Shaking the foundations: delusions in sequence models for interaction and control

by   Pedro A. Ortega, et al.

The recent phenomenal success of language models has reinvigorated machine learning research, and large sequence models such as transformers are being applied to a variety of domains. One important problem class that has remained relatively elusive however is purposeful adaptive behavior. Currently there is a common perception that sequence models "lack the understanding of the cause and effect of their actions" leading them to draw incorrect inferences due to auto-suggestive delusions. In this report we explain where this mismatch originates, and show that it can be resolved by treating actions as causal interventions. Finally, we show that in supervised learning, one can teach a system to condition or intervene on data by training with factual and counterfactual error signals respectively.


page 1

page 2

page 3

page 4


Counterfactual Instances Explain Little

In many applications, it is important to be able to explain the decision...

Counterfactual Temporal Point Processes

Machine learning models based on temporal point processes are the state ...

Causal Decision Making and Causal Effect Estimation Are Not the Same... and Why It Matters

Causal decision making (CDM) at scale has become a routine part of busin...

Conformer LLMs – Convolution Augmented Large Language Models

This work builds together two popular blocks of neural architecture, nam...

What if This Modified That? Syntactic Interventions via Counterfactual Embeddings

Neural language models exhibit impressive performance on a variety of ta...

The sequence matters: A systematic literature review of using sequence analysis in Learning Analytics

Describing and analysing sequences of learner actions is becoming more p...

Learning to Sketch with Deep Q Networks and Demonstrated Strokes

Doodling is a useful and common intelligent skill that people can learn ...

Please sign up or login with your details

Forgot password? Click here to reset