Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization

• URL: http://arxiv.org/abs/2210.04492v2
• Date: Fri, 2 Jun 2023 04:13:08 GMT
• Title: Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization
• Authors: Zonghan Yang, Xiaoyuan Yi, Peng Li, Yang Liu, Xing Xie
• Abstract summary: Pre-trained language models (PLMs) have prospered in various natural language generation (NLG) tasks due to their ability to generate fairly fluent text. These models are observed to capture and reproduce harmful contents in training corpora, typically toxic language and social biases, raising severe moral issues. We propose the first unified framework of detoxifying and debiasing called UDDIA, which jointly formalizes these two problems as rectifying the output space.
• Score: 32.50246008433889
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Warning: this paper contains model outputs exhibiting offensiveness and biases. Recently pre-trained language models (PLMs) have prospered in various natural language generation (NLG) tasks due to their ability to generate fairly fluent text. Nevertheless, these models are observed to capture and reproduce harmful contents in training corpora, typically toxic language and social biases, raising severe moral issues. Prior works on ethical NLG tackle detoxifying and debiasing separately, which is problematic since we find debiased models still exhibit toxicity while detoxified ones even exacerbate social biases. To address such a challenge, we propose the first unified framework of detoxifying and debiasing called UDDIA, which jointly formalizes these two problems as rectifying the output space. We theoretically interpret our framework as learning a text distribution mixing weighted attributes. Besides, UDDIA conducts adaptive optimization of only a few parameters during decoding based on a parameter-efficient tuning schema without any training data. This leads to minimal generation quality loss and improved rectification performance with acceptable computational cost. Experimental results demonstrate that compared to several strong baselines, UDDIA achieves debiasing and detoxifying simultaneously and better balances efficiency and effectiveness, taking a further step towards practical ethical NLG.

Related papers

• Language Rectified Flow: Advancing Diffusion Language Generation with Probabilistic Flows [53.31856123113228]
  This paper proposes Language Rectified Flow (ours) Our method is based on the reformulation of the standard probabilistic flow models. Experiments and ablation studies demonstrate that our method can be general, effective, and beneficial for many NLP tasks.
  arXiv  Detail & Related papers  (2024-03-25T17:58:22Z)
• Fine-Grained Detoxification via Instance-Level Prefixes for Large Language Models [26.474136481185724]
  Fine-grained detoxification via instance-level prefixes (FGDILP) to mitigate toxic text without additional cost. FGDILP contrasts the contextualized representation in attention space using a positive prefix-prepended prompt. We validate that FGDILP enables controlled text generation with regard to toxicity at both the utterance and context levels.
  arXiv  Detail & Related papers  (2024-02-23T09:04:48Z)
• Contrastive Perplexity for Controlled Generation: An Application in Detoxifying Large Language Models [25.212449683397647]
  This paper studies the integration of a contrastive learning objective for fine-tuning LLMs for implicit knowledge editing and controlled text generation. To facilitate training the model in a self-supervised fashion, we leverage an off-the-shelf LLM for training data generation.
  arXiv  Detail & Related papers  (2024-01-16T16:49:39Z)
• An Empirical Analysis of Parameter-Efficient Methods for Debiasing Pre-Trained Language Models [55.14405248920852]
  We conduct experiments with prefix tuning, prompt tuning, and adapter tuning on different language models and bias types to evaluate their debiasing performance. We find that the parameter-efficient methods are effective in mitigating gender bias, where adapter tuning is consistently the most effective. We also find that prompt tuning is more suitable for GPT-2 than BERT, and racial and religious bias is less effective when it comes to racial and religious bias.
  arXiv  Detail & Related papers  (2023-06-06T23:56:18Z)
• A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity [84.6421260559093]
  This study is the largest set of experiments to validate, quantify, and expose undocumented intuitions about text pretraining. Our findings indicate there does not exist a one-size-fits-all solution to filtering training data.
  arXiv  Detail & Related papers  (2023-05-22T15:57:53Z)
• 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)
• NoiER: An Approach for Training more Reliable Fine-TunedDownstream Task Models [54.184609286094044]
  We propose noise entropy regularisation (NoiER) as an efficient learning paradigm that solves the problem without auxiliary models and additional data. The proposed approach improved traditional OOD detection evaluation metrics by 55% on average compared to the original fine-tuned models.
  arXiv  Detail & Related papers  (2021-08-29T06:58:28Z)
• Understanding and Improving Lexical Choice in Non-Autoregressive Translation [98.11249019844281]
  We propose to expose the raw data to NAT models to restore the useful information of low-frequency words. Our approach pushes the SOTA NAT performance on the WMT14 English-German and WMT16 Romanian-English datasets up to 27.8 and 33.8 BLEU points, respectively.
  arXiv  Detail & Related papers  (2020-12-29T03:18:50Z)
• 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)

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.