AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preference

• URL: http://arxiv.org/abs/2410.00409v1
• Date: Tue, 1 Oct 2024 05:14:48 GMT
• Title: AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preference
• Authors: Yang Han, Yiming Wang, Rui Wang, Lu Chen, Kai Yu,
• Abstract summary: We introduce a novel human summarization preference alignment framework AlignSum. With AlignSum, PLMs like BART-Large surpass 175B GPT-3 in both automatic and human evaluations.
• Score: 22.13596750775719
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text summarization tasks commonly employ Pre-trained Language Models (PLMs) to fit diverse standard datasets. While these PLMs excel in automatic evaluations, they frequently underperform in human evaluations, indicating a deviation between their generated summaries and human summarization preferences. This discrepancy is likely due to the low quality of fine-tuning datasets and the limited availability of high-quality human-annotated data that reflect true human preference. To address this challenge, we introduce a novel human summarization preference alignment framework AlignSum. This framework consists of three parts: Firstly, we construct a Data Pymarid with extractive, abstractive, and human-annotated summary data. Secondly, we conduct the Gaussian Resampling to remove summaries with extreme lengths. Finally, we implement the two-stage hierarchical fine-tuning with Data Pymarid after Gaussian Resampling. We apply AlignSum to PLMs on the human-annotated CNN/DailyMail and BBC XSum datasets. Experiments show that with AlignSum, PLMs like BART-Large surpass 175B GPT-3 in both automatic and human evaluations. This demonstrates that AlignSum significantly enhances the alignment of language models with human summarization preferences.

Related papers

• Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback [87.37721254914476]
  We introduce a routing framework that combines inputs from humans and LMs to achieve better annotation quality. We train a performance prediction model to predict a reward model's performance on an arbitrary combination of human and LM annotations. We show that the selected hybrid mixture achieves better reward model performance compared to using either one exclusively.
  arXiv  Detail & Related papers  (2024-10-24T20:04:15Z)
• Automated Filtering of Human Feedback Data for Aligning Text-to-Image Diffusion Models [36.84880190385986]
  Fine-tuning text-to-image diffusion models with human feedback is an effective method for aligning model behavior with human intentions. However, this alignment process often suffers from slow convergence due to the large size and noise present in human feedback datasets. We propose FiFA, a novel automated data filtering algorithm designed to enhance the fine-tuning of diffusion models using human feedback datasets.
  arXiv  Detail & Related papers  (2024-10-14T05:18:07Z)
• Model-based Preference Optimization in Abstractive Summarization without Human Feedback [5.438770095369458]
  We introduce Model-based Preference Optimization (MPO) to fine-tune Large Language Models for improved summarization abilities without any human feedback. Our experiments on standard summarization datasets and various metrics demonstrate that our proposed MPO significantly enhances the quality of generated summaries without relying on human feedback.
  arXiv  Detail & Related papers  (2024-09-27T10:35:45Z)
• Chatting Up Attachment: Using LLMs to Predict Adult Bonds [0.0]
  We use GPT-4 and Claude 3 Opus to create agents that simulate adults with varying profiles, childhood memories, and attachment styles. We evaluate our models using a transcript dataset from 9 humans who underwent the same interview protocol, analyzed and labeled by mental health professionals. Our findings indicate that training the models using only synthetic data achieves performance comparable to training the models on human data.
  arXiv  Detail & Related papers  (2024-08-31T04:29:19Z)
• Towards Enhancing Coherence in Extractive Summarization: Dataset and Experiments with LLMs [70.15262704746378]
  We propose a systematically created human-annotated dataset consisting of coherent summaries for five publicly available datasets and natural language user feedback. Preliminary experiments with Falcon-40B and Llama-2-13B show significant performance improvements (10% Rouge-L) in terms of producing coherent summaries.
  arXiv  Detail & Related papers  (2024-07-05T20:25:04Z)
• Aligning Large Language Models with Self-generated Preference Data [72.99676237703099]
  We propose a new framework that boosts the alignment of large language models (LLMs) with human preferences. Our key idea is leveraging the human prior knowledge within the small (seed) data. We introduce a noise-aware preference learning algorithm to mitigate the risk of low quality within generated preference data.
  arXiv  Detail & Related papers  (2024-06-06T18:01:02Z)
• AugSumm: towards generalizable speech summarization using synthetic labels from large language model [61.73741195292997]
  Abstractive speech summarization (SSUM) aims to generate human-like summaries from speech. conventional SSUM models are mostly trained and evaluated with a single ground-truth (GT) human-annotated deterministic summary. We propose AugSumm, a method to leverage large language models (LLMs) as a proxy for human annotators to generate augmented summaries.
  arXiv  Detail & Related papers  (2024-01-10T18:39:46Z)
• Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models [115.501751261878]
  Fine-tuning language models(LMs) on human-generated data remains a prevalent practice. We investigate whether we can go beyond human data on tasks where we have access to scalar feedback. We find that ReST$EM$ scales favorably with model size and significantly surpasses fine-tuning only on human data.
  arXiv  Detail & Related papers  (2023-12-11T18:17:43Z)
• Efficient Few-Shot Fine-Tuning for Opinion Summarization [83.76460801568092]
  Abstractive summarization models are typically pre-trained on large amounts of generic texts, then fine-tuned on tens or hundreds of thousands of annotated samples. We show that a few-shot method based on adapters can easily store in-domain knowledge. We show that this self-supervised adapter pre-training improves summary quality over standard fine-tuning by 2.0 and 1.3 ROUGE-L points on the Amazon and Yelp datasets.
  arXiv  Detail & Related papers  (2022-05-04T16:38:37Z)
• Abstractive Summarization for Low Resource Data using Domain Transfer and Data Synthesis [1.148539813252112]
  We explore using domain transfer and data synthesis to improve the performance of recent abstractive summarization methods. We show that tuning state of the art model trained on newspaper data could boost performance on student reflection data. We propose a template-based model to synthesize new data, which when incorporated into training further increased ROUGE scores.
  arXiv  Detail & Related papers  (2020-02-09T17:49:08Z)

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.