Boyan Wang — accepted AI-conference papers

2026

A Survey of Joint Online-Offline Fine-tuning for Large Language Models

Taihang Zhen, Guang Yang, Chenzhang Li, Nuo Yan, Shilong Zhou, Guangyu Liu +5

IJCAI 2026

Post-training for Large Language Models (LLMs) can be mainly categorized into offline Supervised Fine-Tuning (SFT) for knowledge acquisition and online Reinforcement Fine-Tuning (RFT) for adaptive refinement. Current state-of-the-art approaches typically employ a sequential cold-start pipeline (SFT-

Cited by 0 Scholar ↗

2026

SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks

Hongye Cao, Sijia Jing, Yanming Wang, Ziyue Peng, Zhixin Bai, Zhe Cao +11

ICLR 2026poster

With the rapid advancement of Large Language Models (LLMs), the safety of LLMs has been a critical concern requiring precise assessment. Current benchmarks primarily concentrate on single-turn dialogues or a single jailbreak attack method to assess the safety. Additionally, these benchmarks have not…

Cited by 0 Source ↗code ↗Scholar ↗