Tag
Emo-Jev is a training-free framework that uses Jev's probabilistic decision interface for text classification, decomposing tasks into atomic judgments or aggregating multiple judgment paths to improve over direct prediction, evaluated across eight sentiment, emotion, sarcasm, and humor datasets against five state-of-the-art LLMs.
An essay arguing that typical LLM-based agent pipelines built as LLM → tool → action lack proper uncertainty handling, and proposing a belief-state architecture with Bayesian updates and value-of-information policies. The LLM should act as investigator/translator, while the system enforces permissions and calibrated beliefs.
Introduces ForecastBench-Sim, a simulated-world forecasting benchmark built on game rollouts from Freeciv, designed to provide controlled, immediately resolvable tasks for evaluating probabilistic reasoning in AI systems.
This thesis proposes a modular framework for scalable uncertainty reasoning in knowledge graphs, addressing imprecise attribute values, probabilistic triple existence, and incomplete schema through tailored algebraic, logical, and geometric techniques.
This paper introduces BeliefMem, a novel memory paradigm for LLM agents that stores multiple candidate conclusions with probabilities to handle partial observability and reduce self-reinforcing errors. Empirical evaluations show it outperforms deterministic baselines on LoCoMo and ALFWorld benchmarks.
AI systems must incorporate probabilistic reasoning to handle uncertainty for robust and trustworthy decision-making, as discussed by Zoubin Ghahramani regarding the mathematics of uncertainty in intelligent systems.