Search Results for author:
Found 3 papers, 2 papers with code
Underspecification in Language Modeling Tasks: A Causality-Informed Study of Gendered Pronoun Resolution
Modern language modeling tasks are often underspecified: for a given token prediction, many words may satisfy the user's intent of producing natural language at inference time, however only one word will minimize the task's loss function at training time.
Selection Collider Bias in Large Language Models
In this paper we motivate the causal mechanisms behind sample selection induced collider bias (selection collider bias) that can cause Large Language Models (LLMs) to learn unconditional dependence between entities that are unconditionally independent in the real world.
Selection Bias Induced Spurious Correlations in Large Language Models
In this work we show how large language models (LLMs) can learn statistical dependencies between otherwise unconditionally independent variables due to dataset selection bias.
