Value Alignment from Unstructured Text

Inkit Padhi, Karthikeyan Natesan Ramamurthy, Prasanna Sattigeri, Manish Nagireddy, Pierre Dognin, Kush R. Varshney


Abstract
Aligning large language models (LLMs) to value systems has emerged as a significant area of research within the fields of AI and NLP. Currently, this alignment process relies on the availability of high-quality supervised and preference data, which can be both time-consuming and expensive to curate or annotate. In this paper, we introduce a systematic end-to-end methodology for aligning LLMs to the implicit and explicit values represented in unstructured text data. Our proposed approach leverages the use of scalable synthetic data generation techniques to effectively align the model to the values present in the unstructured data. Through two distinct use-cases, we demonstrate the efficiency of our methodology on the Mistral-7B-Instruct model. Our approach credibly aligns LLMs to the values embedded within documents, and shows improved performance against other approaches, as quantified through the use of automatic metrics and win rates.
Anthology ID:
2024.emnlp-industry.81
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track
Month:
November
Year:
2024
Address:
Miami, Florida, US
Editors:
Franck Dernoncourt, Daniel Preoţiuc-Pietro, Anastasia Shimorina
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1083–1095
Language:
URL:
https://aclanthology.org/2024.emnlp-industry.81
DOI:
Bibkey:
Cite (ACL):
Inkit Padhi, Karthikeyan Natesan Ramamurthy, Prasanna Sattigeri, Manish Nagireddy, Pierre Dognin, and Kush R. Varshney. 2024. Value Alignment from Unstructured Text. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 1083–1095, Miami, Florida, US. Association for Computational Linguistics.
Cite (Informal):
Value Alignment from Unstructured Text (Padhi et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-industry.81.pdf