Beyond Instruction Following: Evaluating Rule Following of Large Language Models

Although Large Language Models (LLMs) have demonstrated strong instruction-following ability to be helpful, they are further supposed to be controlled and guided by rules in real-world scenarios to be safe, and accurate in responses. This demands the possession of rule-following capability of LLMs. However, few works have made a clear evaluation of the rule-following capability of LLMs. Previous studies that try to evaluate the rule-following capability of LLMs fail to distinguish the rule-following scenarios from the instruction-following scenarios. Therefore, this paper first makes a clarification of the concept of rule-following, and curates a comprehensive benchmark, RuleBench, to evaluate a diversified range of rule-following abilities. Our experimental results on a variety of LLMs show that they are still limited in following rules. Our further analysis provides insights into the improvements for LLMs toward a better rule-following intelligent agent. The data and code can be found at: https://anonymous.4open.science/r/llm-rule-following-B3E3/

Training, Architecture, and Prior for Deterministic Uncertainty Methods

Accurate and efficient uncertainty estimation is crucial to build reliable Machine Learning (ML) models capable to provide calibrated uncertainty estimates, generalize and detect Out-Of-Distribution (OOD) datasets. To this end, Deterministic Uncertainty Methods (DUMs) is a promising model family capable to perform uncertainty estimation in a single forward pass. This work investigates important design choices in DUMs: (1) we show that training schemes decoupling the core architecture and the uncertainty head schemes can significantly improve uncertainty performances. (2) we demonstrate that the core architecture expressiveness is crucial for uncertainty performance and that additional architecture constraints to avoid feature collapse can deteriorate the trade-off between OOD generalization and detection. (3) Contrary to other Bayesian models, we show that the prior defined by DUMs do not have a strong effect on the final performances.