6 papers
Efficient Inference for Coupled Hidden Markov Models in Continuous Time and Discrete Space
Giosue Migliorini, Padhraic Smyth
Systems of interacting continuous-time Markov chains are a powerful model class, but inference is typically intractable in high dimensional settings. Auxiliary information, such as…
EventFlow: Forecasting Temporal Point Processes with Flow Matching
Gavin Kerrigan, Kai Nelson, Padhraic Smyth
Continuous-time event sequences, in which events occur at irregular intervals, are ubiquitous across a wide range of industrial and scientific domains. The contemporary modeling pa…
Bayesian Evaluation of Large Language Model Behavior
Rachel Longjohn, Shang Wu, Saatvik Kher +2
It is increasingly important to evaluate how text generation systems based on large language models (LLMs) behave, such as their tendency to produce harmful output or their sensiti…
Shifting norms in scholarly publications: trends in readability, objectivity, authorship, and AI use
Padraig Cunningham, Padhraic Smyth, Barry Smyth
Academic and scientific publishing practices have changed significantly in recent years. This paper presents an analysis of 17 million research papers published since 2000 to explo…
Semantic Probabilistic Control of Language Models
Kareem Ahmed, Catarina G Belem, Padhraic Smyth +1
Semantic control entails steering LM generations towards satisfying subtle non-lexical constraints, e.g., toxicity, sentiment, or politeness, attributes that can be captured by a s…
ELBOing Stein: Variational Bayes with Stein Mixture Inference
Ola Rønning, Eric Nalisnick, Christophe Ley +2
Stein variational gradient descent (SVGD) [Liu and Wang, 2016] performs approximate Bayesian inference by representing the posterior with a set of particles. However, SVGD suffers…