Relying on the Unreliable: The Impact of Language Models’ Reluctance to Express Uncertainty
The paper explores the ability of language models (LMs) to express uncertainties when answering questions. It was…
Using Natural Language Inference to Improve Persona Extraction from Dialogue in a New Domain
This article by Alexandra DeLucia et al. addresses the challenge of creating unique personas for dialogue agents,…
The Unreasonable Effectiveness of Easy Training Data for Hard Tasks
The research paper explores the notion of ‘easy-to-hard generalization’ in language models. It addresses the problem of…
Synthetic Data Generation Framework, Dataset, and Efficient Deep Model for Pedestrian Intention Prediction
The article presents a framework, ARCANE, for generating synthetic datasets to improve models predicting pedestrian intentions, crucial…
A Universal Knowledge Model and Cognitive Architecture for Prototyping AGI
The article identifies 42 cognitive architectures for creating general artificial intelligence (AGI) and proposes a new cognitive…
MultiSlot ReRanker: A Generic Model-based Re-Ranking Framework in Recommendation Systems
The authors propose a generic model-based re-ranking framework, MultiSlot ReRanker, that optimizes relevance, diversity, and freshness. It…
Cognitive BPM as an Equalizer: Improving Access and Efficiency for Employees with (and without) Cognitive Disabilities
The article investigates how AI can improve business processes, particularly for individuals with cognitive disabilities. It centers…
Vehicle: Bridging the Embedding Gap in the Verification of Neuro-Symbolic Programs
The authors discuss the increasing prevalence of neuro-symbolic programs, which combine traditional code with machine learning components,…
Sanity Checks Revisited: An Exploration to Repair the Model Parameter Randomisation Test
The article discusses the Model Parameter Randomisation Test (MPRT), a widely acknowledged method in the eXplainable Artificial…
A Brain-inspired Computational Model for Human-like Concept Learning
This paper discusses the process of concept learning in humans, a crucial part of cognition that affects…