30 citations · 33 across the 10 of their papers we have counts for
13 papers
LLM Agents for Automated Post-Training via Structured Recipe Optimization
Ruohong Liu, Bohan Tang, Lekang Jiang +2
Automated post-training transforms pre-trained large language models (LLMs) into models capable of handling diverse domains by automatically constructing and optimizing a recipe of…
Recursive Harness Self-Improvement for Frontier Reasoning Data Synthesis
Wenlong Zhang, Zhengbo Jiao, Chenxu Zhang +5
Generating progressively harder reasoning problems requires synthesis procedures that adapt as the task distribution evolves. Existing task-level recursion reuses generated problem…
Benchmarking Patent Drafting from Inventor-Style Disclosures
Lekang Jiang, Wenjun Sun, Stephan Goetz
While recent large language models (LLMs) have achieved promising results on individual patent drafting tasks, they fundamentally fail to investigate the core challenge of real-wor…
ADIAS: Automated Design of Interactive Agentic Systems
Lekang Jiang, Bohan Tang, Stephan Goetz +1
Self-evolving agents can improve without updating model weights by iteratively optimizing the harness based on evaluation feedback. Existing methods are largely candidate-centric:…
When Reasoning Hurts Legal Drafting: The Verbalization Bottleneck in Patent Claim Generation
Lekang Jiang, Wenjun Sun, Stephan Goetz
Patent claim drafting is a challenging legal drafting task that requires technical expertise, precise linguistic control, strict adherence to formal conventions, and the preservati…
Reasoning for Hierarchical Text Classification: The Case of Patents
Lekang Jiang, Wenjun Sun, Stephan Goetz
Hierarchical text classification (HTC) assigns documents to multiple levels of a pre-defined taxonomy. Automated patent subject classification represents one of the hardest HTC sce…
Enriching Patent Claim Generation with European Patent Dataset
Lekang Jiang, Chengzu Li, Stephan Goetz
Drafting patent claims is time-intensive, costly, and requires professional skill. Therefore, researchers have investigated large language models (LLMs) to assist inventors in writ…
Towards Better Evaluation for Generated Patent Claims
Lekang Jiang, Pascal A Scherz, Stephan Goetz
Patent claims define the scope of protection and establish the legal boundaries of an invention. Drafting these claims is a complex and time-consuming process that usually requires…
Patent-CR: A Dataset for Patent Claim Revision
Lekang Jiang, Pascal A Scherz, Stephan Goetz
This paper presents Patent-CR, the first dataset created for the patent claim revision task in English. It includes both initial patent applications rejected by patent examiners an…
Can Large Language Models Generate High-quality Patent Claims?
Lekang Jiang, Caiqi Zhang, Pascal A Scherz +1
Large language models (LLMs) have shown exceptional performance across various text generation tasks but remain under-explored in the patent domain, which offers highly structured…
Natural Language Processing in the Patent Domain: A Survey
Lekang Jiang, Stephan Goetz
Patents, which encapsulate crucial technical and legal information in text form and referenced drawings, present a rich domain for natural language processing (NLP) applications. A…
Towards Temporal Edge Regression: A Case Study on Agriculture Trade Between Nations
Lekang Jiang, Caiqi Zhang, Farimah Poursafaei +1
Recently, Graph Neural Networks (GNNs) have shown promising performance in tasks on dynamic graphs such as node classification, link prediction and graph regression. However, few w…
FDAPT: Federated Domain-adaptive Pre-training for Language Models
Lekang Jiang, Filip Svoboda, Nicholas D. Lane
Foundation models (FMs) have shown prominent success in a wide range of tasks. Their applicability to specific domain-task pairings relies on the availability of, both, high-qualit…