Jiachen Li


2024

pdf bib
Cross-Task Defense: Instruction-Tuning LLMs for Content Safety
Yu Fu | Wen Xiao | Jia Chen | Jiachen Li | Evangelos Papalexakis | Aichi Chien | Yue Dong
Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)

Recent studies reveal that Large Language Models (LLMs) face challenges in balancing safety with utility, particularly when processing long texts for NLP tasks like summarization and translation. Despite defenses against malicious short questions, the ability of LLMs to safely handle dangerous long content, such as manuals teaching illicit activities, remains unclear. Our work aims to develop robust defenses for LLMs in processing malicious documents alongside benign NLP task queries. We introduce a defense dataset comprised of safety-related examples and propose single-task and mixed-task losses for instruction tuning. Our empirical results demonstrate that LLMs can significantly enhance their capacity to safely manage dangerous content with appropriate instruction tuning. Additionally, strengthening the defenses of tasks most susceptible to misuse is effective in protecting LLMs against processing harmful information. We also observe that trade-offs between utility and safety exist in defense strategies, where Llama2, utilizing our proposed approach, displays a significantly better balance compared to Llama1.

pdf bib
More Samples or More Prompts? Exploring Effective Few-Shot In-Context Learning for LLMs with In-Context Sampling
Bingsheng Yao | Guiming Chen | Ruishi Zou | Yuxuan Lu | Jiachen Li | Shao Zhang | Yisi Sang | Sijia Liu | James Hendler | Dakuo Wang
Findings of the Association for Computational Linguistics: NAACL 2024

While most existing works on LLM prompting techniques focus only on how to select a better set of data samples inside one single prompt input (In-Context Learning or ICL), why can not we design and leverage multiple prompts together to further improve the LLM’s performance? In this work, we propose In-Context Sampling (ICS), a low-resource LLM prompting technique to produce confident predictions by optimizing the construction of multiple ICL prompt inputs. Extensive experiments with three open-source LLMs (FlanT5-XL, Mistral-7B, and Mixtral-8x7B) on four NLI datasets (e-SNLI, Multi-NLI, ANLI, and Contract-NLI) and one QA dataset (CommonsenseQA) illustrate that ICS can consistently enhance LLMs’ performance. An in-depth evaluation with three data similarity-based ICS strategies suggests that these strategies can further elevate LLM’s performance, which sheds light on a new yet promising future research direction.