paper-with-me

Papers

Causal Intersectionality and Dual Form of Gradient Descent for Multimodal Analysis: a Case Study on Hateful Memes

2023-08-19 · Yosuke Miyanishi, Minh Le Nguyen

Amidst the rapid expansion of Machine Learning (ML) and Large Language Models (LLMs), understanding the semantics within their mechanisms is vital. Causal analyses define semantics, while gradient-based methods are essential to eXplainable AI (XAI), interpreting the model's 'black box'. Integrating these, we investigate how a model's mechanisms reveal its causal effect on evidence-based decision-making. Research indicates intersectionality - the combined impact of an individual's demographics - can be framed as an Average Treatment Effect (ATE). This paper demonstrates that hateful meme detection can be viewed as an ATE estimation using intersectionality principles, and summarized gradient-based attention scores highlight distinct behaviors of three Transformer models. We further reveal that LLM Llama-2 can discern the intersectional aspects of the detection through in-context learning and that the learning process could be explained via meta-gradient, a secondary form of gradient. In conclusion, this work furthers the dialogue on Causality and XAI. Our code is available online (see External Resources section).

📄 PDF Abstract BibTeX arXiv:2308.11585

Code (1)

HireTheHero/CausalIntersectionalityDualGradient 공식 구현 pytorch

Tasks

Decision MakingFormIn-Context Learning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Causal intersectionality for fair ranking

2020-06-15 · Ke Yang, Joshua R. Loftus, Julia Stoyanovich

In this paper we propose a causal modeling approach to intersectional fairness, and a flexible, task-specific method for computing intersectionally fair rankings. Rankings are used in many contexts, ranging from Web sear…

Causal InferenceFairness

A Granger-Causal Perspective on Gradient Descent with Application to Pruning

2024-12-04 · Aditya Shah, Aditya Challa, Sravan Danda, Archana Mathur 외

Stochastic Gradient Descent (SGD) is the main approach to optimizing neural networks. Several generalization properties of deep networks, such as convergence to a flatter minima, are believed to arise from SGD. This arti…

See Me and Believe Me: Causality and Intersectionality in Testimonial Injustice in Healthcare

2024-10-02 · Kenya S. Andrews, Mesrob I. Ohannessian, Elena Zheleva

In medical settings, it is critical that all who are in need of care are correctly heard and understood. When this is not the case due to prejudices a listener has, the speaker is experiencing \emph{testimonial injustice…

Causal Discovery

Factoring the Matrix of Domination: A Critical Review and Reimagination of Intersectionality in AI Fairness

2023-03-16 · Anaelia Ovalle, Arjun Subramonian, Vagrant Gautam, Gilbert Gee 외

Intersectionality is a critical framework that, through inquiry and praxis, allows us to examine how social inequalities persist through domains of structure and discipline. Given AI fairness' raison d'etre of "fairness"…

Fairness

How Transformers Learn Causal Structure with Gradient Descent

2024-02-22 · Eshaan Nichani, Alex Damian, Jason D. Lee

The incredible success of transformers on sequence modeling tasks can be largely attributed to the self-attention mechanism, which allows information to be transferred between different parts of a sequence. Self-attentio…

In-Context Learning