SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation

• URL: http://arxiv.org/abs/2502.13674v1
• Date: Wed, 19 Feb 2025 12:31:58 GMT
• Title: SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation
• Authors: Song Duong, Florian Le Bronnec, Alexandre Allauzen, Vincent Guigue, Alberto Lumbreras, Laure Soulier, Patrick Gallinari,
• Abstract summary: Large Language Models (LLMs) often produce hallucinations, i.e., information that is unfaithful or not grounded in the input context. This paper introduces a novel self-supervised method for generating a training set of unfaithful samples. We then refine the model using a training process that encourages the generation of grounded outputs over unfaithful ones.
• Score: 55.61004653386632
• License:
• Abstract: Large Language Models (LLMs), when used for conditional text generation, often produce hallucinations, i.e., information that is unfaithful or not grounded in the input context. This issue arises in typical conditional text generation tasks, such as text summarization and data-to-text generation, where the goal is to produce fluent text based on contextual input. When fine-tuned on specific domains, LLMs struggle to provide faithful answers to a given context, often adding information or generating errors. One underlying cause of this issue is that LLMs rely on statistical patterns learned from their training data. This reliance can interfere with the model's ability to stay faithful to a provided context, leading to the generation of ungrounded information. We build upon this observation and introduce a novel self-supervised method for generating a training set of unfaithful samples. We then refine the model using a training process that encourages the generation of grounded outputs over unfaithful ones, drawing on preference-based training. Our approach leads to significantly more grounded text generation, outperforming existing self-supervised techniques in faithfulness, as evaluated through automatic metrics, LLM-based assessments, and human evaluations.

Related papers

• SPOT: Text Source Prediction from Originality Score Thresholding [6.790905400046194]
  countermeasures aim at detecting misinformation, usually involve domain specific models trained to recognize the relevance of any information. Instead of evaluating the validity of the information, we propose to investigate LLM generated text from the perspective of trust.
  arXiv  Detail & Related papers  (2024-05-30T21:51:01Z)
• Enhancing Contextual Understanding in Large Language Models through Contrastive Decoding [9.2433070542025]
  Large language models (LLMs) tend to inadequately integrate input context during text generation. We introduce a novel approach integrating contrastive decoding with adversarial irrelevant passages as negative samples.
  arXiv  Detail & Related papers  (2024-05-04T20:38:41Z)
• Curriculum-Based Self-Training Makes Better Few-Shot Learners for Data-to-Text Generation [56.98033565736974]
  We propose Curriculum-Based Self-Training (CBST) to leverage unlabeled data in a rearranged order determined by the difficulty of text generation. Our method can outperform fine-tuning and task-adaptive pre-training methods, and achieve state-of-the-art performance in the few-shot setting of data-to-text generation.
  arXiv  Detail & Related papers  (2022-06-06T16:11:58Z)
• Joint Retrieval and Generation Training for Grounded Text Generation [75.11057157342974]
  Grounded generation models appear to offer remedies, but their training typically relies on rarely-available parallel data. We propose a framework that alleviates this data constraint by jointly training a grounded generator and document retriever on the language model signal. We demonstrate that by taking advantage of external references our approach can produce more informative and interesting text in both prose and dialogue generation.
  arXiv  Detail & Related papers  (2021-05-14T00:11:38Z)
• Evaluating Factuality in Generation with Dependency-level Entailment [57.5316011554622]
  We propose a new formulation of entailment that decomposes it at the level of dependency arcs. We show that our dependency arc entailment model trained on this data can identify factual inconsistencies in paraphrasing and summarization better than sentence-level methods.
  arXiv  Detail & Related papers  (2020-10-12T06:43:10Z)
• Text Generation by Learning from Demonstrations [17.549815256968877]
  Current approaches to text generation largely rely on autoregressive models and maximum likelihood estimation. We propose GOLD: an easy-to-optimize algorithm that learns from expert demonstrations by importance weighting. According to both automatic and human evaluation, models trained by GOLD outperform those trained by MLE and policy gradient.
  arXiv  Detail & Related papers  (2020-09-16T17:58:37Z)
• Unsupervised Text Generation by Learning from Search [86.51619839836331]
  TGLS is a novel framework to unsupervised Text Generation by Learning. We demonstrate the effectiveness of TGLS on two real-world natural language generation tasks, paraphrase generation and text formalization.
  arXiv  Detail & Related papers  (2020-07-09T04:34:48Z)
• QURIOUS: Question Generation Pretraining for Text Generation [13.595014409069584]
  We propose question generation as a pretraining method, which better aligns with the text generation objectives. Our text generation models pretrained with this method are better at understanding the essence of the input and are better language models for the target task.
  arXiv  Detail & Related papers  (2020-04-23T08:41:52Z)
• PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation [92.7366819044397]
  Self-supervised pre-training has emerged as a powerful technique for natural language understanding and generation. This work presents PALM with a novel scheme that jointly pre-trains an autoencoding and autoregressive language model on a large unlabeled corpus. An extensive set of experiments show that PALM achieves new state-of-the-art results on a variety of language generation benchmarks.
  arXiv  Detail & Related papers  (2020-04-14T06:25:36Z)

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.