6 papers
Many Voices, One Reward: Multi-Role Rubric Generation for LLM Judging and Reward Modeling
Dazhi Fu, Jiuding Yang, Yiwen Guo +1
Reliable reward and preference signals are critical for evaluating and optimizing large language models on open-ended tasks. Rubric-based judges offer a transparent way to decompos…
Model-Level GNN Explanations via Rule-to-Graph Readout for Logit Reconstruction
Shengyao Lu, Jiuding Yang, Aedan J. DeFrates +3
We propose a novel model-level GNN explanation framework that shifts the explanation target from class-wise rule extraction to rule-based logit reconstruction. Our method recasts t…
PerfCoder: Large Language Models for Interpretable Code Performance Optimization
Jiuding Yang, Shengyao Lu, Hongxuan Liu +4
Large language models (LLMs) have achieved remarkable progress in automatic code generation, yet their ability to produce high-performance code remains limited--a critical requirem…
Enhancing and Assessing Instruction-Following with Fine-Grained Instruction Variants
Jiuding Yang, Weidong Guo, Kaitong Yang +3
The effective alignment of Large Language Models (LLMs) with precise instructions is essential for their application in diverse real-world scenarios. Current methods focus on enhan…
TaCIE: Enhancing Instruction Comprehension in Large Language Models through Task-Centred Instruction Evolution
Jiuding Yang, Shengyao Lu, Weidong Guo +4
Large Language Models (LLMs) require precise alignment with complex instructions to optimize their performance in real-world applications. As the demand for refined instruction tun…
Instruction Fusion: Advancing Prompt Evolution through Hybridization
Weidong Guo, Jiuding Yang, Kaitong Yang +4
The fine-tuning of Large Language Models (LLMs) specialized in code generation has seen notable advancements through the use of open-domain coding queries. Despite the successes, e…