Papers by David A. Clifton
DrAgent: Empowering Large Language Models as Medical Agents for Multi-hop Medical Reasoning (2025.findings-emnlp)
Copied to clipboard
Fenglin Liu, Zheng Li, Hongjian Zhou, Qingyu Yin, Jingfeng Yang, Xin Liu, Zhengyang Wang, Xianfeng Tang, Shiyang Li, Xiang He, Ruijie Wang, Bing Yin, Xiao Gu, Lei Clifton, David A. Clifton
| Challenge: | commercial LLMs can be difficult to use in real-world clinical decision-making . a lightweight LLM can be used to collaborate with diverse clinical tools . |
| Approach: | They propose a lightweight LLM that can be used to build medical LLMs as agents . they use recursive curriculum learning to optimize the LLM in an easy-to-hard progression . |
| Outcome: | The proposed approach outperforms human experts in medical examinations on diverse datasets. |
MiniALBERT: Model Distillation via Parameter-Efficient Recursive Transformers (2023.eacl-main)
Copied to clipboard
| Challenge: | Pre-trained Language Models (LMs) are an integral part of natural language processing but their usability is constrained by computational and time complexity and their increasing size. |
| Approach: | They propose a technique for converting knowledge of fully parameterised LMs into a compact recursive student. |
| Outcome: | The proposed models match the performance of bloated models with negligible performance losses. |
Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval (2026.acl-long)
Copied to clipboard
Joaquin Polonuer, Lucas Vittor, Iñaki Arango, Ayush Noori, David A. Clifton, Luciano Del Corro, Marinka Zitnik
| Challenge: | ARK: Adaptive Retriever of Knowledge is a tool-using KG retriever that allows a language model to control breadth-depth tradeoffs without requiring a fragile seed selection or pre-set hop depth. |
| Approach: | They propose a tool-using KG retriever that gives a language model control over breadth-depth tradeoff using global lexical search over node descriptors and one-hop neighborhood exploration that composes into multi-hop traversal. |
| Outcome: | The proposed model improves on a teacher's dataset by +7.0, +26.6, and +13.5% while retaining 98.5% of the teacher' s Hit@1 rate. |