Linguistically-Informed Transformations (LIT): A Method for Automatically Generating Contrast Sets

• URL: http://arxiv.org/abs/2010.08580v3
• Date: Thu, 12 Nov 2020 18:16:58 GMT
• Title: Linguistically-Informed Transformations (LIT): A Method for Automatically Generating Contrast Sets
• Authors: Chuanrong Li, Lin Shengshuo, Leo Z. Liu, Xinyi Wu, Xuhui Zhou, Shane Steinert-Threlkeld
• Abstract summary: We propose a Linguistically-Informed Transformation (LIT) method to automatically generate contrast sets. Experiments show that current pretrained language models struggle on our automatically generated contrast sets. We improve models' performance on the contrast sets by apply-ing LIT to augment the training data, without affecting performance on the original data.
• Score: 13.706520309917634
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Although large-scale pretrained language models, such as BERT and RoBERTa, have achieved superhuman performance on in-distribution test sets, their performance suffers on out-of-distribution test sets (e.g., on contrast sets). Building contrast sets often re-quires human-expert annotation, which is expensive and hard to create on a large scale. In this work, we propose a Linguistically-Informed Transformation (LIT) method to automatically generate contrast sets, which enables practitioners to explore linguistic phenomena of interests as well as compose different phenomena. Experimenting with our method on SNLI and MNLI shows that current pretrained language models, although being claimed to contain sufficient linguistic knowledge, struggle on our automatically generated contrast sets. Furthermore, we improve models' performance on the contrast sets by apply-ing LIT to augment the training data, without affecting performance on the original data.

Related papers

• Tuning-Free Personalized Alignment via Trial-Error-Explain In-Context Learning [74.56097953187994]
  We present Trial-Error-Explain In-Context Learning (TICL), a tuning-free method that personalizes language models for text generation tasks. TICL iteratively expands an in-context learning prompt via a trial-error-explain process, adding model-generated negative samples and explanations. TICL achieves up to 91.5% against the previous state-of-the-art and outperforms competitive tuning-free baselines for personalized alignment tasks.
  arXiv  Detail & Related papers  (2025-02-13T05:20:21Z)
• From Superficial Patterns to Semantic Understanding: Fine-Tuning Language Models on Contrast Sets [0.21756081703275998]
  This study explores how the robustness of a language model can be improved by exposing it to small amounts of more complex contrast sets during training. With this approach, the model recovers performance and achieves nearly 90% accuracy on contrast sets, highlighting the importance of diverse and challenging training data.
  arXiv  Detail & Related papers  (2025-01-05T23:19:55Z)
• How Hard is this Test Set? NLI Characterization by Exploiting Training Dynamics [49.9329723199239]
  We propose a method for the automated creation of a challenging test set without relying on the manual construction of artificial and unrealistic examples. We categorize the test set of popular NLI datasets into three difficulty levels by leveraging methods that exploit training dynamics. When our characterization method is applied to the training set, models trained with only a fraction of the data achieve comparable performance to those trained on the full dataset.
  arXiv  Detail & Related papers  (2024-10-04T13:39:21Z)
• Harnessing the Intrinsic Knowledge of Pretrained Language Models for Challenging Text Classification Settings [5.257719744958367]
  This thesis explores three challenging settings in text classification by leveraging the intrinsic knowledge of pretrained language models (PLMs) We develop models that utilize features based on contextualized word representations from PLMs, achieving performance that rivals or surpasses human accuracy. Lastly, we tackle the sensitivity of large language models to in-context learning prompts by selecting effective demonstrations.
  arXiv  Detail & Related papers  (2024-08-28T09:07:30Z)
• DETAIL: Task DEmonsTration Attribution for Interpretable In-context Learning [75.68193159293425]
  In-context learning (ICL) allows transformer-based language models to learn a specific task with a few "task demonstrations" without updating their parameters. We propose an influence function-based attribution technique, DETAIL, that addresses the specific characteristics of ICL. We experimentally prove the wide applicability of DETAIL by showing our attribution scores obtained on white-box models are transferable to black-box models in improving model performance.
  arXiv  Detail & Related papers  (2024-05-22T15:52:52Z)
• Evaluating Concurrent Robustness of Language Models Across Diverse Challenge Sets [46.19529338280716]
  Language models, characterized by their black-box nature, often hallucinate and display sensitivity to input perturbations. We introduce a methodology designed to examine how input perturbations affect language models across various scales. We present three distinct fine-tuning strategies to address robustness against multiple perturbations.
  arXiv  Detail & Related papers  (2023-11-15T02:59:10Z)
• Expedited Training of Visual Conditioned Language Generation via Redundancy Reduction [61.16125290912494]
  $textEVL_textGen$ is a framework designed for the pre-training of visually conditioned language generation models. We show that our approach accelerates the training of vision-language models by a factor of 5 without a noticeable impact on overall performance.
  arXiv  Detail & Related papers  (2023-10-05T03:40:06Z)
• UniDiff: Advancing Vision-Language Models with Generative and Discriminative Learning [86.91893533388628]
  This paper presents UniDiff, a unified multi-modal model that integrates image-text contrastive learning (ITC), text-conditioned image synthesis learning (IS), and reciprocal semantic consistency modeling (RSC) UniDiff demonstrates versatility in both multi-modal understanding and generative tasks.
  arXiv  Detail & Related papers  (2023-06-01T15:39:38Z)
• Beyond Contrastive Learning: A Variational Generative Model for Multilingual Retrieval [109.62363167257664]
  We propose a generative model for learning multilingual text embeddings. Our model operates on parallel data in $N$ languages. We evaluate this method on a suite of tasks including semantic similarity, bitext mining, and cross-lingual question retrieval.
  arXiv  Detail & Related papers  (2022-12-21T02:41:40Z)
• Multi-Scales Data Augmentation Approach In Natural Language Inference For Artifacts Mitigation And Pre-Trained Model Optimization [0.0]
  We provide a variety of techniques for analyzing and locating dataset artifacts inside the crowdsourced Stanford Natural Language Inference corpus. To mitigate dataset artifacts, we employ a unique multi-scale data augmentation technique with two distinct frameworks. Our combination method enhances our model's resistance to perturbation testing, enabling it to continuously outperform the pre-trained baseline.
  arXiv  Detail & Related papers  (2022-12-16T23:37:44Z)

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.