6 papers
PrefReward: Learning User Preference Matrix for Personalized Text Generation
Yue Wu, Chengbing Wang, Yimeng Bai +3
Large Language Models (LLMs) have demonstrated remarkable ability in generating personalized content by leveraging user histories and contextual cues. However, most existing person…
SDLLMFuzz: Dynamic-static LLM-assisted greybox fuzzing for structured input programs
Yihao Zou, Tianming Zheng, Futai Zou +1
Fuzzing has become a widely adopted technique for vulnerability discovery, yet it remains ineffective for structured-input programs due to strict syntactic constraints and limited…
Stability-Weighted Decoding for Diffusion Language Models
Yue Wu, Jian Huang
Diffusion large language models (dLLMs) enable parallel text generation by iteratively denoising a fully masked sequence, unmasking a subset of masked tokens at each step. Existing…
DISC: Dynamic Decomposition Improves LLM Inference Scaling
Jonathan Light, Wei Cheng, Benjamin Riviere +6
Inference scaling methods for LLMs often rely on decomposing problems into steps (or groups of tokens), followed by sampling and selecting the best next steps. However, these steps…
Scattered Forest Search: Smarter Code Space Exploration with LLMs
Jonathan Light, Yue Wu, Yiyou Sun +6
We frame code generation as a black-box optimization problem within the code space and demonstrate how optimization-inspired techniques can enhance inference scaling. Based on this…
PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners
Yijia Xiao, Yiqiao Jin, Yushi Bai +10
The proliferation of Large Language Models (LLMs) has driven considerable interest in fine-tuning them with domain-specific data to create specialized language models. Nevertheless…