Personalized Abstractive Summarization by Tri-agent Generation Pipeline

• URL: http://arxiv.org/abs/2305.02483v2
• Date: Fri, 1 Mar 2024 23:41:24 GMT
• Title: Personalized Abstractive Summarization by Tri-agent Generation Pipeline
• Authors: Wen Xiao, Yujia Xie, Giuseppe Carenini, Pengcheng He
• Abstract summary: We propose a tri-agent generation pipeline comprising a generator, an instructor, and an editor to enhance output personalization. The generator produces an initial output, the instructor automatically generates editing instructions based on user preferences, and the editor refines the output to align with those preferences. We train the instructor using editor-steered reinforcement learning, leveraging feedback from a large-scale editor model to optimize instruction generation.
• Score: 69.38358552893762
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Tailoring outputs from large language models, like ChatGPT, to implicit user preferences remains a challenge despite their impressive generative capabilities. In this paper, we propose a tri-agent generation pipeline comprising a generator, an instructor, and an editor to enhance output personalization. The generator produces an initial output, the instructor automatically generates editing instructions based on user preferences, and the editor refines the output to align with those preferences. The inference-only large language model (ChatGPT) serves as both the generator and editor, with a smaller model acting as the instructor to guide output generation. We train the instructor using editor-steered reinforcement learning, leveraging feedback from a large-scale editor model to optimize instruction generation. Experimental results on two abstractive summarization datasets demonstrate the effectiveness of our approach in generating outputs that better meet user expectations. Code is available at \url{https://github.com/Wendy-Xiao/chatgpt_editing_summ}

Related papers

• Specify and Edit: Overcoming Ambiguity in Text-Based Image Editing [24.316956641791034]
  We propose a zero-shot inference pipeline for diffusion-based editing systems. We use a large language model (LLM) to decompose the input instruction into specific instructions. Our pipeline improves the interpretability of editing models, and boosts the output diversity.
  arXiv  Detail & Related papers  (2024-07-29T17:59:57Z)
• Prompt Optimization via Adversarial In-Context Learning [51.18075178593142]
  adv-ICL is implemented as a two-player game between a generator and a discriminator. The generator tries to generate realistic enough output to fool the discriminator. We show that adv-ICL results in significant improvements over state-of-the-art prompt optimization techniques.
  arXiv  Detail & Related papers  (2023-12-05T09:44:45Z)
• SPROUT: an Interactive Authoring Tool for Generating Programming Tutorials with the Visualization of Large Language Models [19.885485760758783]
  The rapid development of large language models (LLMs) has revolutionized the efficiency of creating programming tutorials. We introduce a novel approach that breaks down the programming tutorial creation task into actionable steps. We then present SPROUT, an authoring tool equipped with a series of interactive visualizations that empower users to have greater control and understanding of the programming tutorial creation process.
  arXiv  Detail & Related papers  (2023-12-04T10:46:52Z)
• 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)
• PePe: Personalized Post-editing Model utilizing User-generated Post-edits [28.749742163017544]
  We introduce a personalized automatic post-editing framework to address this challenge. We first collect post-editing data that connotes the user preference from a live machine translation system. We then propose a model that combines a discriminator module and user-specific parameters on the APE framework.
  arXiv  Detail & Related papers  (2022-09-21T06:09:58Z)
• Learning Structural Edits via Incremental Tree Transformations [102.64394890816178]
  We present a generic model for incremental editing of structured data (i.e., "structural edits") Our editor learns to iteratively generate tree edits (e.g., deleting or adding a subtree) and applies them to the partially edited data. We evaluate our proposed editor on two source code edit datasets, where results show that, with the proposed edit encoder, our editor significantly improves accuracy over previous approaches.
  arXiv  Detail & Related papers  (2021-01-28T16:11:32Z)
• Contrastive Triple Extraction with Generative Transformer [72.21467482853232]
  We introduce a novel model, contrastive triple extraction with a generative transformer. Specifically, we introduce a single shared transformer module for encoder-decoder-based generation. To generate faithful results, we propose a novel triplet contrastive training object.
  arXiv  Detail & Related papers  (2020-09-14T05:29:24Z)
• POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training [93.79766670391618]
  We present POINTER, a novel insertion-based approach for hard-constrained text generation. The proposed method operates by progressively inserting new tokens between existing tokens in a parallel manner. The resulting coarse-to-fine hierarchy makes the generation process intuitive and interpretable.
  arXiv  Detail & Related papers  (2020-05-01T18:11:54Z)

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.