analiza aiqbench
This paper introduces a benchmark that tests how well tabular ML models, including LLMs, generalize when training data is skewed by convenience sampling. Its main contribution is controlled perturbation of feature-target relationships against a fixed deployment population, which isolates a failure mode that existing distribution-shift benchmarks handle loosely. For practitioners, the key question is whether the reported degradation holds across real datasets and LLM architectures, since the benchmark's value depends on how well its synthetic shifts reflect actual sampling bias.
INCONVENIENT: A Benchmark to Assess LLM Generalization Capabilities from Convenience Samples
arXiv:2610.21038v1 Announce Type: cross Abstract: Machine learning models for tabular prediction typically assume that training data are representative of the population on which they will be deployed. In practice, however, data are often collected based on convenience, availability, or cost, resulting in systematic sampling biases that can distort feature--target relationships and undermine real-world generalization. Existing tabular distribution-shift benchmarks primarily construct out-of-distribution (OOD) settings by partitioning observations across naturally occurring domains. While such partitions may induce changes in P(Y | X), the resulting shifts are neither explicitly controlled nor isolated, and the evaluation distributions themselves are often not representative of the broader target population. We introduce INCONVENIENT, a benchmark designed to study robustness to convenience-sample bias. Rather than relying on naturally occurring domain partitions, INCONVENIENT directly perturbs feature--target relationships in the training distribution while preserving the original population distribution as the deployment environment. This setting more closely reflects real-world scenarios in which models are developed from unrepresentative samples and subsequently deployed on a broader population. The distinction is particularly relevant for large language models (LLMs), whose pretraining may encode population-level knowledge that extends beyond the relationships observed in a biased training dataset. Unlike existing distribution-shift benchmarks, INCONVENIENT provides explicit control over both the direction and severity of relationship shifts, enabling a systematic assessment of robustness to convenience sampling. The benchmark comprises 200 tabular classification and regression datasets spanning diverse application domains and generates around 15,500 shifted training distributions which lead to substantial downstream degradation.
Abstract:Machine learning models for tabular prediction typically assume that training data are representative of the population on which they will be deployed. In practice, however, data are often collected based on convenience, availability, or cost, resulting in systematic sampling biases that can distort feature--target relationships and undermine real-world generalization. Existing tabular distribution-shift benchmarks primarily construct out-of-distribution (OOD) settings by partitioning observations across naturally occurring domains. While such partitions may induce changes in P(Y | X), the resulting shifts are neither explicitly controlled nor isolated, and the evaluation distributions themselves are often not representative of the broader target population. We introduce INCONVENIENT, a benchmark designed to study robustness to convenience-sample bias. Rather than relying on naturally occurring domain partitions, INCONVENIENT directly perturbs feature--target relationships in the training distribution while preserving the original population distribution as the deployment environment. This setting more closely reflects real-world scenarios in which models are developed from unrepresentative samples and subsequently deployed on a broader population. The distinction is particularly relevant for large language models (LLMs), whose pretraining may encode population-level knowledge that extends beyond the relationships observed in a biased training dataset. Unlike existing distribution-shift benchmarks, INCONVENIENT provides explicit control over both the direction and severity of relationship shifts, enabling a systematic assessment of robustness to convenience sampling. The benchmark comprises 200 tabular classification and regression datasets spanning diverse application domains and generates around 15,500 shifted training distributions which lead to substantial downstream degradation.
Machine Learning (cs.LG); Computation and Language (cs.CL)
arXiv:2610.21038 [cs.LG]
(or arXiv:2610.21038v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.21038 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 336 cuvinte
Subiecte conexe
[AINews] not much happened today
Latent Space · 10 sept. 2026
Coverage-driven alignment - What ‘Teaching Claude Why’ can borrow from AV verification
LessWrong · 8 iun. 2026
Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident
METR · 26 aug. 2026
Projection sampling preserves capabilities but diminishes gains from alignment fine-tuning
LessWrong · 16 oct. 2026