paper-with-me

Papers

Selection Collider Bias in Large Language Models

2022-08-22 · Emily McMilin

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. We show that selection collider bias can become amplified in underspecified learning tasks, and although difficult to overcome, we describe a method to exploit the resulting spurious correlations for determination of when a model may be uncertain about its prediction. We demonstrate an uncertainty metric that matches human uncertainty in tasks with gender pronoun underspecification on an extended version of the Winogender Schemas evaluation set, and we provide an online demo where users can apply our uncertainty metric to their own texts and models.

📄 PDF Abstract BibTeX arXiv:2208.10063

Code (1)

2dot71mily/selection_collider_bias_uai_clr_2022 공식 구현

Similar Papers 제목 키워드 기반

Latent Adversarial Debiasing: Mitigating Collider Bias in Deep Neural Networks

2020-11-19 · Luke Darlow, Stanisław Jastrzębski, Amos Storkey

Collider bias is a harmful form of sample selection bias that neural networks are ill-equipped to handle. This bias manifests itself when the underlying causal signal is strongly correlated with other confounding signals…

Selection bias

Assessing Classifier Fairness with Collider Bias

2020-10-08 · Zhenlong Xu, Jixue Liu, Debo Cheng, Jiuyong Li 외

The increasing application of machine learning techniques in everyday decision-making processes has brought concerns about the fairness of algorithmic decision-making. This paper concerns the problem of collider bias whi…

Decision MakingFairness

Representation Disentaglement via Regularization by Causal Identification

2023-02-28 · Juan Castorena

In this work, we propose the use of a causal collider structured model to describe the underlying data generative process assumptions in disentangled representation learning. This extends the conventional i.i.d. factoriz…

Causal IdentificationCausal InferenceDisentanglementRepresentation Learning+1

The role of collider bias in understanding statistics on racially biased policing

2020-07-16 · Norman Fenton, Martin Neil, Steven Frazier

Contradictory conclusions have been made about whether unarmed blacks are more likely to be shot by police than unarmed whites using the same data. The problem is that, by relying only on data of 'police encounters', the…

Do LLMs Share Human-Like Biases? Causal Reasoning Under Prior Knowledge, Irrelevant Context, and Varying Compute Budgets

2026-02-03 · Hanna M. Dettki, Charley M. Wu, Bob Rehder arxiv

Large language models (LLMs) are increasingly used in domains where causal reasoning matters, yet it remains unclear whether their judgments reflect normative causal computation, human-like shortcuts, or brittle pattern …