Attention is not not Explanation
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 reserved pith:53SET5XXrecord.jsonopen to challenge →
read the original abstract
Attention mechanisms play a central role in NLP systems, especially within recurrent neural network (RNN) models. Recently, there has been increasing interest in whether or not the intermediate representations offered by these modules may be used to explain the reasoning for a model's prediction, and consequently reach insights regarding the model's decision-making process. A recent paper claims that `Attention is not Explanation' (Jain and Wallace, 2019). We challenge many of the assumptions underlying this work, arguing that such a claim depends on one's definition of explanation, and that testing it needs to take into account all elements of the model, using a rigorous experimental design. We propose four alternative tests to determine when/whether attention can be used as explanation: a simple uniform-weights baseline; a variance calibration based on multiple random seed runs; a diagnostic framework using frozen weights from pretrained models; and an end-to-end adversarial attention training protocol. Each allows for meaningful interpretation of attention mechanisms in RNN models. We show that even when reliable adversarial distributions can be found, they don't perform well on the simple diagnostic, indicating that prior work does not disprove the usefulness of attention mechanisms for explainability.
This paper has not been read by Pith yet.
Forward citations
Cited by 10 Pith papers
-
Attention Is Not All You Need for Diffraction
Physics-informed transformer with sin^2(theta) encoding, physics-aware positional encoding, multi-task decoder, and three-stage curriculum classifies powder diffraction into 99 extinction groups, with structured error...
-
Contribution Weights: A Geometrical Analysis of Self-Attention Transformers
Contribution Weights combine attention, value magnitude, and directional alignment to measure token influence more faithfully than attention alone, and show attention sinks actively suppress information via a convex s...
-
Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
-
Large Vision-Language Models Get Lost in Attention
In LVLMs, attention can be replaced by random Gaussian weights with little or no performance loss, indicating that current models get lost in attention rather than efficiently using visual context.
-
Large Language Models Decide Early and Explain Later
LLMs settle on their answer after a minority of CoT tokens and produce an average 760 more as post-decision explanation, enabling early stopping that saves 500 tokens per query at a 2% accuracy cost.
-
Explainable AI: Context-Aware Layer-Wise Integrated Gradients for Explaining Transformer Models
CA-LIG is a unified hierarchical attribution method that computes layer-wise Integrated Gradients fused with class-specific attention gradients to generate signed, context-sensitive explanations for transformer models.
-
AttnTrace: Contextual Attribution of Prompt Injection and Knowledge Corruption
AttnTrace is an attention-weight-based context traceback method for LLMs that claims higher accuracy and efficiency than prior art like TracLLM while aiding prompt injection detection.
-
ChessMimic: Per-Rating Transformer Models for Human Move, Clock, and Outcome Prediction in Online Blitz Chess
Per-100-Elo-band transformers outperform Maia-2 in move prediction accuracy across all bands and reach 0.78 AUC on outcome prediction using held-out Lichess data.
-
Uncertainty-Aware Transformers: Conformal Prediction for Language Models
CONFIDE applies conformal prediction to transformer embeddings for valid prediction sets, improving accuracy up to 4.09% and efficiency over baselines on models like BERT-tiny.
-
Exploring Radiologists' Expectations of Explainable Machine Learning Models in Medical Image Analysis
Radiologists provided input on explainable ML needs and beneficial clinical tasks, resulting in guidelines for developing clinically aligned models in radiology.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.