Papers by Yinpeng Dong
Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to improve LLMs' ability to align their responses with objective facts suffer from poor generalization and trade-offs in other different capabilities. |
| Approach: | They propose to introduce PKUE (Precise Knowledge Utilization Enhancement) which fine-tunes the model on self-generated responses to precise and simple factual questions through preference optimization. |
| Outcome: | The proposed enhancements improve LLM’s ability to precisely leverage its knowledge and improve FactualBench, a comprehensive and precise factual QA dataset containing 181k Chinese data spanning 21 domains. |
AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization via Multi-LLMs (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing jailbreak research exhibits limitations in universality, validity, and efficiency . Existing methods for jailbreaking LLMs have limited validity and effectiveness . |
| Approach: | They propose a black-box approach that uses wordplay-guided mapping rule sampling to create universal adversarial prompts. |
| Outcome: | The proposed method efficiently identifies security vulnerabilities across various LLMs, achieving an average success rate of over 80% with fewer than 10 queries. |
Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to exploit black-box jailbreaks fail to capture key attack patterns . a novel framework decomposes jailbreak strategies into essential components . |
| Approach: | They propose a framework that decomposes jailbreak strategies into essential components and develops genetic-based optimization with intention evaluation mechanisms. |
| Outcome: | The proposed framework achieves 90% success rate on Claude-3.5, where prior methods completely fail . it also surpasses specialized safeguard models in evaluation accuracy . |