Michael Shieh
2024
Prompt Optimization via Adversarial In-Context Learning
Do Long
|
Yiran Zhao
|
Hannah Brown
|
Yuxi Xie
|
James Zhao
|
Nancy Chen
|
Kenji Kawaguchi
|
Michael Shieh
|
Junxian He
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
We propose a new method, Adversarial In-Context Learning (adv-ICL), to optimize prompts for in-context learning (ICL). Inspired by adversarial learning, adv-ICL is implemented as a two-player game between a generator and discriminator, with LLMs acting as both. In each round, given an input prefixed by task instructions and several exemplars, the generator produces an output. The discriminator then classifies the generator’s input-output pair as model-generated or real data. Based on the discriminator’s loss, a prompt modifier LLM proposes possible edits to the generator and discriminator prompts, and the edits that most improve the adversarial loss are selected. We show that applying adv-ICL results in significant improvements over state-of-the-art prompt optimization techniques for both open and closed-source models on 13 generation and classification tasks including summarization, arithmetic reasoning, machine translation, data-to-text generation, and the MMLU and big-bench hard benchmarks. In addition, our method is computationally efficient, easily extensible to other LLMs and tasks, and effective in low-resource settings.
InstructCoder: Instruction Tuning Large Language Models for Code Editing
Kaixin Li
|
Qisheng Hu
|
James Zhao
|
Hui Chen
|
Yuxi Xie
|
Tiedong Liu
|
Michael Shieh
|
Junxian He
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
Code editing encompasses a variety of pragmatic tasks that developers deal with daily. Despite its relevance and practical usefulness, automatic code editing remains an underexplored area in the evolution of deep learning models, partly due to data scarcity. In this work, we explore the use of Large Language Models (LLMs) to edit code based on user instructions. Evaluated on a novel human-written execution-based benchmark dubbed EditEval, we found current models often struggle to fulfill the instructions. In light of this, we contribute InstructCoder, the first instruction-tuning dataset designed to adapt LLMs for general-purpose code editing, containing high-diversity code-editing tasks such as comment insertion, code optimization, and code refactoring. It consists of over 114,000 instruction-input-output triplets and covers multiple distinct code editing scenarios. The collection process starts with filtered commit data sourced from GitHub Python repositories as seeds. Subsequently, the dataset is systematically expanded through an iterative process, where both seed and generated tasks are used to prompt ChatGPT for more data. Our findings reveal that open-source LLMs fine-tuned on InstructCoder can significantly enhance the accuracy of code edits, exhibiting superior code-editing performance matching advanced proprietary LLMs. The datasets and the source code are publicly available.
Search
Co-authors
- Yuxi Xie 2
- James Zhao 2
- Junxian He 2
- Do Long 1
- Yiran Zhao 1
- show all...
Venues
- acl2