Entity · paper

Selection Shapes the Boundary: A Preregistered Replication of Monotonicity and Label Agreement in Unselected NLI Populations

paperactiveprovisional

selection-shapes-the-boundary-a-preregistered-replication-of-monotonicity-and-label-agreement-in-unselected-nli-populations-49a22d22

·1 events·first seen Jul 22, 2026

Aliases: Selection Shapes the Boundary: A Preregistered Replication of Monotonicity and Label Agreement in Unselected NLI Populations

Co-occurring entities

SNLI ChaosNLI MultiNLI

More like this (12)

The Neutral Mask: How RLHF Provides Shallow Alignment while Leaving Partisan Structure Intact in a Large Language Model Scaling LLM Reasoning from Minimal Labels: A Semi-Supervised Framework with a Lightweight Verifier Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Models On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignment leave-one-out baseline Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation Dynamic-Probabilistic Consistency Gap The Shibboleth Effect: Auditing the Cross-Lingual Distributional Skew of Large Language Models StylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMs LESS: Mutual-Stability Sampling for Diffusion Language Models MultiNLI Human Label Variation (HLV)

Recent events (1)

4arXiv · cs.CL·Jul 22, 2026·source ↗

Preregistered replication finds monotonicity-agreement boundary in NLI is a selection artifact, not a population property

A preregistered replication study tests whether non-upward monotonicity operators produce lower label agreement in NLI datasets, a finding from prior work on human label variation (HLV). Using unselected SNLI and MultiNLI development sets rather than the disagreement-selected ChaosNLI resource, all seven confirmatory contrasts return effects in the opposite direction and far below the smallest effect size of interest. The authors conclude the earlier negative boundary is likely a selection artifact of ChaosNLI's construction, not a population-level linguistic property. The result carries a methodological warning for HLV research: claims built on selected re-annotation resources should explicitly condition on their selection criteria.

Evaluation and Benchmarking Selection Shapes the Boundary: A Preregistered Replication of Monotonicity and Label Agreement in Unselected NLI Populations SNLI ChaosNLI +1 more