English
Related papers

Related papers: Omitted Variable Bias in Language Models Under Dis…

200 papers

We develop a framework for quantifying omitted variable bias (OVB) in nonlinear instrumental variable (IV) estimators, including the local average treatment effect (LATE), the LATE for the treated (LATT), and the partially linear IV model…

Econometrics · Economics 2026-04-07 Yu-Min Yen

Out-of-distribution (OOD) detection aims to identify test examples that do not belong to the training distribution and are thus unlikely to be predicted reliably. Despite a plethora of existing works, most of them focused only on the…

Machine Learning · Computer Science 2023-11-07 Reza Averly , Wei-Lun Chao

Randomized controlled trials (RCTs) yield internally valid causal effect estimates, but generalizing these results to target populations with different characteristics requires an untestable selection ignorability assumption: conditional on…

Methodology · Statistics 2026-03-31 Amir Asiaee , Samhita Pal , Jared D. Huling

The releases of powerful open-weight large language models (LLMs) are often not accompanied by access to their full training data. Existing interpretability methods, particularly those based on activations, often require or assume…

Machine Learning · Computer Science 2026-04-22 Ziqian Zhong , Aditi Raghunathan

Despite machine learning models' success in Natural Language Processing (NLP) tasks, predictions from these models frequently fail on out-of-distribution (OOD) samples. Prior works have focused on developing state-of-the-art methods for…

Computation and Language · Computer Science 2021-11-30 Dyah Adila , Dongyeop Kang

Training models that perform well under distribution shifts is a central challenge in machine learning. In this paper, we introduce a modeling framework where, in addition to training data, we have partial structural knowledge of the…

Machine Learning · Computer Science 2021-10-28 Tobias Sutter , Andreas Krause , Daniel Kuhn

Improving the reliability of deployed machine learning systems often involves developing methods to detect out-of-distribution (OOD) inputs. However, existing research often narrowly focuses on samples from classes that are absent from the…

Machine Learning · Computer Science 2024-12-11 Charles Guille-Escuret , Pierre-André Noël , Ioannis Mitliagkas , David Vazquez , Joao Monteiro

Out-of-distribution (OOD) learning often relies heavily on statistical approaches or predefined assumptions about OOD data distributions, hindering their efficacy in addressing multifaceted challenges of OOD generalization and OOD detection…

Machine Learning · Computer Science 2024-08-16 Haoyue Bai , Xuefeng Du , Katie Rainey , Shibin Parameswaran , Yixuan Li

Despite agreement on the importance of detecting out-of-distribution (OOD) examples, there is little consensus on the formal definition of OOD examples and how to best detect them. We categorize these examples by whether they exhibit a…

Computation and Language · Computer Science 2021-12-16 Udit Arora , William Huang , He He

In a physical system, changing parameters such as temperature can induce a phase transition: an abrupt change from one state of matter to another. Analogous phenomena have recently been observed in large language models. Typically, the task…

Machine Learning · Computer Science 2024-05-28 Julian Arnold , Flemming Holtorf , Frank Schäfer , Niels Lörch

While pretrained language models have exhibited impressive generalization capabilities, they still behave unpredictably under certain domain shifts. In particular, a model may learn a reasoning process on in-domain training data that does…

Computation and Language · Computer Science 2022-10-14 Prasann Singhal , Jarad Forristal , Xi Ye , Greg Durrett

Most machine learning models operate under the assumption that the training, testing and deployment data is independent and identically distributed (i.i.d.). This assumption doesn't generally hold true in a natural setting. Usually, the…

Machine Learning · Computer Science 2021-12-14 Kumud Lakara , Akshat Bhandari , Pratinav Seth , Ujjwal Verma

Deep learning models often rely only on a small set of features even when there is a rich set of predictive signals in the training data. This makes models brittle and sensitive to distribution shifts. In this work, we first examine vision…

Computer Vision and Pattern Recognition · Computer Science 2023-09-01 Armand Mihai Nicolicioiu , Andrei Liviu Nicolicioiu , Bogdan Alexe , Damien Teney

Attribute labeling at large scale is typically incomplete and partial, posing significant challenges to model optimization. Existing attribute learning methods often treat the missing labels as negative or simply ignore them all during…

Computer Vision and Pattern Recognition · Computer Science 2023-12-18 Kongming Liang , Xinran Wang , Rui Wang , Donghui Gao , Ling Jin , Weidong Liu , Xiatian Zhu , Zhanyu Ma , Jun Guo

In this paper, we consider the contextual robust optimization problem under an out-of-distribution setting. The contextual robust optimization problem considers a risk-sensitive objective function for an optimization problem with the…

Optimization and Control · Mathematics 2025-06-06 Zhongze Cai , Hansheng Jiang , Xiaocheng Li

A distribution shift can have fundamental consequences such as signaling a change in the operating environment or significantly reducing the accuracy of downstream models. Thus, understanding distribution shifts is critical for examining…

Machine Learning · Computer Science 2023-06-21 Sean Kulinski , David I. Inouye

Preference alignment methods are increasingly critical for steering large language models (LLMs) to generate outputs consistent with human values. While recent approaches often rely on synthetic data generated by LLMs for scalability and…

Computation and Language · Computer Science 2025-10-21 Mingye Zhu , Yi Liu , Zheren Fu , Yongdong Zhang , Zhendong Mao

Distribution shift occurs when the test distribution differs from the training distribution, and it can considerably degrade performance of machine learning models deployed in the real world. Temporal shifts -- distribution shifts arising…

Machine Learning · Computer Science 2023-01-18 Huaxiu Yao , Caroline Choi , Bochuan Cao , Yoonho Lee , Pang Wei Koh , Chelsea Finn

Generative classifiers offer potential advantages over their discriminative counterparts, namely in the areas of data efficiency, robustness to data shift and adversarial examples, and zero-shot learning (Ng and Jordan,2002; Yogatama et…

Computation and Language · Computer Science 2019-10-02 Xiaoan Ding , Kevin Gimpel

Although prior work on bias mitigation has focused on promoting social equality and demographic parity, less attention has been given to aligning LLM's outputs to desired distributions. For example, we might want to align a model with…

Computation and Language · Computer Science 2025-10-09 Ingroj Shrestha , Padmini Srinivasan