7 papers
LePREC: Reasoning as Classification over Structured Factors for Assessing Relevance of Legal Issues
Fanyu Wang, Xiaoxi Kang, Paul Burgess +6
More than half of the global population struggles to meet their civil justice needs due to limited legal resources. While Large Language Models (LLMs) have demonstrated impressive…
TAB-AUDIT: Detecting AI-Fabricated Scientific Tables via Multi-View Likelihood Mismatch
Shuo Huang, Yan Pen, Lizhen Qu
AI-generated fabricated scientific manuscripts raise growing concerns with large-scale breaches of academic integrity. In this work, we present the first systematic study on detect…
Evidence-based Distributional Alignment for Large Language Models
Viet-Thanh Pham, Lizhen Qu, Zhuang Li +1
Distributional alignment enables large language models (LLMs) to predict how a target population distributes its responses across answer options, rather than collapsing disagreemen…
DiscoSG: Towards Discourse-Level Text Scene Graph Parsing through Iterative Graph Refinement
Shaoqing Lin, Chong Teng, Fei Li +3
Vision-Language Models (VLMs) generate discourse-level, multi-sentence visual descriptions, challenging text scene graph parsers built for single-sentence caption-to-graph mapping.…
On the Reliability of Large Language Models for Causal Discovery
Tao Feng, Lizhen Qu, Niket Tandon +3
This study investigates the efficacy of Large Language Models (LLMs) in causal discovery. Using newly available open-source LLMs, OLMo and BLOOM, which provide access to their pre-…
Automating IRAC Analysis in Malaysian Contract Law using a Semi-Structured Knowledge Base
Xiaoxi Kang, Lizhen Qu, Lay-Ki Soon +2
The effectiveness of Large Language Models (LLMs) in legal reasoning is often limited due to the unique legal terminologies and the necessity for highly specialized knowledge. Thes…