Detection and Measurement of Syntactic Templates in Generated Text

• URL: http://arxiv.org/abs/2407.00211v2
• Date: Sun, 06 Oct 2024 10:05:06 GMT
• Title: Detection and Measurement of Syntactic Templates in Generated Text
• Authors: Chantal Shaib, Yanai Elazar, Junyi Jessy Li, Byron C. Wallace,
• Abstract summary: We offer an analysis of syntactic features to characterize general repetition in models. We find that models tend to produce templated text in downstream tasks at a higher rate than what is found in human-reference texts.
• Score: 58.111650675717414
• License:
• Abstract: Recent work on evaluating the diversity of text generated by LLMs has focused on word-level features. Here we offer an analysis of syntactic features to characterize general repetition in models, beyond frequent n-grams. Specifically, we define syntactic templates and show that models tend to produce templated text in downstream tasks at a higher rate than what is found in human-reference texts. We find that most (76%) templates in model-generated text can be found in pre-training data (compared to only 35% of human-authored text), and are not overwritten during fine-tuning processes such as RLHF. This connection to the pre-training data allows us to analyze syntactic templates in models where we do not have the pre-training data. We also find that templates as features are able to differentiate between models, tasks, and domains, and are useful for qualitatively evaluating common model constructions. Finally, we demonstrate the use of templates as a useful tool for analyzing style memorization of training data in LLMs.

Related papers

• Explaining Datasets in Words: Statistical Models with Natural Language Parameters [66.69456696878842]
  We introduce a family of statistical models -- including clustering, time series, and classification models -- parameterized by natural language predicates. We apply our framework to a wide range of problems: taxonomizing user chat dialogues, characterizing how they evolve across time, finding categories where one language model is better than the other.
  arXiv  Detail & Related papers  (2024-09-13T01:40:20Z)
• Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvements [10.687101698324897]
  Large language models demonstrate a remarkable capability for learning to solve new tasks from a few examples. The prompt template, or the way the input examples are formatted to obtain the prompt, is an important yet often overlooked aspect of in-context learning. We show that a poor choice of the template can reduce the performance of the strongest models and inference methods to a random guess level.
  arXiv  Detail & Related papers  (2024-01-12T18:58:26Z)
• A Quality-based Syntactic Template Retriever for Syntactically-controlled Paraphrase Generation [67.98367574025797]
  Existing syntactically-controlled paraphrase generation models perform promisingly with human-annotated or well-chosen syntactic templates. The prohibitive cost makes it unfeasible to manually design decent templates for every source sentence. We propose a novel Quality-based Syntactic Template Retriever (QSTR) to retrieve templates based on the quality of the to-be-generated paraphrases.
  arXiv  Detail & Related papers  (2023-10-20T03:55:39Z)
• TrueTeacher: Learning Factual Consistency Evaluation with Large Language Models [20.09470051458651]
  We introduce TrueTeacher, a method for generating synthetic data by annotating diverse model-generated summaries. Unlike prior work, TrueTeacher does not rely on human-written summaries, and is multilingual by nature.
  arXiv  Detail & Related papers  (2023-05-18T17:58:35Z)
• A Unified Understanding of Deep NLP Models for Text Classification [88.35418976241057]
  We have developed a visual analysis tool, DeepNLPVis, to enable a unified understanding of NLP models for text classification. The key idea is a mutual information-based measure, which provides quantitative explanations on how each layer of a model maintains the information of input words in a sample. A multi-level visualization, which consists of a corpus-level, a sample-level, and a word-level visualization, supports the analysis from the overall training set to individual samples.
  arXiv  Detail & Related papers  (2022-06-19T08:55:07Z)
• Evaluation of HTR models without Ground Truth Material [2.4792948967354236]
  evaluation of Handwritten Text Recognition models during their development is straightforward. But the evaluation process becomes tricky as soon as we switch from development to application. We show that lexicon-based evaluation can compete with lexicon-based methods.
  arXiv  Detail & Related papers  (2022-01-17T01:26:09Z)
• How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN [63.79300884115027]
  Current language models can generate high-quality text. Are they simply copying text they have seen before, or have they learned generalizable linguistic abstractions? We introduce RAVEN, a suite of analyses for assessing the novelty of generated text.
  arXiv  Detail & Related papers  (2021-11-18T04:07:09Z)
• Improving Compositional Generalization with Self-Training for Data-to-Text Generation [36.973617793800315]
  We study the compositional generalization of current generation models in data-to-text tasks. By simulating structural shifts in the compositional Weather dataset, we show that T5 models fail to generalize to unseen structures. We propose an approach based on self-training using finetuned BLEURT for pseudo-response selection.
  arXiv  Detail & Related papers  (2021-10-16T04:26:56Z)
• Syntax-Enhanced Pre-trained Model [49.1659635460369]
  We study the problem of leveraging the syntactic structure of text to enhance pre-trained models such as BERT and RoBERTa. Existing methods utilize syntax of text either in the pre-training stage or in the fine-tuning stage, so that they suffer from discrepancy between the two stages. We present a model that utilizes the syntax of text in both pre-training and fine-tuning stages.
  arXiv  Detail & Related papers  (2020-12-28T06:48:04Z)

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.