# Explicit Abstention Knobs for Predictable Reliability in Video Question Answering

Source: [Explicit Abstention Knobs for Predictable Reliability in Video Question Answering](<https://www.sota2.com/research/paper/695b457c53fdd5c36174308c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-17T05:00:11.890Z

Authors: Jorge Ortiz

Published: 2025-12-31T23:27:32.000Z

## Abstract

High-stakes deployment of vision-language models (VLMs) requires selective prediction, where systems abstain when uncertain rather than risk costly errors. We investigate whether confidence-based abstention provides reliable control over error rates in video question answering, and whether that control remains robust under distribution shift. Using NExT-QA and Gemini 2.0 Flash, we establish two findings. First, confidence thresholding provides mechanistic control in-distribution. Sweeping threshold epsilon produces smooth risk-coverage tradeoffs, reducing error rates f

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2601.00138>)

[PDF](<https://arxiv.org/pdf/2601.00138.pdf>)