From the 1 of 4 linked papers with an AI index.
4 papers
SkillSmith: Learning to Compose Parametric Skills and Textual Knowledge
Lucio M. Dery, Benedict Aaron Tjandra, Siavash Samiei +4
SkillSmith is a method that lets a large language model reason over both textual knowledge and prefix‑tuned model weights, enabling it to generate new parametric skill prefixes for…
T-GRAB: A Synthetic Diagnostic Benchmark for Learning on Temporal Graphs
Alireza Dizaji, Benedict Aaron Tjandra, Mehrab Hamidi +2
Dynamic graph learning methods have recently emerged as powerful tools for modelling relational data evolving through time. However, despite extensive benchmarking efforts, it rema…
Enhancing the Expressivity of Temporal Graph Networks through Source-Target Identification
Benedict Aaron Tjandra, Federico Barbero, Michael Bronstein
Despite the successful application of Temporal Graph Networks (TGNs) for tasks such as dynamic node classification and link prediction, they still perform poorly on the task of dyn…
Fine-Tuning Large Language Models to Appropriately Abstain with Semantic Entropy
Benedict Aaron Tjandra, Muhammed Razzak, Jannik Kossen +2
Large Language Models (LLMs) are known to hallucinate, whereby they generate plausible but inaccurate text. This phenomenon poses significant risks in critical applications, such a…