3 papers
cs.CL2026
Reverse Constitutional AI: A Framework for Controllable Toxic Data Generation via Probability-Clamped RLAIF
Yuan Fang, Yiming Luo, Aimin Zhou +1
Ensuring the safety of large language models (LLMs) requires robust red teaming, yet the systematic synthesis of high-quality toxic data remains under-explored. We propose Reverse…
cs.LG2025
daDPO: Distribution-Aware DPO for Distilling Conversational Abilities
Zhengze Zhang, Shiqi Wang, Yiqun Shen +5
Large language models (LLMs) have demonstrated exceptional performance across various applications, but their conversational abilities decline sharply as model size decreases, pres…
cs.CL2025
Consultant Decoding: Yet Another Synergistic Mechanism
Chuanghao Ding, Jiaping Wang, Ziqing Yang +4
The synergistic mechanism based on Speculative Decoding (SD) has garnered considerable attention as a simple yet effective approach for accelerating the inference of large language…