Yanran Tang

汤嫣然

I am currently a Postdoctoral Researcher at The University of Queensland (UQ). I recently completed my PhD at UQ, supervised by Professors Helen Huang and Xue Li. I obataied my Bachelor of Law (LL.B.)⚖️ and Master of Law (LL.M.)⚖️ degrees in 2018 and 2021 respectively.

My research focuses on artificial intelligence for the legal domain, particularly legal information retrieval, legal reasoning, and legal decision-making. I am especially interested in graph neural networks (GNNs) and large language models (LLMs), and their applications to real-world legal tasks.

Talks

  • 06.2024 Give a talk, “Effective Representation Learning for Legal Case Retrieval”, at IR Seminar, The University of Glasgow. [slides]

  • 05.2024 Give a talk, “Effective Representation Learning for Legal Case Retrieval”, at THUIR, Tsinghua University. [slides]

  • 03.2024 Give a talk, “Graph Neural Networks for Legal Case Retrieval with Text-Attributed Graphs”, at IRonGraphs Workshop at ECIR 2024. [slides]

Selected Research

Google Scholar page includes the full publication list.

PontTuset Cassette: Case-to-Case Structural Distillation for Efficient Legal Case Retrieval
Yanran Tang, Ruihong Qiu, Hongzhi Yin, Xue Li, Zi Huang
TOIS 2026
arXiv / code

A knowledge distillation framework that transfers structural knowledge from graph neural networks to lightweight legal case representations, enabling efficient and effective legal case retrieval.

PontTuset LEXA: Legal case retrieval via graph contrastive learning with contextualised LLM embeddings
Yanran Tang, Ruihong Qiu, Yilun Liu, Xue Li, Zi Huang
WWWJ 2026
arXiv / code

A graph contrastive learning framework that leverages graph augmentation to provide enhanced training signals, while integrating contextualised LLM embeddings to learn more expressive legal case representations for accurate legal case retrieval.

PontTuset ReaKase-8B: Legal Case Retrieval via Knowledge and Reasoning Representations with LLMs
Yanran Tang, Ruihong Qiu, Xue Li, Zi Huang
ADC 2025
arXiv / code

A reasoning-enhanced LLM architecture that integrates structured legal knowledge to more effectively bridge the gap between case facts and judicial outcomes, thereby enabling more accurate legal case retrieval.

PontTuset CaseLink: Inductive Graph Learning for Legal Case Retrieval
Yanran Tang, Ruihong Qiu, Hongzhi Yin, Xue Li, and Zi Huang
SIGIR 2024
arXiv / code

An inductive graph learning paradigm for legal case retrieval is proposed to tackle the challenge of unseen testing query and candidate cases.

PontTuset CaseGNN: Graph Neural Networks for Legal Case Retrieval with Text-Attributed Graphs
Yanran Tang, Ruihong Qiu, Yilun Liu, Xue Li, Zi Huang
ECIR 2024
arXiv / code

A structural modelling of law case with GNN for effective retrieval is introduced.

PontTuset Prompt-based Effective Input Reformulation for Legal Case Retrieval
Yanran Tang, Ruihong Qiu, Xue Li
ADC 2023
arXiv / code

An effective legal case retriver that focus on legal feature alignment with the aid of LM prompting and LLM summarisation is introduced.

Honors and Awards

  • Runner-up in Task 1: Legal Case Retrieval, Competition on Legal Information Extraction/Entailment (COLIEE) 2025
  • Student Support Grants, ECIR 2024
  • Third Prize in Task 1: Legal Case Retrieval, Competition on Legal Information Extraction/Entailment (COLIEE) 2023
  • Third Prize in Legal Case Retrieval Track, Competition of Challenge of AI in Law (CAIL) 2023
  • Gold CIRES-ADC Travel Grant, CIRES PhD School and the Australasian Database Conference (ADC) 2023
  • UQ Graduate School Scholarship, Graduate School, The University of Queensland (2023-2026)
  • SCUT Graduate Scholarship, School of Law, South China University of Technology (2018-2021)

MISC

I speak Cantonese, Mandarin and English.

Updated on 07/09/2026.