Weiguo Fan


2024

pdf
Instances Need More Care: Rewriting Prompts for Instances with LLMs in the Loop Yields Better Zero-Shot Performance
Saurabh Srivastava | Chengyue Huang | Weiguo Fan | Ziyu Yao
Findings of the Association for Computational Linguistics ACL 2024

Large language models (LLMs) have revolutionized zero-shot task performance, mitigating the need for task-specific annotations while enhancing task generalizability. Despite its advancements, current methods using trigger phrases such as “Let’s think step by step” remain limited. This study introduces PRomPTed, an approach that optimizes the zero-shot prompts for individual task instances following an innovative manner of “LLMs in the loop”.Our comprehensive evaluation across 13 datasets and 10 task types based on GPT-4 reveals that PRomPTed significantly outperforms both the naive zero-shot approaches and a strong baseline (i.e., “Output Refinement”) which refines the task output instead of the input prompt. Our experimental results also confirmed the generalization of this advantage to the relatively weaker GPT-3.5. Even more intriguingly, we found that leveraging GPT-3.5 to rewrite prompts for the stronger GPT-4 not only matches but occasionally exceeds the efficacy of using GPT-4 as the prompt rewriter. Our research thus presents a huge value in not only enhancing zero-shot LLM performance but also potentially enabling supervising LLMs with their weaker counterparts, a capability attracting much interest recently. Finally, our additional experiments confirm the generalization of the advantages to open-source LLMs such as Mistral 7B and Mixtral 8x7B.

2005

pdf
Discretization Based Learning for Information Retrieval
Dmitri Roussinov | Weiguo Fan
Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing

pdf
Mining Context Specific Similarity Relationships Using The World Wide Web
Dmitri Roussinov | Leon J. Zhao | Weiguo Fan
Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing

2002

pdf
Evaluating Web-based Question Answering Systems
Dragomir R. Radev | Hong Qi | Harris Wu | Weiguo Fan
Proceedings of the Third International Conference on Language Resources and Evaluation (LREC’02)

2000

pdf
Automatic summarization of search engine hit lists
Dragomir R. Radev | Weiguo Fan
ACL-2000 Workshop on Recent Advances in Natural Language Processing and Information Retrieval