When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data

• URL: http://arxiv.org/abs/2102.02201v1
• Date: Wed, 3 Feb 2021 18:57:08 GMT
• Title: When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data
• Authors: Peter Hase, Mohit Bansal
• Abstract summary: We study the circumstances under which explanations of individual data points can improve modeling performance. We make use of three existing datasets with explanations: e-SNLI, TACRED, SemEval.
• Score: 84.87772675171412
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many methods now exist for conditioning model outputs on task instructions, retrieved documents, and user-provided explanations and feedback. Rather than relying solely on examples of task inputs and outputs, these approaches allow for valuable additional data to be used in modeling with the purpose of improving model correctness and aligning learned models with human priors. Meanwhile, a growing body of evidence suggests that some language models can (1) store a large amount of knowledge in their parameters, and (2) perform inference over tasks in unstructured text to solve new tasks at test time. These results raise the possibility that, for some tasks, humans cannot explain to a model any more about the task than it already knows or could infer on its own. In this paper, we study the circumstances under which explanations of individual data points can (or cannot) improve modeling performance. In order to carefully control important properties of the data and explanations, we introduce a synthetic dataset for experiments, and we also make use of three existing datasets with explanations: e-SNLI, TACRED, SemEval. We first give a formal framework for the available modeling approaches, in which explanation data can be used as model inputs, as labels, or as a prior. After arguing that the most promising role for explanation data is as model inputs, we propose to use a retrieval-based method and show that it solves our synthetic task with accuracies upwards of 95%, while baselines without explanation data achieve below 65% accuracy. We then identify properties of datasets for which retrieval-based modeling fails. With the three existing datasets, we find no improvements from explanation retrieval. Drawing on our findings from our synthetic task, we suggest that at least one of six preconditions for successful modeling fails to hold with these datasets.

Related papers

• Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration [90.41908331897639]
  Large language models (LLMs) have significantly benefited from training on diverse, high-quality task-specific data. We present a novel approach, ReverseGen, designed to automatically generate effective training samples.
  arXiv  Detail & Related papers  (2024-10-22T06:43:28Z)
• Learning-based Models for Vulnerability Detection: An Extensive Study [3.1317409221921144]
  We extensively and comprehensively investigate two types of state-of-the-art learning-based approaches. We experimentally demonstrate the priority of sequence-based models and the limited abilities of both graph-based models.
  arXiv  Detail & Related papers  (2024-08-14T13:01:30Z)
• Numerical Literals in Link Prediction: A Critical Examination of Models and Datasets [2.5999037208435705]
  Link Prediction models that incorporate numerical literals have shown minor improvements on existing benchmark datasets. It is unclear whether a model is actually better in using numerical literals, or better capable of utilizing the graph structure. We propose a methodology to evaluate LP models that incorporate numerical literals.
  arXiv  Detail & Related papers  (2024-07-25T17:55:33Z)
• Zero-shot Retrieval: Augmenting Pre-trained Models with Search Engines [83.65380507372483]
  Large pre-trained models can dramatically reduce the amount of task-specific data required to solve a problem, but they often fail to capture domain-specific nuances out of the box. This paper shows how to leverage recent advances in NLP and multi-modal learning to augment a pre-trained model with search engine retrieval.
  arXiv  Detail & Related papers  (2023-11-29T05:33:28Z)
• CHORUS: Foundation Models for Unified Data Discovery and Exploration [6.85448651843431]
  We show that foundation models are highly applicable to the data discovery and data exploration domain. We show that a foundation-model-based approach outperforms the task-specific models and so the state of the art. This suggests a future direction in which disparate data management tasks can be unified under foundation models.
  arXiv  Detail & Related papers  (2023-06-16T03:58:42Z)
• AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators [98.11286353828525]
  GPT-3.5 series models have demonstrated remarkable few-shot and zero-shot ability across various NLP tasks. We propose AnnoLLM, which adopts a two-step approach, explain-then-annotate. We build the first conversation-based information retrieval dataset employing AnnoLLM.
  arXiv  Detail & Related papers  (2023-03-29T17:03:21Z)
• Synthetic Model Combination: An Instance-wise Approach to Unsupervised Ensemble Learning [92.89846887298852]
  Consider making a prediction over new test data without any opportunity to learn from a training set of labelled data. Give access to a set of expert models and their predictions alongside some limited information about the dataset used to train them.
  arXiv  Detail & Related papers  (2022-10-11T10:20:31Z)
• Representing Knowledge by Spans: A Knowledge-Enhanced Model for Information Extraction [7.077412533545456]
  We propose a new pre-trained model that learns representations of both entities and relationships simultaneously. By encoding spans efficiently with span modules, our model can represent both entities and their relationships but requires fewer parameters than existing models.
  arXiv  Detail & Related papers  (2022-08-20T07:32:25Z)
• Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills [32.55545292360155]
  We propose to leverage semi-structured tables, and automatically generate at scale question-paragraph pairs. We add a pre-training step over this synthetic data, which includes examples that require 16 different reasoning skills. We show that our model, PReasM, substantially outperforms T5, a popular pre-trained encoder-decoder model.
  arXiv  Detail & Related papers  (2021-07-15T11:37:14Z)
• Model-agnostic multi-objective approach for the evolutionary discovery of mathematical models [55.41644538483948]
  In modern data science, it is more interesting to understand the properties of the model, which parts could be replaced to obtain better results. We use multi-objective evolutionary optimization for composite data-driven model learning to obtain the algorithm's desired properties.
  arXiv  Detail & Related papers  (2021-07-07T11:17:09Z)

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.