Challenge: Existing methods for analyzing and training NLP models have not been integrated to combine their complementary advantages.
Approach: They introduce a framework for selective rationalization and counterfactual text generation that leverages CREST to regularize selective rationales and a loss function that regularizes selective rationals.
Outcome: The proposed framework generates valid counterfactuals that are more natural than those produced by previous methods and can be used for data augmentation at scale.

Similar Papers

Measuring Association Between Labels and Free-Text Rationales (2021.emnlp-main)

Copied to clipboard

Challenge: Existing models for extractive rationales do not work as well on reasoning tasks requiring free-text rationale.
Approach: They propose to use pipelines to extract rationales from input words and to use them to explain reasoning tasks.
Outcome: The proposed models exhibit desirable properties for explaining commonsense question-answering and natural language inference, indicating their potential for producing faithful free-text rationales.
EXPLAIN, EDIT, GENERATE: Rationale-Sensitive Counterfactual Data Augmentation for Multi-hop Fact Verification (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods to augment training data with counterfactuals fail to handle multi-hop fact verification due to their incapability to preserve complex logical relationships.
Approach: They propose to augment training data with counterfactuals that alter causal features of the original data by preserving logical relationships.
Outcome: The proposed method outperforms the baselines and can generate linguistically diverse counterfactuals without disrupting their logical relationships.
Counterfactuals of Counterfactuals: a back-translation-inspired approach to analyse counterfactual editors (2023.findings-acl)

Copied to clipboard

Challenge: Existing explanations for classifiers are counterfactual or contrastive . lack of universal ground truth for counterf actual edits hinders their evaluation .
Approach: They propose a back translation-inspired evaluation methodology that utilises earlier outputs of the explainer as ground truth proxies to investigate the consistency of explainers.
Outcome: The proposed method can provide valuable insights into the behaviour of predictor and explainer models and infer patterns that would otherwise be obscured.
Can Rationalization Improve Robustness? (2022.naacl-main)

Copied to clipboard

Challenge: Existing models that generate rationales before making predictions can ignore noise or adversarially added text by simply masking it out of the generated rationale.
Approach: They propose to use a 'rationalizethen-predict' framework to generate subsets of input to generate rationales and then make predictions using them.
Outcome: The proposed models improve robustness over AddText attacks while struggling in certain scenarios.
NeuroCounterfactuals: Beyond Minimal-Edit Counterfactuals for Richer Data Augmentation (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to produce counterfactuals rely on small perturbations via minimal edits, resulting in simplistic changes.
Approach: They propose a novel approach to produce counterfactuals that allow for larger edits and linguistic diversity while still bearing similarity to the original document.
Outcome: The proposed approach outperforms existing methods for generalizing natural language models under select settings.
SPECTRA: Sparse Structured Text Rationalization (2021.emnlp-main)

Copied to clipboard

Challenge: Sparse attention mechanisms are a deterministic alternative, but they lack a way to regularize rationale extraction.
Approach: They propose a framework for deterministic extraction of structured explanations via constrained inference on a factor graph, forming a differentiable layer.
Outcome: The proposed framework outperforms previous studies on performance and plausibility of extracted rationales.
Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationales (2024.findings-naacl)

Copied to clipboard

Challenge: Saliency post-hoc explainability methods are important tools for understanding complex NLP models, but they may not align with human intuition, making the explanations not plausible.
Approach: They propose a method for incorporating rationales into text classification models by augmenting the standard cross-entropy loss with a novel loss function inspired by contrastive learning.
Outcome: The proposed approach enhances the plausibility of post-hoc explanations while preserving their faithfulness.
A Survey on Natural Language Counterfactual Generation (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in NLP are driven by a variety of Large Language Models (LLMs), such as GPT-3 (175B) and PaLM (540B).
Approach: They propose a taxonomy that categorizes the methods into four groups and summarizes the metrics for evaluating the generation quality.
Outcome: The proposed taxonomy categorizes the generation methods into four groups and summarizes the metrics for evaluating the quality.
Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models (2021.acl-long)

Copied to clipboard

Challenge: Existing counterfactual generation methods rely on manual labor to create very few counterf actuals or only instantiate limited types of perturbations such as paraphrases or word substitutions.
Approach: They propose a general-purpose counterfactual generator that allows for control over perturbation types and locations.
Outcome: The proposed generator produces diverse sets of realistic counterfactuals that are useful in various applications.
Self-Training Meets Consistency: Improving LLMs’ Reasoning with Consistency-Driven Rationale Evaluation (2025.naacl-long)

Copied to clipboard

Challenge: Existing approaches labeled rationales that produce correct answers as appropriate for training but one measure risks misjudging rationale quality, leading models to learn flawed reasoning patterns.
Approach: They propose a framework that evaluates rationales through follow-up questions and leverages this evaluation to guide its training.
Outcome: The proposed framework improves robustness and correctness of rationales and reasoning abilities compared to previous self-training approaches.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations