paper-with-me

홈 › Papers

Counterfactuals of Counterfactuals: a back-translation-inspired approach to analyse counterfactual editors

2023-05-26 · Giorgos Filandrianos, Edmund Dervakos, Orfeas Menis-Mastromichalakis, Chrysoula Zerva, Giorgos Stamou

In the wake of responsible AI, interpretability methods, which attempt to provide an explanation for the predictions of neural models have seen rapid progress. In this work, we are concerned with explanations that are applicable to natural language processing (NLP) models and tasks, and we focus specifically on the analysis of counterfactual, contrastive explanations. We note that while there have been several explainers proposed to produce counterfactual explanations, their behaviour can vary significantly and the lack of a universal ground truth for the counterfactual edits imposes an insuperable barrier on their evaluation. We propose a new back translation-inspired evaluation methodology that utilises earlier outputs of the explainer as ground truth proxies to investigate the consistency of explainers. We show that by iteratively feeding the counterfactual to the explainer we can obtain valuable insights into the behaviour of both the predictor and the explainer models, and infer patterns that would be otherwise obscured. Using this methodology, we conduct a thorough analysis and propose a novel metric to evaluate the consistency of counterfactual generation approaches with different characteristics across available performance indicators.

📄 PDF Abstract BibTeX arXiv:2305.17055

Code (1)

geofila/counterfactuals-of-counterfactuals 공식 구현

Tasks

counterfactual

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation

2026-01-01 · Qianli Wang, Van Bach Nguyen, Yihong Liu, Fedor Splitt 외 arxiv

Counterfactuals refer to minimally edited inputs that cause a model's prediction to change, serving as a promising approach to explaining the model's behavior. Large language models (LLMs) excel at generating English cou…

Data Augmentation

NeuroCounterfactuals: Beyond Minimal-Edit Counterfactuals for Richer Data Augmentation

2022-10-22 · Phillip Howard, Gadi Singer, Vasudev Lal, Yejin Choi 외

While counterfactual data augmentation offers a promising step towards robust generalization in natural language processing, producing a set of counterfactuals that offer valuable inductive bias for models remains a chal…

counterfactualData AugmentationDiversityInductive Bias+4

Deep Backtracking Counterfactuals for Causally Compliant Explanations

2023-10-11 · Klaus-Rudolf Kladny, Julius von Kügelgen, Bernhard Schölkopf, Michael Muehlebach

Counterfactuals answer questions of what would have been observed under altered circumstances and can therefore offer valuable insights. Whereas the classical interventional interpretation of counterfactuals has been stu…

counterfactualPhilosophy

Natural Counterfactuals With Necessary Backtracking

2024-02-02 · Guang-Yuan Hao, Jiji Zhang, Biwei Huang, Hao Wang 외

Counterfactual reasoning is pivotal in human cognition and especially important for providing explanations and making decisions. While Judea Pearl's influential approach is theoretically elegant, its generation of a coun…

counterfactualCounterfactual Reasoning

Interactive Analysis of LLMs using Meaningful Counterfactuals

2024-04-23 · Furui Cheng, Vilém Zouhar, Robin Shing Moon Chan, Daniel Fürst 외

Counterfactual examples are useful for exploring the decision boundaries of machine learning models and determining feature attributions. How can we apply counterfactual-based methods to analyze and explain LLMs? We iden…

counterfactual