10 papers
Summoning the Oracle to Slay It: Mitigating Look-Ahead Bias in Financial Backtesting with Large Language Models
Weixian Waylon Li, Mengyu Wang, Tiejun Ma
Backtesting large language models (LLMs) on historical financial data is unreliable because pre-training cuts off after the events happened. An LLM trained in 2024 already "knows"…
GRAB: A Risk Taxonomy--Grounded Benchmark for Unsupervised Topic Discovery in Financial Disclosures
Ying Li, Tiejun Ma
Risk categorization in 10-K risk disclosures matters for oversight and investment, yet no public benchmark evaluates unsupervised topic models for this task. We present GRAB, a fin…
Self Knowledge Re-expression: A Fully Local Method for Adapting LLMs to Tasks Using Intrinsic Knowledge
Mengyu Wang, Xiaoying Zhi, Zhiyi Li +4
While the next-token prediction (NTP) paradigm enables large language models (LLMs) to express their intrinsic knowledge, its sequential nature constrains performance on specialize…
Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory
Weixian Waylon Li, Jiaxin Zhang, Xianan Jim Yang +2
Structured memory representations such as knowledge graphs are central to autonomous agents and other long-lived systems. However, most existing approaches model time as discrete m…
Spectral Attention Steering for Prompt Highlighting
Weixian Waylon Li, Yuchen Niu, Yongxin Yang +3
Attention steering is an important technique for controlling model focus, enabling capabilities such as prompt highlighting, where the model prioritises user-specified text. Howeve…
One More Question is Enough, Expert Question Decomposition (EQD) Model for Domain Quantitative Reasoning
Mengyu Wang, Sotirios Sabanis, Miguel de Carvalho +2
Domain-specific quantitative reasoning remains a major challenge for large language models (LLMs), especially in fields requiring expert knowledge and complex question answering (Q…