CodecLM: Aligning Language Models with Tailored Synthetic Data

Zifeng Wang, Chun-Liang Li, Vincent Perot, Long Le, Jin Miao, Zizhao Zhang, Chen-Yu Lee, Tomas Pfister


Abstract
Instruction tuning has emerged as the key in aligning large language models (LLMs) with specific task instructions, thereby mitigating the discrepancy between the next-token prediction objective and users’ actual goals. To reduce the labor and time cost to collect or annotate data by humans, researchers start to explore the use of LLMs to generate instruction-aligned synthetic data. Recent works focus on generating diverse instructions and applying LLM to increase instruction complexity, often neglecting downstream use cases. It remains unclear how to tailor high-quality data to elicit better instruction-following abilities in different target instruction distributions and LLMs. To this end, we introduce CodecLM, a general framework for adaptively generating high-quality synthetic data for LLM alignment with different downstream instruction distributions and LLMs. Drawing on the Encode-Decode principles, we use LLMs as codecs to guide the data generation process. We first encode seed instructions into metadata, which are concise keywords generated on-the-fly to capture the target instruction distribution, and then decode metadata to create tailored instructions. We also introduce Self-Rubrics and Contrastive Filtering during decoding to tailor data-efficient samples. Extensive experiments on four open-domain instruction following benchmarks validate the effectiveness of CodecLM over the current state-of-the-arts.
Anthology ID:
2024.findings-naacl.235
Volume:
Findings of the Association for Computational Linguistics: NAACL 2024
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3712–3729
Language:
URL:
https://aclanthology.org/2024.findings-naacl.235
DOI:
10.18653/v1/2024.findings-naacl.235
Bibkey:
Cite (ACL):
Zifeng Wang, Chun-Liang Li, Vincent Perot, Long Le, Jin Miao, Zizhao Zhang, Chen-Yu Lee, and Tomas Pfister. 2024. CodecLM: Aligning Language Models with Tailored Synthetic Data. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 3712–3729, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
CodecLM: Aligning Language Models with Tailored Synthetic Data (Wang et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-naacl.235.pdf