paper-with-me

Papers

Self-Alignment with Instruction Backtranslation

2023-08-11 · Xian Li, Ping Yu, Chunting Zhou, Timo Schick, Omer Levy, Luke Zettlemoyer, Jason Weston, Mike Lewis

We present a scalable method to build a high quality instruction following language model by automatically labelling human-written text with corresponding instructions. Our approach, named instruction backtranslation, starts with a language model finetuned on a small amount of seed data, and a given web corpus. The seed model is used to construct training examples by generating instruction prompts for web documents (self-augmentation), and then selecting high quality examples from among these candidates (self-curation). This data is then used to finetune a stronger model. Finetuning LLaMa on two iterations of our approach yields a model that outperforms all other LLaMa-based models on the Alpaca leaderboard not relying on distillation data, demonstrating highly effective self-alignment.

📄 PDF Abstract BibTeX arXiv:2308.06259

Code (2)

Spico197/Humback pytorch
davidkim205/komt pytorch

Tasks

Instruction FollowingLanguage ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

Better Alignment with Instruction Back-and-Forth Translation

2024-08-08 · Thao Nguyen, Jeffrey Li, Sewoong Oh, Ludwig Schmidt 외

We propose a new method, instruction back-and-forth translation, to construct high-quality synthetic data grounded in world knowledge for aligning large language models (LLMs). Given documents from a web corpus, we gener…

DiversityTranslationWorld Knowledge

Physician Detection of Clinical Harm in Machine Translation: Quality Estimation Aids in Reliance and Backtranslation Identifies Critical Errors

2023-10-25 · Nikita Mehandru, Sweta Agrawal, Yimin Xiao, Elaine C Khoong 외

A major challenge in the practical use of Machine Translation (MT) is that users lack guidance to make informed decisions about when to rely on outputs. Progress in quality estimation research provides techniques to auto…

Decision MakingMachine Translation

Language Models can Self-Lengthen to Generate Long Texts

2024-10-31 · Shanghaoran Quan, Tianyi Tang, Bowen Yu, An Yang 외

Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to process long contexts, yet a notable gap remains in generating long, aligned outputs. This limitation stems from a training…

Text Generation

MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training

2025-02-17 · Hui Huang, Jiaheng Liu, Yancheng He, Shilong Li 외

Complex instruction-following with elaborate constraints is imperative for Large Language Models (LLMs). While existing methods have constructed data for complex instruction alignment, they all rely on a more advanced mo…

Instruction Following

Self-Specialization: Uncovering Latent Expertise within Large Language Models

2023-09-29 · Junmo Kang, Hongyin Luo, Yada Zhu, Jacob Hansen 외

Recent works have demonstrated the effectiveness of self-alignment in which a large language model is aligned to follow general instructions using instructional data generated from the model itself starting from a handfu…

HallucinationInstruction FollowingLanguage ModelingLanguage Modelling+1