The Dual-use Dilemma in LLMs: Do Empowering Ethical Capacities Make a Degraded Utility?
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910847287164928 |
|---|---|
| author | Zhang, Yiyi Chen, Xingyu Chen, Kexin Du, Yuyang Dang, Xilin Heng, Pheng-Ann |
| author_facet | Zhang, Yiyi Chen, Xingyu Chen, Kexin Du, Yuyang Dang, Xilin Heng, Pheng-Ann |
| contents | Recent years have witnessed extensive efforts to enhance Large Language Models (LLMs) across various domains, alongside growing attention to their ethical implications. However, a critical challenge remains largely overlooked: LLMs must balance between rejecting harmful requests for safety and accommodating legitimate ones for utility. This paper presents a Direct Preference Optimization (DPO) based alignment framework that achieves better overall performance by addressing this ethical-utility trade-off, using chemical domain applications as a proof-of-concept. Our alignment pipeline starts with a GPT-assisted three-phase data generation scheme, in which we create LibraChemQA, a chemical question-answering dataset comprising 31.6k triplet instances. By incorporating an innovative balanced seed in the data generation process, our framework systematically considers both legitimate and illegitimate requests. The framework also introduces a rephrasing mechanism for efficient data augmentation that enhances the model's chemical comprehension. We further develop a novel hybrid evaluation scheme with LLM judges for precise assessment of both safety and utility. Experimental results demonstrate our model's substantial improvements in overall performance where both safety and utility are considered - the resulting model outperforms leading LLMs including Claude-3, GPT-4o, and LLaMA-3 by margins of 13.44%, 7.16%, and 7.10% respectively on our released benchmark. At the end of this paper, we analyze experimental results obtained from testing DeepSeek-R1 on our benchmark and reveal the critical ethical concerns raised by this highly acclaimed model. We highlight that the long Chain-of-Thought (CoT) reasoning process employed by DeepSeek-R1, as well as other LLMs distilled from it, introduces significant ethical vulnerabilities when exposed to users. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_13952 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Dual-use Dilemma in LLMs: Do Empowering Ethical Capacities Make a Degraded Utility? Zhang, Yiyi Chen, Xingyu Chen, Kexin Du, Yuyang Dang, Xilin Heng, Pheng-Ann Computation and Language Artificial Intelligence Recent years have witnessed extensive efforts to enhance Large Language Models (LLMs) across various domains, alongside growing attention to their ethical implications. However, a critical challenge remains largely overlooked: LLMs must balance between rejecting harmful requests for safety and accommodating legitimate ones for utility. This paper presents a Direct Preference Optimization (DPO) based alignment framework that achieves better overall performance by addressing this ethical-utility trade-off, using chemical domain applications as a proof-of-concept. Our alignment pipeline starts with a GPT-assisted three-phase data generation scheme, in which we create LibraChemQA, a chemical question-answering dataset comprising 31.6k triplet instances. By incorporating an innovative balanced seed in the data generation process, our framework systematically considers both legitimate and illegitimate requests. The framework also introduces a rephrasing mechanism for efficient data augmentation that enhances the model's chemical comprehension. We further develop a novel hybrid evaluation scheme with LLM judges for precise assessment of both safety and utility. Experimental results demonstrate our model's substantial improvements in overall performance where both safety and utility are considered - the resulting model outperforms leading LLMs including Claude-3, GPT-4o, and LLaMA-3 by margins of 13.44%, 7.16%, and 7.10% respectively on our released benchmark. At the end of this paper, we analyze experimental results obtained from testing DeepSeek-R1 on our benchmark and reveal the critical ethical concerns raised by this highly acclaimed model. We highlight that the long Chain-of-Thought (CoT) reasoning process employed by DeepSeek-R1, as well as other LLMs distilled from it, introduces significant ethical vulnerabilities when exposed to users. |
| title | The Dual-use Dilemma in LLMs: Do Empowering Ethical Capacities Make a Degraded Utility? |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2501.13952 |