Self-Alignment with Instruction Backtranslation

• URL: http://arxiv.org/abs/2308.06259v3
• Date: Tue, 12 Mar 2024 05:22:46 GMT
• Title: Self-Alignment with Instruction Backtranslation
• Authors: Xian Li, Ping Yu, Chunting Zhou, Timo Schick, Omer Levy, Luke Zettlemoyer, Jason Weston, Mike Lewis
• Abstract summary: We present a 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.
• Score: 162.02529653768096
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Removing Distributional Discrepancies in Captions Improves Image-Text Alignment [76.31530836622694]
  We introduce a model designed to improve the prediction of image-text alignment. Our approach focuses on generating high-quality training datasets for the alignment task. We also demonstrate the applicability of our model by ranking the images generated by text-to-image models based on text alignment.
  arXiv  Detail & Related papers  (2024-10-01T17:50:17Z)
• Align$^2$LLaVA: Cascaded Human and Large Language Model Preference Alignment for Multi-modal Instruction Curation [56.75665429851673]
  This paper introduces a novel instruction curation algorithm, derived from two unique perspectives, human and LLM preference alignment. Experiments demonstrate that we can maintain or even improve model performance by compressing synthetic multimodal instructions by up to 90%.
  arXiv  Detail & Related papers  (2024-09-27T08:20:59Z)
• Improving Sentence Embeddings with Automatic Generation of Training Data Using Few-shot Examples [13.946626388239443]
  We aim to improve sentence embeddings without using large manually annotated datasets. We will focus on automatic dataset generation through few-shot learning and explore the appropriate methods to leverage few-shot examples.
  arXiv  Detail & Related papers  (2024-02-23T06:33:51Z)
• Self-Supervised Representation Learning for Online Handwriting Text Classification [0.8594140167290099]
  We propose the novel Part of Stroke Masking (POSM) as a pretext task for pretraining models to extract informative representations from the online handwriting of individuals in English and Chinese languages. To evaluate the quality of the extracted representations, we use both intrinsic and extrinsic evaluation methods. The pretrained models are fine-tuned to achieve state-of-the-art results in tasks such as writer identification, gender classification, and handedness classification.
  arXiv  Detail & Related papers  (2023-10-10T14:07:49Z)
• LongForm: Effective Instruction Tuning with Reverse Instructions [74.14035528786997]
  We introduce the LongForm-C dataset, which is created by reverse instructions. We generate instructions via LLMs for human-written corpus examples using reverse instructions. Our models outperform 10x larger language models without instruction tuning on tasks such as story/recipe generation and long-form question answering.
  arXiv  Detail & Related papers  (2023-04-17T17:36:35Z)
• Self-Instruct: Aligning Language Models with Self-Generated Instructions [76.42871502364697]
  Self-Instruct is a framework for improving the instruction-following capabilities of pretrained language models. Our pipeline generates instructions, input, and output samples from a language model, then filters invalid or similar ones before using them to finetune the original model. For further evaluation, we curate a set of expert-written instructions for novel tasks, and show through human evaluation that tuning GPT3 with Self-Instruct outperforms using existing public instruction datasets by a large margin.
  arXiv  Detail & Related papers  (2022-12-20T18:59:19Z)
• Unsupervised Paraphrasing with Pretrained Language Models [85.03373221588707]
  We propose a training pipeline that enables pre-trained language models to generate high-quality paraphrases in an unsupervised setting. Our recipe consists of task-adaptation, self-supervision, and a novel decoding algorithm named Dynamic Blocking. We show with automatic and human evaluations that our approach achieves state-of-the-art performance on both the Quora Question Pair and the ParaNMT datasets.
  arXiv  Detail & Related papers  (2020-10-24T11:55:28Z)
• Abstractive Text Summarization based on Language Model Conditioning and Locality Modeling [4.525267347429154]
  We train a Transformer-based neural model on the BERT language model. In addition, we propose a new method of BERT-windowing, which allows chunk-wise processing of texts longer than the BERT window size. The results of our models are compared to a baseline and the state-of-the-art models on the CNN/Daily Mail dataset.
  arXiv  Detail & Related papers  (2020-03-29T14:00:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.