8 papers
DevBench: A Realistic, Developer-Informed Benchmark for Code Generation Models
Adarsh Kumarappan, Pareesa Ameneh Golnari, Wen Wen +5
DevBench is a telemetry-driven benchmark designed to evaluate Large Language Models (LLMs) on realistic code completion tasks. It includes 1,800 evaluation instances across six pro…
TopoChunker: Topology-Aware Agentic Document Chunking Framework
Xiaoyu Liu
Current document chunking methods for Retrieval-Augmented Generation (RAG) typically linearize text. This forced linearization strips away intrinsic topological hierarchies, creati…
DPI: Exploiting Parameter Heterogeneity for Interference-Free Fine-Tuning
Xiaoyu Liu, Xiaoyu Guan, Di Liang +1
Supervised fine-tuning (SFT) is a crucial step for adapting large language models (LLMs) to downstream tasks. However, conflicting objectives across heterogeneous SFT tasks often i…
PersonaLedger: Generating Realistic Financial Transactions with Persona Conditioned LLMs and Rule Grounded Feedback
Dehao Yuan, Tyler Farnan, Stefan Tesliuc +8
Strict privacy regulations limit access to real transaction data, slowing open research in financial AI. Synthetic data can bridge this gap, but existing generators do not jointly…
Predicate-Argument Structure Divergences in Chinese and English Parallel Sentences and their Impact on Language Transfer
Rocco Tripodi, Xiaoyu Liu
Cross-lingual Natural Language Processing (NLP) has gained significant traction in recent years, offering practical solutions in low-resource settings by transferring linguistic kn…
Uncovering Pretraining Code in LLMs: A Syntax-Aware Attribution Approach
Yuanheng Li, Zhuoyang Chen, Xiaoyun Liu +5
As large language models (LLMs) become increasingly capable, concerns over the unauthorized use of copyrighted and licensed content in their training data have grown, especially in…