Large language models (LLMs) used for ordinal classification exhibit positional bias, where changes in label order, demonstration order, and demonstration placement affect predictions. Systematic experiments across ten frontier LLMs, eight prompt/task/model factors, and five datasets reveal that all models are sensitive to these positional sources, and that accuracy and stability often diverge. Various correction methods, including pointwise, pairwise, and listwise inference, do not reliably mitigate the bias, though a comparison-based listwise approach shows the best overall balance yet varies across models and bias types.
arXiv:2602.02219v3 Announce Type: replace Abstract: Large language models are widely employed as evaluators, a paradigm commonly referred to as LLM-as-a-judge. Prior research has predominantly examin...
arXiv:2608.20999v1 Announce Type: new Abstract: Multimodal LLMs apply the language model interface to visual inputs, where ordinal regression tasks such as age estimation, image quality assessment, a...
arXiv:2608. 11947v1 Announce Type: cross Abstract: Multiple-choice benchmarks are widely used to evaluate large language models, but MCQ scores conflate knowledge with sensitivity to option order, which makes them unreliable measures of model knowledge.
Large language models are increasingly evaluated through the values they endorse, but such evaluations presuppose that models can identify the value expressed in a concrete situation. We study this prerequisite as controlled top-1 recognition over Schwartz's ten basic values.
The paper introduces DIAL, a framework that uses large language models (LLMs) as judges while mitigating position bias and aligning their judgments with human preferences. DIAL separates judge‑specific position effects, learns shared structure in debiased LLM preferences, and adaptively calibrates this structure toward human targets using limited human comparisons. Experiments on simulations and three human‑preference benchmarks show that DIAL remains robust to unbalanced response order, achieves strong human‑aligned rankings with few labels, and adapts when LLM information is imperfect, supported by a real‑data study of over 410K judgments from 21 LLM judges.
The paper argues that the current LLM-as-a-judge evaluation method, which compensates for systematic measurement bias by increasing the number of comparisons, is statistically unsound and computationally wasteful. It identifies that treating LLM judges as neutral ignores documented biases such as position bias, verbosity bias, judge severity, and self‑enhancement. The authors propose a unified latent variable framework that jointly models pairwise and ordinal data while explicitly correcting for these confounders, enabling reliable rankings with far fewer comparisons and negligible additional compute.
arXiv:2607. 23575v1 Announce Type: cross Abstract: Ordinal regression is widely used in scenarios where labels are discrete yet inherently ordered.
arXiv:2610.01428v1 Announce Type: cross Abstract: Generalization in large language models (LLMs) is the ability to produce consistent and semantically stable outputs when the same input is expressed...
The paper investigates how benchmark contamination—leakage of test items into training data—affects large language model (LLM) leaderboards. By comparing original test items with semantically equivalent paraphrases, the authors measure contamination as a violation of anchor-item invariance and find that it inflates absolute scores but rarely changes model rankings. Across 47 public models and 74 finetuned models on four benchmarks, the rank correlation between standard and paraphrase-controlled leaderboards is 0.997, with only a handful of cases showing differential contamination that could alter rankings.
arXiv:2608.28382v1 Announce Type: new Abstract: Users often ask large language models (LLMs) to report how confident they are, but it is unclear whether such linguistic confidence tracks the model's...
The paper introduces an Item Response Theory (IRT)–based indicator that identifies likely mislabeled items in large language model (LLM) benchmarks with 95% precision among the top 200 examples across seven preference and multiple-choice datasets, using responses from 114 models. It outperforms a supervised classifier and attributes the mislabels to mechanical labeling heuristics, inherited annotation errors, and inherently ambiguous items. The IRT analysis also reveals that reward models tend to specialize in stylistic preference rather than factual knowledge, and pinpoints a frontier reward model that aligns with detected mislabels at 78% accuracy compared to 38% for other models, suggesting benchmark contamination or over‑optimization.
Direct-decision models turn text into low-latency structured labels and scores, making them attractive for classification and automatic evaluation. Yet reliability requires more than accuracy: a model...