Reducing Non-Normative Text Generation from Language Models

• URL: http://arxiv.org/abs/2001.08764v2
• Date: Thu, 29 Oct 2020 19:37:27 GMT
• Title: Reducing Non-Normative Text Generation from Language Models
• Authors: Xiangyu Peng, Siyan Li, Spencer Frazier, Mark Riedl
• Abstract summary: Large-scale language models such as GPT-2 are pretrained on diverse corpora scraped from the internet. We introduce a technique for fine-tuning GPT-2 using a policy gradient reinforcement learning technique and a normative text classifier.
• Score: 7.293053431456775
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large-scale, transformer-based language models such as GPT-2 are pretrained on diverse corpora scraped from the internet. Consequently, they are prone to generating non-normative text (i.e. in violation of social norms). We introduce a technique for fine-tuning GPT-2, using a policy gradient reinforcement learning technique and a normative text classifier to produce reward and punishment values. We evaluate our technique on five data sets using automated and human participant experiments. The normative text classifier is 81-90% accurate when compared to gold-standard human judgments of normative and non-normative generated text. Our normative fine-tuning technique is able to reduce non-normative text by 27-61%, depending on the data set.

Related papers

• GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation [93.55550787058012]
  This paper presents an automatic, versatile, and human-aligned evaluation metric for text-to-3D generative models. To this end, we first develop a prompt generator using GPT-4V to generate evaluating prompts. We then design a method instructing GPT-4V to compare two 3D assets according to user-defined criteria.
  arXiv  Detail & Related papers  (2024-01-08T18:52:09Z)
• Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models [39.37532848489779]
  We propose Error Norm Truncation (ENT), a robust enhancement method to the standard training objective that truncates noisy data. We show that ENT improves generation quality over standard training and previous soft and hard truncation methods.
  arXiv  Detail & Related papers  (2023-10-02T01:30:27Z)
• When Automated Assessment Meets Automated Content Generation: Examining Text Quality in the Era of GPTs [5.952677937197871]
  We empirically assess the differences in how ML-based scoring models trained on human content assess the quality of content generated by humans versus GPTs. Results of our benchmark analysis reveal that transformer pretrained language models (PLMs) more accurately score human essay quality as compared to CNN/RNN and feature-based ML methods.
  arXiv  Detail & Related papers  (2023-09-25T19:32:18Z)
• A Chat About Boring Problems: Studying GPT-based text normalization [22.64840464909988]
  We show the capacity of Large-Language Models for text normalization in few-shot scenarios. We find LLM based text normalization to achieve error rates around 40% lower than top normalization systems. We create a new taxonomy of text normalization errors and apply it to results from GPT-3.5-Turbo and GPT-4.0.
  arXiv  Detail & Related papers  (2023-09-23T16:32:59Z)
• INSTRUCTSCORE: Explainable Text Generation Evaluation with Finegrained Feedback [80.57617091714448]
  We present InstructScore, an explainable evaluation metric for text generation. We fine-tune a text evaluation metric based on LLaMA, producing a score for generated text and a human readable diagnostic report.
  arXiv  Detail & Related papers  (2023-05-23T17:27:22Z)
• Collaborative Generative AI: Integrating GPT-k for Efficient Editing in Text-to-Image Generation [114.80518907146792]
  We investigate the potential of utilizing large-scale language models, such as GPT-k, to improve the prompt editing process for text-to-image generation. We compare the common edits made by humans and GPT-k, evaluate the performance of GPT-k in prompting T2I, and examine factors that may influence this process.
  arXiv  Detail & Related papers  (2023-05-18T21:53:58Z)
• SESCORE2: Learning Text Generation Evaluation via Synthesizing Realistic Mistakes [93.19166902594168]
  We propose SESCORE2, a self-supervised approach for training a model-based metric for text generation evaluation. Key concept is to synthesize realistic model mistakes by perturbing sentences retrieved from a corpus. We evaluate SESCORE2 and previous methods on four text generation tasks across three languages.
  arXiv  Detail & Related papers  (2022-12-19T09:02:16Z)
• DIALOG-22 RuATD Generated Text Detection [0.0]
  Detectors that can distinguish between TGM-generated text and human-written ones play an important role in preventing abuse of TGM. We describe our pipeline for the two DIALOG-22 RuATD tasks: detecting generated text (binary task) and classification of which model was used to generate text.
  arXiv  Detail & Related papers  (2022-06-16T09:33:26Z)
• Classifiers are Better Experts for Controllable Text Generation [63.17266060165098]
  We show that the proposed method significantly outperforms recent PPLM, GeDi, and DExperts on PPL and sentiment accuracy based on the external classifier of generated texts. The same time, it is also easier to implement and tune, and has significantly fewer restrictions and requirements.
  arXiv  Detail & Related papers  (2022-05-15T12:58:35Z)
• A Benchmark Corpus for the Detection of Automatically Generated Text in Academic Publications [0.02578242050187029]
  This paper presents two datasets comprised of artificially generated research content. In the first case, the content is completely generated by the GPT-2 model after a short prompt extracted from original papers. The partial or hybrid dataset is created by replacing several sentences of abstracts with sentences that are generated by the Arxiv-NLP model. We evaluate the quality of the datasets comparing the generated texts to aligned original texts using fluency metrics such as BLEU and ROUGE.
  arXiv  Detail & Related papers  (2022-02-04T08:16:56Z)
• Improving Text Generation with Student-Forcing Optimal Transport [122.11881937642401]
  We propose using optimal transport (OT) to match the sequences generated in training and testing modes. An extension is also proposed to improve the OT learning, based on the structural and contextual information of the text sequences. The effectiveness of the proposed method is validated on machine translation, text summarization, and text generation tasks.
  arXiv  Detail & Related papers  (2020-10-12T19:42:25Z)

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.