Heterogenous Profiles Between Matched Primary Tumors and Brain Metastases Reveal Tumor Evolution

Chen, Yanming; Wang, Ji; Tao, Chuming; Wang, Ye; Zhu, Qing; Yuan, Liqun; Wang, Zhongyong; Sheng, Minfeng; Zhang, Tan; Li, Shenggang; Zhang, Yongsheng; Dong, Jun; Lan, Qing; Zhao, Jizong

doi:10.21203/rs.3.rs-1105667/v1

Cited by 1 publication

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our work, we mainly test robustness from the prompt design perspective such as how to select in-context examples, the number of in-context examples and the prompt format of in-context examples. It would also be valuable to investigate our prompting methods under different databases, natural language questions, or SQL perturbations (Chang et al, 2023a). This broader exploration would enable us to evaluate the robustness of our prompting methods across diverse scenarios.…”

Section: Limitationsmentioning

confidence: 99%

Exploring Chain of Thought Style Prompting for Text-to-SQL

Tai,

Chen,

Zhang

et al. 2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

In-context learning with large language models (LLMs) has recently caught increasing attention due to its superior few-shot performance on various tasks. However, its performance on text-to-SQL parsing still has much room for improvement. In this paper, we hypothesize that a crucial aspect of LLMs to improve for text-to-SQL parsing is their multi-step reasoning ability. Thus, we systematically study how to enhance LLMs' reasoning ability through chain of thought (CoT) style prompting, including the original chain-of-thought prompting (Wei et al., 2022b) and least-to-most prompting (Zhou et al., 2023). Our experiments demonstrate that iterative prompting as in Zhou et al. ( 2023) may be unnecessary for text-to-SQL parsing, and using detailed reasoning steps tends to have more error propagation issues. Based on these findings, we propose a new CoT-style prompting method for text-to-SQL parsing. It brings 5.2 and 6.5 point absolute gains on the Spider development set and the Spider Realistic set, respectively, compared to the standard prompting method without reasoning steps; 2.4 and 1.5 point absolute gains, compared to the least-to-most prompting method 1 .

show abstract

Section: Limitationsmentioning

confidence: 99%