Format Sensitivity Index: Token-Controlled Prompt Wrapper Robustness and Schema Compliance in LLM Benchmarking

• URL: http://arxiv.org/abs/2607.09665v1
• Date: Sat, 02 May 2026 22:51:41 GMT
• Title: Format Sensitivity Index: Token-Controlled Prompt Wrapper Robustness and Schema Compliance in LLM Benchmarking
• Abstract summary: We study the variance under a token-controlled protocol and introduce two complementary metrics: the Format Sensitivity Index (FSI), the accuracy range induced by wrapper choice, and the Parseability Sensitivity Index (PSI), the corresponding range in answer parseability.<n>We find that mean FSI varies by over 30x across models and is largely explained by compliance failures.<n>A fixed-effects regression shows that parseability remains a strong predictor of accuracy even after controlling for task, model, and wrapper.
• Score: 0.0
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Prompt wrappers often differ only in formatting, yet they can change model scores enough to flip leaderboard conclusions. We study this variance under a token-controlled protocol and introduce two complementary metrics: the Format Sensitivity Index (FSI), the accuracy range induced by wrapper choice, and the Parseability Sensitivity Index (PSI), the corresponding range in answer parseability. Across 140,000 OpenRouter generations spanning 7 QA tasks, 5 wrapper families, and 4 instruct models from 7B to 72B parameters, we find that mean FSI varies by over 30x across models and is largely explained by compliance failures. A fixed-effects regression shows that parseability remains a strong predictor of accuracy even after controlling for task, model, and wrapper. We argue that reporting accuracy without wrapper variance and compliance is statistically fragile, and we give practical recommendations for both benchmarking and structured-output deployments.

Related papers

• Semantic Drift in Bug Resolution: How Behavioral Signals Propagate from Reports to Tests and Patches [18.727291516223115]
  Desc2Fix is a framework for measuring semantic alignment between bug reports, triggering tests, and developer-written fixes.<n>We analyze 2,857 report-test-patch triplets from Defects4J and SWT-Bench using GPT-4o and DeepSeek-Chat.
  arXiv  Detail & Related papers  (2026-07-20T22:32:23Z)
• CaliDist: Calibrating Large Language Models via Behavioral Robustness to Distraction [51.56484100374058]
  Existing calibration methods for Large Language Models (LLMs) often overlook a critical dimension of trustworthiness: a model's behavioral robustness.<n>We introduce textscCaliDist, a novel post-hoc calibration approach that directly measures and penalizes a model's susceptibility to distraction.<n>textscCaliDist consistently achieves lower Expected Error (ECE) and Brier Score compared with strong baselines.
  arXiv  Detail & Related papers  (2026-06-04T07:27:53Z)
• Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization [54.749573452394664]
  We find that accuracy collapses as instance data grows, even when the formulation itself is simple.<n>We address this via a simple inference-time approach, BIND, which externalizes numeric data to structured files so the model binds data rather than from prompt prompt.<n>We validate our hypothesis by finetuning a model exclusively on binding and show that it outperforms end-to-end SFT and RL across three structurally distinct optimization categories.
  arXiv  Detail & Related papers  (2026-05-20T21:25:41Z)
• What Single-Prompt Accuracy Misses: A Multi-Variant Reliability Audit of Language Models [0.0]
  Single-prompt accuracy is the dominant way to benchmark language models, but it can miss reliability failures that matter.<n>We evaluate a 15-model open-weight corpus, with the main reliability analyses focused on 10 instruct models across five classification and reasoning benchmarks.<n>We find three broad results. First, evaluation design can materially change the conclusion.<n>Second, confidence signals are fragile. On MMLU-Pro, every primary model verbally reports confidence substantially above both its accuracy and its token-probability confidence on the same rows, and verbal parse rate can collapse for a single model on a single prompt variant.
  arXiv  Detail & Related papers  (2026-05-03T20:05:08Z)
• Parametric Knowledge and Retrieval Behavior in RAG Fine-Tuning for Electronic Design Automation [0.18472148461613155]
  We evaluate RAG fine-tuning for long-form text generation in electronic design automation.<n>We introduce TriFEX, a human-validated, triple-based evaluation pipeline.<n>We show that ROUGE and BERTScore fail to detect factual differences that our triple-based evaluation reveals.
  arXiv  Detail & Related papers  (2026-03-24T10:33:57Z)
• FMBench: Adaptive Large Language Model Output Formatting [49.52930069696333]
  We present FMBench, a benchmark for adaptive Markdown output formatting.<n>Experiments on two model families show that SFT consistently improves semantic alignment.<n>Results also reveal an inherent trade-off between semantic and structural objectives.
  arXiv  Detail & Related papers  (2026-02-06T04:42:06Z)
• CodeFuse-CommitEval: Towards Benchmarking LLM's Power on Commit Message and Code Change Inconsistency Detection [8.631593963090985]
  Version control relies on commit messages to convey the rationale for code changes, but these messages are often low quality and inconsistent with their diffs-known as message-code inconsistency (MCI)<n>We introduce CODEFUSE-COMMITEVAL, the first benchmark designed for MCI detection using large language models (LLMs)<n>We generate seven types of inconsistent messages through rule-guided mutations of originally consistent commits and apply two-fold validation to verify both positive and negative samples.
  arXiv  Detail & Related papers  (2025-11-25T03:33:57Z)
• Do LLMs Know They Are Being Tested? Evaluation Awareness and Incentive-Sensitive Failures in GPT-OSS-20B [1.948261185683419]
  We investigate whether "evaluation scent" inflates measured performance without commensurate capability gains.<n>We run six paired A/B scenarios that hold task content and decoding fixed while varying framing.<n>We provide a reproducible A/B framework (prompt banks, validators, per-run scores, scripts) and practical guidance.
  arXiv  Detail & Related papers  (2025-10-08T09:49:05Z)
• Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty [49.19257648205146]
  We propose an unsupervised conformal inference framework for generation.<n>Our gates achieve close-to-nominal coverage and provide tighter, more stable thresholds than split UCP.<n>The result is a label-free, API-compatible gate for test-time filtering.
  arXiv  Detail & Related papers  (2025-09-26T23:40:47Z)
• BUMP: A Benchmark of Unfaithful Minimal Pairs for Meta-Evaluation of Faithfulness Metrics [70.52570641514146]
  We present a benchmark of unfaithful minimal pairs (BUMP) BUMP is a dataset of 889 human-written, minimally different summary pairs. Unlike non-pair-based datasets, BUMP can be used to measure the consistency of metrics.
  arXiv  Detail & Related papers  (2022-12-20T02:17:30Z)
• Robust Question Answering Through Sub-part Alignment [53.94003466761305]
  We model question answering as an alignment problem. We train our model on SQuAD v1.1 and test it on several adversarial and out-of-domain datasets.
  arXiv  Detail & Related papers  (2020-04-30T09:10:57Z)
• Meta-Learned Confidence for Few-shot Learning [60.6086305523402]
  A popular transductive inference technique for few-shot metric-based approaches, is to update the prototype of each class with the mean of the most confident query examples. We propose to meta-learn the confidence for each query sample, to assign optimal weights to unlabeled queries. We validate our few-shot learning model with meta-learned confidence on four benchmark datasets.
  arXiv  Detail & Related papers  (2020-02-27T10:22:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.