activity
20242026
collaborators

6 papers

cs.SE2026

Beyond Correctness: Enhancing Architectural Reasoning in Code LLMs via Scalable Labeling with Agentic Judgment

Kirill Vasilevski, Ximing Dong, Benjamin Rombaut +8

LLMs have substantially improved software engineering yet real-world development requires architectural understanding. Such understanding is prohibitively expensive to label manual…

cs.SE2026

When Elo Lies: Hidden Biases in Codeforces-Based Evaluation of Large Language Models

Shenyu Zheng, Ximing Dong, Xiaoshuang Liu +6

As Large Language Models (LLMs) achieve breakthroughs in complex reasoning, Codeforces-based Elo ratings have emerged as a prominent metric for evaluating competitive programming c…

cs.CL2026

Beyond Tokens: Semantic-Aware Speculative Decoding for Efficient Inference by Probing Internal States

Ximing Dong, Shaowei Wang, Dayi Lin +2

Large Language Models (LLMs) achieve strong performance across many tasks but suffer from high inference latency due to autoregressive decoding. The issue is exacerbated in Large R…

cs.CL2025

Model Performance-Guided Evaluation Data Selection for Effective Prompt Optimization

Ximing Dong, Shaowei Wang, Dayi Lin +1

Optimizing Large Language Model (LLM) performance requires well-crafted prompts, but manual prompt engineering is labor-intensive and often ineffective. Automated prompt optimizati…

cs.CL2025

A Framework for Real-time Safeguarding the Text Generation of Large Language Model

Ximing Dong, Dayi Lin, Shaowei Wang +1

Large Language Models (LLMs) have significantly advanced natural language processing (NLP) tasks but also pose ethical and societal risks due to their propensity to generate harmfu…

cs.CL2024

PromptExp: Multi-granularity Prompt Explanation of Large Language Models

Ximing Dong, Shaowei Wang, Dayi Lin +4

Large Language Models excel in tasks like natural language understanding and text generation. Prompt engineering plays a critical role in leveraging LLM effectively. However, LLMs…