# Consistency-based Abductive Reasoning over Perceptual Errors of Multiple Pre-trained Models in Novel Environments

arXiv: https://arxiv.org/abs/2505.19361 · HTML: https://mlsanity.com/paper/2505.19361/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 5 of its 24 references that are in the map.
- First posted on arXiv 25 May 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 5 of 5)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [The Surprising Effectiveness of Test-Time Training for Few-Shot Learning](https://mlsanity.com/paper/2411.07279/) (2024)
- [Imagining and building wise machines: The centrality of AI metacognition](https://mlsanity.com/paper/2411.02478/) (2024)
- [Rule-Based Error Detection and Correction to Operationalize Movement Trajectory Classification](https://mlsanity.com/paper/2308.14250/) (2023)

## Built on by (most cited first, 4 of 4)

- [Machine Learning Model Integration with Open World Temporal Logic for Process Automation](https://mlsanity.com/paper/2506.17776/) (2025)
- [Lattice Annotated Temporal (LAT) Logic for Non-Markovian Reasoning](https://mlsanity.com/paper/2509.02958/) (2025)
- [Position: Artificial Intelligence Needs Meta Intelligence -- the Case for Metacognitive AI](https://mlsanity.com/paper/2605.15567/) (2026)
- [Adversarially Robust Abductive Fusion of Pre-trained Transformer-based Perception Models](https://mlsanity.com/paper/2608.04190/) (2026)

## Abstract (arXiv)

The deployment of pre-trained perception models in novel environments often leads to performance degradation due to distributional shifts. Although recent artificial intelligence approaches for metacognition use logical rules to characterize and filter model errors, improving precision often comes at the cost of reduced recall. This paper addresses the hypothesis that leveraging multiple pre-trained models can mitigate this recall reduction. We formulate the challenge of identifying and managing conflicting predictions from various models as a consistency-based abduction problem, building on the idea of abductive learning (ABL) but applying it to test-time instead of training. The input predictions and the learned error detection rules derived from each model are encoded in a logic program. We then seek an abductive explanation--a subset of model predictions--that maximizes prediction coverage while ensuring the rate of logical inconsistencies (derived from domain constraints) remains below a specified threshold. We propose two algorithms for this knowledge representation task: an exact method based on Integer Programming (IP) and an efficient Heuristic Search (HS). Through extensive experiments on a simulated aerial imagery dataset featuring controlled, complex distributional shifts, we demonstrate that our abduction-based framework outperforms individual models and standard ensemble baselines, achieving, for instance, average relative improvements of approximately 13.6% in F1-score and 16.6% in accuracy across 15 diverse test datasets when compared to the best individual model. Our results validate the use of consistency-based abduction as an effective mechanism to robustly integrate knowledge from multiple imperfect models in challenging, novel scenarios.