paper-with-me

Papers

A Practical Method for Generating String Counterfactuals

2024-02-17 · Matan Avitan, Ryan Cotterell, Yoav Goldberg, Shauli Ravfogel

Interventions targeting the representation space of language models (LMs) have emerged as an effective means to influence model behavior. Such methods are employed, for example, to eliminate or alter the encoding of demographic information such as gender within the model's representations and, in so doing, create a counterfactual representation. However, because the intervention operates within the representation space, understanding precisely what aspects of the text it modifies poses a challenge. In this paper, we give a method to convert representation counterfactuals into string counterfactuals. We demonstrate that this approach enables us to analyze the linguistic alterations corresponding to a given representation space intervention and to interpret the features utilized to encode a specific concept. Moreover, the resulting counterfactuals can be used to mitigate bias in classification through data augmentation.

📄 PDF Abstract BibTeX arXiv:2402.11355

Code (1)

MatanAvitan/rep-to-string-counterfactuals 공식 구현 pytorch

Tasks

counterfactualData Augmentation

Methods 이 논문이 사용한 방법론

Counterfactuals 설명 없음

Similar Papers 제목 키워드 기반

Gumbel Counterfactual Generation From Language Models

2024-11-11 · Shauli Ravfogel, Anej Svete, Vésteinn Snæbjarnarson, Ryan Cotterell

Understanding and manipulating the causal generation mechanisms in language models is essential for controlling their behavior. Previous work has primarily relied on techniques such as representation surgery -- e.g., mod…

counterfactualCounterfactual ReasoningSentence

CoLa-DCE -- Concept-guided Latent Diffusion Counterfactual Explanations

2024-06-03 · Franz Motzkus, Christian Hellert, Ute Schmid

Recent advancements in generative AI have introduced novel prospects and practical implementations. Especially diffusion models show their strength in generating diverse and, at the same time, realistic features, positio…

CoLAcounterfactualimage-classificationImage Classification

Evaluating and Mitigating Bias in Image Classifiers: A Causal Perspective Using Counterfactuals

2020-09-17 · Saloni Dash, Vineeth N Balasubramanian, Amit Sharma

Counterfactual examples for an input -- perturbations that change specific features but not others -- have been shown to be useful for evaluating bias of machine learning models, e.g., against specific demographic groups…

BIG-bench Machine LearningcounterfactualFairnessvalid

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

Good Counterfactuals and Where to Find Them: A Case-Based Technique for Generating Counterfactuals for Explainable AI (XAI)

2020-05-26 · Mark T. Keane, Barry Smyth

Recently, a groundswell of research has identified the use of counterfactual explanations as a potentially significant solution to the Explainable AI (XAI) problem. It is argued that (a) technically, these counterfactual…

counterfactualExplainable Artificial Intelligence (XAI)