Solving Data-centric Tasks using Large Language Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910381148995584 |
|---|---|
| author | Barke, Shraddha Poelitz, Christian Negreanu, Carina Suzana Zorn, Benjamin Cambronero, José Gordon, Andrew D. Le, Vu Nouri, Elnaz Polikarpova, Nadia Sarkar, Advait Slininger, Brian Toronto, Neil Williams, Jack |
| author_facet | Barke, Shraddha Poelitz, Christian Negreanu, Carina Suzana Zorn, Benjamin Cambronero, José Gordon, Andrew D. Le, Vu Nouri, Elnaz Polikarpova, Nadia Sarkar, Advait Slininger, Brian Toronto, Neil Williams, Jack |
| contents | Large language models (LLMs) are rapidly replacing help forums like StackOverflow, and are especially helpful for non-professional programmers and end users. These users are often interested in data-centric tasks, such as spreadsheet manipulation and data wrangling, which are hard to solve if the intent is only communicated using a natural-language description, without including the data. But how do we decide how much data and which data to include in the prompt? This paper makes two contributions towards answering this question. First, we create a dataset of real-world NL-to-code tasks manipulating tabular data, mined from StackOverflow posts. Second, we introduce a cluster-then-select prompting technique, which adds the most representative rows from the input data to the LLM prompt. Our experiments show that LLM performance is indeed sensitive to the amount of data passed in the prompt, and that for tasks with a lot of syntactic variation in the input table, our cluster-then-select technique outperforms a random selection baseline. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_11734 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Solving Data-centric Tasks using Large Language Models Barke, Shraddha Poelitz, Christian Negreanu, Carina Suzana Zorn, Benjamin Cambronero, José Gordon, Andrew D. Le, Vu Nouri, Elnaz Polikarpova, Nadia Sarkar, Advait Slininger, Brian Toronto, Neil Williams, Jack Programming Languages Artificial Intelligence Software Engineering Large language models (LLMs) are rapidly replacing help forums like StackOverflow, and are especially helpful for non-professional programmers and end users. These users are often interested in data-centric tasks, such as spreadsheet manipulation and data wrangling, which are hard to solve if the intent is only communicated using a natural-language description, without including the data. But how do we decide how much data and which data to include in the prompt? This paper makes two contributions towards answering this question. First, we create a dataset of real-world NL-to-code tasks manipulating tabular data, mined from StackOverflow posts. Second, we introduce a cluster-then-select prompting technique, which adds the most representative rows from the input data to the LLM prompt. Our experiments show that LLM performance is indeed sensitive to the amount of data passed in the prompt, and that for tasks with a lot of syntactic variation in the input table, our cluster-then-select technique outperforms a random selection baseline. |
| title | Solving Data-centric Tasks using Large Language Models |
| topic | Programming Languages Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2402.11734 |