# Are LLMs Positionally Consistent Ordinal Classifiers? A Systematic Evaluation

arXiv: https://arxiv.org/abs/2608.08869 · HTML: https://mlsanity.com/paper/2608.08869/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 32 references that are in the map.
- First posted on arXiv 9 Aug 2026.

## Builds on (most cited first, 26 of 26)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [Large Language Models Are Not Robust Multiple Choice Selectors](https://mlsanity.com/paper/2309.03882/) (2023)
- [Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents](https://mlsanity.com/paper/2304.09542/) (2023)
- [Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2406.07791/) (2024)
- [Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions](https://mlsanity.com/paper/2308.11483/) (2023)
- [SemEval-2017 Task 4: Sentiment Analysis in Twitter](https://mlsanity.com/paper/1912.00741/) (2019)
- [SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval)](https://mlsanity.com/paper/1903.08983/) (2019)
- [Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering](https://mlsanity.com/paper/2309.17249/) (2023)
- [Mitigating Label Biases for In-context Learning](https://mlsanity.com/paper/2305.19148/) (2023)
- [Reordering Examples Helps during Priming-based Few-Shot Learning](https://mlsanity.com/paper/2106.01751/) (2021)
- [Evaluating Scoring Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2506.22316/) (2025)
- [CalibraEval: Calibrating Prediction Distribution to Mitigate Selection Bias in LLMs-as-Judges](https://mlsanity.com/paper/2410.15393/) (2024)
- [Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language Models](https://mlsanity.com/paper/2310.07712/) (2023)
- [Unveiling Selection Biases: Exploring Order and Token Sensitivity in Large Language Models](https://mlsanity.com/paper/2406.03009/) (2024)
- [Where to show Demos in Your Prompt: A Positional Bias of In-Context Learning](https://mlsanity.com/paper/2507.22887/) (2025)
- [Measuring Scalar Constructs in Social Science with LLMs](https://mlsanity.com/paper/2509.03116/) (2025)
- [Teacher-Student Training for Debiasing: General Permutation Debiasing for Large Language Models](https://mlsanity.com/paper/2403.13590/) (2024)
- [Am I More Pointwise or Pairwise? Revealing Position Bias in Rubric-Based LLM-as-a-Judge](https://mlsanity.com/paper/2602.02219/) (2026)
- [LAMPO: Large Language Models as Preference Machines for Few-shot Ordinal Classification](https://mlsanity.com/paper/2408.03359/) (2024)
- [Positional Bias in Binary Question Answering: How Uncertainty Shapes Model Preferences](https://mlsanity.com/paper/2506.23743/) (2025)

## Built on by (most cited first, 1 of 1)

- [CORDIAL: Calibrating Ordinal LLM Outputs from Few Labels](https://mlsanity.com/paper/2609.29807/) (2026)

## Abstract (arXiv)

Large language models are increasingly used for ordinal classification, yet semantically equivalent changes to prompt organization can alter their predictions. We conduct systematic experiments to characterize positional bias from label order, demonstration order, and demonstration placement. First, we apply the three probes to ten frontier LLMs on a common ordinal-classification task; every model is sensitive to all three positional sources, showing that the problem is pervasive. Second, we vary eight prompt-, task-, and model-level factors across five datasets; accuracy and stability are often misaligned, and only lower scale cardinality consistently improves both. Third, we compare pointwise, pairwise, and listwise inference, alternative aggregation and debiasing methods, and joint configurations; the tested corrections do not provide a reliable remedy, while a comparison-based listwise formulation offers the best balance but transfers unevenly across models and bias sources. These findings show that positional robustness depends on the full system configuration rather than the model alone. Ordinal-classification systems should therefore be selected jointly for predictive performance and stability.