Validity Threats for Foundation Model Research

• URL: http://arxiv.org/abs/2606.05029v1
• Date: Wed, 03 Jun 2026 15:57:42 GMT
• Title: Validity Threats for Foundation Model Research
• Abstract summary: Controlled experiments are the backbone of machine learning research.<n>However, at the scale of modern foundation models, they have become prohibitively expensive.<n>Instead, the community increasingly relies on research strategies that approximate the ideal experiment at a fraction of the cost.
• Score: 19.108459045725617
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Controlled experiments are the backbone of machine learning research, but at the scale of modern foundation models, they have become prohibitively expensive. Instead, the community increasingly relies on research strategies that approximate the ideal experiment at a fraction of the cost: proxy experiments and scaling laws, observational studies with publicly available models, and single-run designs that leverage variation within individual training runs. In this work, we argue that there is no free lunch when approximating large-scale experiments on a compute budget. Specifically, savings in compute come at the cost of validity threats -- hidden and sometimes untestable assumptions that, when violated, can invalidate research claims. To help navigate such threats, we propose an evaluation framework that casts foundation model research as a causal inference problem. Within this framework, we evaluate different research strategies through four types of validity adapted from the empirical social sciences -- statistical, internal, external, and construct validity. We find that each strategy comes with a characteristic validity profile: proxy experiments trade external and construct validity for statistical and internal validity; observational studies face confounding and effect heterogeneity; and single-run designs are strained by interference between treated units. This analysis reveals several validity threats that have received insufficient attention in the literature. Overall, our evaluation framework provides researchers with a practical toolkit for scrutinizing validity threats in foundation model research~designs.

Related papers

• Long-Horizon Autonomous Architecture Research with a Language-Model Agent: A Behavioural Case Study [0.3683202928838613]
  We study what happens when a single general-purpose large language model acts as the sole researcher on a long-horizon neural architecture design problem.<n>The study comprises three phases, separated by human-declared transitions, that progressively expand the agent's tool surface or problem scale.<n>We conclude that workflow design was at least as influential as agent capability in this study and propose diversified search, budgeted moonshot hypotheses, explicit forks, and regime-aware re-validation.
  arXiv  Detail & Related papers  (2026-08-03T09:56:34Z)
• Rethinking Software Empirical Studies with Structural Causal Models [12.18241004961061]
  Causal Inference offers a fundamental approach for advancing empirical software engineering (ESE) beyond traditional statistical association.<n>This paper introduces CausalSE, a framework that operationalizes Judea Pearl's causal inference paradigm in ESE context.
  arXiv  Detail & Related papers  (2026-05-27T13:41:05Z)
• Exploring the Garden of Forking Paths in Empirical Software Engineering Research: A Multiverse Analysis [3.6324565773746147]
  We conduct a so-called multiverse analysis on a published empirical SE paper.<n>We identify nine pivotal analytical decisions with at least one equally defensible alternative.<n>The overwhelming majority produced qualitatively different, and sometimes even opposite, findings.
  arXiv  Detail & Related papers  (2025-12-09T18:47:00Z)
• Data Fusion for Partial Identification of Causal Effects [62.56890808004615]
  We propose a novel partial identification framework that enables researchers to answer key questions.<n>Is the causal effect positive or negative? and How severe must assumption violations be to overturn this conclusion?<n>We apply our framework to the Project STAR study, which investigates the effect of classroom size on students' third-grade standardized test performance.
  arXiv  Detail & Related papers  (2025-05-30T07:13:01Z)
• Model-free Methods for Event History Analysis and Efficient Adjustment (PhD Thesis) [55.2480439325792]
  This thesis is a series of independent contributions to statistics unified by a model-free perspective.<n>The first chapter elaborates on how a model-free perspective can be used to formulate flexible methods that leverage prediction techniques from machine learning.<n>The second chapter studies the concept of local independence, which describes whether the evolution of one process is directly influenced by another.
  arXiv  Detail & Related papers  (2025-02-11T19:24:09Z)
• Prediction-Powered Causal Inferences [59.98498488132307]
  We focus on Prediction-Powered Causal Inferences (PPCI)<n>We first show that conditional calibration guarantees valid PPCI at population level.<n>We then introduce a sufficient representation constraint transferring validity across experiments.
  arXiv  Detail & Related papers  (2025-02-10T10:52:17Z)
• Addressing Key Challenges of Adversarial Attacks and Defenses in the Tabular Domain: A Methodological Framework for Coherence and Consistency [25.830427564563422]
  Class-Specific Anomaly Detection (CSAD) is an effective novel anomaly detection approach.<n> CSAD evaluates adversarial samples relative to their predicted class distribution, rather than a broad benign distribution.<n>Our evaluation incorporates both anomaly detection rates with SHAP-based assessments to provide a more comprehensive measure of adversarial sample quality.
  arXiv  Detail & Related papers  (2024-12-10T09:17:09Z)
• A Double Machine Learning Approach to Combining Experimental and Observational Data [58.05402364136958]
  We propose a double machine learning approach to combine experimental and observational studies.<n>Our framework proposes a falsification test for external validity and ignorability under milder assumptions.
  arXiv  Detail & Related papers  (2023-07-04T02:53:11Z)
• A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks [72.7373468905418]
  We develop an open-source toolkit OpenBackdoor to foster the implementations and evaluations of textual backdoor learning. We also propose CUBE, a simple yet strong clustering-based defense baseline.
  arXiv  Detail & Related papers  (2022-06-17T02:29:23Z)
• Empirical Estimates on Hand Manipulation are Recoverable: A Step Towards Individualized and Explainable Robotic Support in Everyday Activities [80.37857025201036]
  Key challenge for robotic systems is to figure out the behavior of another agent. Processing correct inferences is especially challenging when (confounding) factors are not controlled experimentally. We propose equipping robots with the necessary tools to conduct observational studies on people.
  arXiv  Detail & Related papers  (2022-01-27T22:15:56Z)
• Targeting Learning: Robust Statistics for Reproducible Research [1.1455937444848387]
  Targeted Learning is a subfield of statistics that unifies advances in causal inference, machine learning and statistical theory to help answer scientifically impactful questions with statistical confidence. The roadmap of Targeted Learning emphasizes tailoring statistical procedures so as to minimize their assumptions, carefully grounding them only in the scientific knowledge available.
  arXiv  Detail & Related papers  (2020-06-12T17:17:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.