What to Learn, and How: Toward Effective Learning from Rationales
- URL: http://arxiv.org/abs/2112.00071v1
- Date: Tue, 30 Nov 2021 20:09:53 GMT
- Title: What to Learn, and How: Toward Effective Learning from Rationales
- Authors: Samuel Carton, Surya Kanoria and Chenhao Tan
- Abstract summary: Learning from rationales seeks to augment model training with human-provided rationales that justify those labels.
Our work highlights the importance of understanding properties of human explanations and exploiting them accordingly in model training.
- Score: 10.287185780246247
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Learning from rationales seeks to augment model training with human-provided
rationales (i.e., a subset of input tokens) that justify those labels. While
intuitive, this idea has proven elusive in practice. We make two observations
about human rationales via empirical analyses: 1) maximizing predicted
rationale accuracy is not necessarily the optimal objective for improving model
performance; 2) human rationales vary in whether they provide sufficient
information for the model to exploit for prediction, and we can use this
variance to assess a dataset's potential improvement from learning from
rationales. Building on these insights, we propose loss functions and learning
strategies, and evaluate their effectiveness on three datasets with human
rationales. Our results demonstrate consistent improvements over baselines in
both label performance and rationale performance, including a 3% accuracy
improvement on MultiRC. Our work highlights the importance of understanding
properties of human explanations and exploiting them accordingly in model
training.
Related papers
- What Do Learning Dynamics Reveal About Generalization in LLM Reasoning? [83.83230167222852]
We find that a model's generalization behavior can be effectively characterized by a training metric we call pre-memorization train accuracy.
By connecting a model's learning behavior to its generalization, pre-memorization train accuracy can guide targeted improvements to training strategies.
arXiv Detail & Related papers (2024-11-12T09:52:40Z) - Beyond Accuracy: Ensuring Correct Predictions With Correct Rationales [10.397502254316645]
We propose a two-phase scheme to ensure double-correct predictions.
First, we curate a new dataset that offers structured rationales for visual recognition tasks.
Second, we propose a rationale-informed optimization method to guide the model in disentangling and localizing visual evidence.
arXiv Detail & Related papers (2024-10-31T18:33:39Z) - Evaluating Human Alignment and Model Faithfulness of LLM Rationale [66.75309523854476]
We study how well large language models (LLMs) explain their generations through rationales.
We show that prompting-based methods are less "faithful" than attribution-based explanations.
arXiv Detail & Related papers (2024-06-28T20:06:30Z) - Improving Language Model Reasoning with Self-motivated Learning [60.779625789039486]
textitSelf-motivated Learning framework motivates the model itself to automatically generate rationales on existing datasets.
We train a reward model with the rank to evaluate the quality of rationales, and improve the performance of reasoning through reinforcement learning.
arXiv Detail & Related papers (2024-04-10T14:05:44Z) - Understanding the Learning Dynamics of Alignment with Human Feedback [17.420727709895736]
This paper provides an attempt to theoretically analyze the learning dynamics of human preference alignment.
We show how the distribution of preference datasets influences the rate of model updates and provide rigorous guarantees on the training accuracy.
arXiv Detail & Related papers (2024-03-27T16:39:28Z) - REFER: An End-to-end Rationale Extraction Framework for Explanation
Regularization [12.409398096527829]
We propose REFER, a framework that employs a differentiable rationale extractor that allows to back-propagate through the rationale extraction process.
We analyze the impact of using human highlights during training by jointly training the task model and the rationale extractor.
arXiv Detail & Related papers (2023-10-22T21:20:52Z) - Robust Learning with Progressive Data Expansion Against Spurious
Correlation [65.83104529677234]
We study the learning process of a two-layer nonlinear convolutional neural network in the presence of spurious features.
Our analysis suggests that imbalanced data groups and easily learnable spurious features can lead to the dominance of spurious features during the learning process.
We propose a new training algorithm called PDE that efficiently enhances the model's robustness for a better worst-group performance.
arXiv Detail & Related papers (2023-06-08T05:44:06Z) - Does Self-Rationalization Improve Robustness to Spurious Correlations? [19.553357015260687]
We ask whether training models to self-rationalize can aid in their learning to solve tasks for the right reasons.
We evaluate robustness to spurious correlations in fine-tuned encoder-decoder and decoder-only models of six different sizes.
We find that while self-rationalization can improve robustness to spurious correlations in low-resource settings, it tends to hurt robustness in higher-resource settings.
arXiv Detail & Related papers (2022-10-24T19:54:57Z) - Double Robust Representation Learning for Counterfactual Prediction [68.78210173955001]
We propose a novel scalable method to learn double-robust representations for counterfactual predictions.
We make robust and efficient counterfactual predictions for both individual and average treatment effects.
The algorithm shows competitive performance with the state-of-the-art on real world and synthetic data.
arXiv Detail & Related papers (2020-10-15T16:39:26Z) - Value-driven Hindsight Modelling [68.658900923595]
Value estimation is a critical component of the reinforcement learning (RL) paradigm.
Model learning can make use of the rich transition structure present in sequences of observations, but this approach is usually not sensitive to the reward function.
We develop an approach for representation learning in RL that sits in between these two extremes.
This provides tractable prediction targets that are directly relevant for a task, and can thus accelerate learning the value function.
arXiv Detail & Related papers (2020-02-19T18:10:20Z)
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.