation remains a critical ongoing challenge. In this work, we focus on tackling the cold-start problem for movies on a large ente…
Causal Reasoning in Large Language Models: A Knowledge Graph Approach
Yejin Kim, Eojin Kang, Juae Kim +1
Large language models (LLMs) typically improve performance by either retrieving semantically similar information, or enhancing reasoning abilities through structured prompts like c…