Joint Repetition Suppression and Content Moderation of Large Language Models

• URL: http://arxiv.org/abs/2304.10611v2
• Date: Mon, 5 Jun 2023 18:16:29 GMT
• Title: Joint Repetition Suppression and Content Moderation of Large Language Models
• Authors: Minghui Zhang, Alex Sokolov, Weixin Cai, Si-Qing Chen
• Abstract summary: Natural language generation (NLG) is one of the most impactful fields in NLP. In this paper, we apply non-exact repetition suppression using token and sequence level unlikelihood loss. We also explore the framework of unlikelihood training objective in order to jointly endow the model with abilities to avoid generating offensive words.
• Score: 4.9990392459395725
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Natural language generation (NLG) is one of the most impactful fields in NLP, and recent years have witnessed its evolution brought about by large language models (LLMs). As the key instrument for writing assistance applications, they are generally prone to replicating or extending offensive content provided in the input. In low-resource data regime, they can also lead to repetitive outputs. Usually, offensive content and repetitions are mitigated with post-hoc methods, including n-gram level blocklists, top-k and nucleus sampling. In this paper, we apply non-exact repetition suppression using token and sequence level unlikelihood loss, and further explore the framework of unlikelihood training objective in order to jointly endow the model with abilities to avoid generating offensive words and phrases from the beginning. Finally, with comprehensive experiments, we demonstrate that our proposed methods work exceptionally in controlling the repetition and content quality of LLM outputs.

Related papers

• Vector-Quantized Prompt Learning for Paraphrase Generation [18.40940464497253]
  This paper proposes to generate diverse and high-quality paraphrases by exploiting the pre-trained models with instance-dependent prompts. Extensive experiments demonstrate that the proposed method achieves new state-of-art results on three benchmark datasets.
  arXiv  Detail & Related papers  (2023-11-25T07:13:06Z)
• HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models [81.56455625624041]
  We introduce the first open-source benchmark to utilize external large language models (LLMs) for ASR error correction. The proposed benchmark contains a novel dataset, HyPoradise (HP), encompassing more than 334,000 pairs of N-best hypotheses. LLMs with reasonable prompt and its generative capability can even correct those tokens that are missing in N-best list.
  arXiv  Detail & Related papers  (2023-09-27T14:44:10Z)
• Mitigating the Learning Bias towards Repetition by Self-Contrastive Training for Open-Ended Generation [92.42032403795879]
  We show that pretrained language models (LMs) such as GPT2 still tend to generate repetitive texts. We attribute their overestimation of token-level repetition probabilities to the learning bias. We find that LMs use longer-range dependencies to predict repetitive tokens than non-repetitive ones, which may be the cause of sentence-level repetition loops.
  arXiv  Detail & Related papers  (2023-07-04T07:53:55Z)
• Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM [31.25193238045053]
  We introduce a novel method, namely GenCo, which leverages the strong generative power of large language models to assist in training a smaller language model. In our method, an LLM plays an important role in the self-training loop of a smaller model in two important ways. It helps crafting additional high-quality training pairs, by rewriting input texts conditioned on predicted labels.
  arXiv  Detail & Related papers  (2023-04-24T07:35:38Z)
• Learning with Rejection for Abstractive Text Summarization [42.15551472507393]
  We propose a training objective for abstractive summarization based on rejection learning. We show that our method considerably improves the factuality of generated summaries in automatic and human evaluations.
  arXiv  Detail & Related papers  (2023-02-16T19:07:08Z)
• Language Model Pre-Training with Sparse Latent Typing [66.75786739499604]
  We propose a new pre-training objective, Sparse Latent Typing, which enables the model to sparsely extract sentence-level keywords with diverse latent types. Experimental results show that our model is able to learn interpretable latent type categories in a self-supervised manner without using any external knowledge.
  arXiv  Detail & Related papers  (2022-10-23T00:37:08Z)
• Improving Pre-trained Language Model Fine-tuning with Noise Stability Regularization [94.4409074435894]
  We propose a novel and effective fine-tuning framework, named Layerwise Noise Stability Regularization (LNSR) Specifically, we propose to inject the standard Gaussian noise and regularize hidden representations of the fine-tuned model. We demonstrate the advantages of the proposed method over other state-of-the-art algorithms including L2-SP, Mixout and SMART.
  arXiv  Detail & Related papers  (2022-06-12T04:42:49Z)
• SDA: Improving Text Generation with Self Data Augmentation [88.24594090105899]
  We propose to improve the standard maximum likelihood estimation (MLE) paradigm by incorporating a self-imitation-learning phase for automatic data augmentation. Unlike most existing sentence-level augmentation strategies, our method is more general and could be easily adapted to any MLE-based training procedure.
  arXiv  Detail & Related papers  (2021-01-02T01:15:57Z)
• Diverse Keyphrase Generation with Neural Unlikelihood Training [6.645227801791013]
  We study sequence-to-sequence (S2S) keyphrase generation models from the perspective of diversity. We first analyze the extent of information redundancy present in the outputs generated by a baseline model trained using maximum likelihood estimation (MLE)
  arXiv  Detail & Related papers  (2020-10-15T11:12:26Z)
• Contextualized Perturbation for Textual Adversarial Attack [56.370304308573274]
  Adversarial examples expose the vulnerabilities of natural language processing (NLP) models. This paper presents CLARE, a ContextuaLized AdversaRial Example generation model that produces fluent and grammatical outputs.
  arXiv  Detail & Related papers  (2020-09-16T06:53:15Z)
• ColdGANs: Taming Language GANs with Cautious Sampling Strategies [29.943949944682196]
  Generative Adversarial Networks (GANs) can mitigate limitations but the discrete nature of text has hindered their application to language generation. We show how classical sampling results in unstable training. We propose to consider alternative exploration strategies in a GAN framework that we name ColdGANs, where we force the sampling to be close to the distribution modes to get smoother learning dynamics. For the first time, to the best of our knowledge, the proposed language GANs compare favorably to MLE, and obtain improvements over the state-of-the-art on three generative tasks.
  arXiv  Detail & Related papers  (2020-06-08T14:48:14Z)

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.