arXiv:2607. 09665v1 Announce Type: new Abstract: Prompt wrappers often differ only in formatting, yet they can change model scores enough to flip leaderboard conclusions.
arXiv:2603. 23530v2 Announce Type: replace-cross Abstract: Large language models often fail to satisfy formatting instructions when they must simultaneously perform demanding tasks.
arXiv:2607. 19257v1 Announce Type: cross Abstract: Practitioners make three prompt-design decisions with almost no controlled evidence behind them: how to format instructions and context (markdown, plain text, prose, or tabular), how many simultaneous instructions a system prompt can carry before compliance degrades, and how much context a model can hold before recall and honesty degrade.
arXiv:2608.21074v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in research workflows and software development pipelines, yet their output remains sensitive to in...
arXiv:2609.06993v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly generate Markdown that is consumed by renderers, agents, code extractors, and structured downstream pipelin...
The study evaluates whether prompt‑token counts can reliably identify the lineage of large language models served via APIs. Using a frozen‑threshold approach on 24 labeled endpoint pairs, the authors find that token‑count consistency perfectly separates development pairs but only half of the holdout pairs meet the strict repeatability criteria, yielding moderate accuracy and perfect specificity. The results confirm token‑count consistency as a fingerprint of shared tokenization stacks but reject it as a standalone test for model‑family attribution.
Practitioners make three prompt-design decisions with almost no controlled evidence behind them: how to format instructions and context (markdown, plain text, prose, or tabular), how many simultaneous instructions a system prompt can carry before compliance degrades, and how much context a model can hold before recall and honesty degrade. We report two controlled experiments crossing all three factors on one held, contamination-free synthetic corpus (the "Book of Veyra," 8,780 uniquely-named entities, deterministically regenerable from a fixed seed), evaluated across five models.
EvalDetectBench is an open pipeline and benchmark designed to measure evaluation awareness in frontier large language models, enabling practitioners to test models against any Inspect-compatible evaluation. It includes a curated transcript suite from current frontier system-card evaluations and diverse deployment sources, and it assesses both how reliably models recognize they are being evaluated and how detectable individual benchmarks are. The benchmark addresses systematic bias by calibrating probes per model and harmonizing generator selection to correct for variance caused by model identity and prompt choice.
arXiv:2608. 02665v1 Announce Type: cross Abstract: A benchmark score is a measurement instrument, yet most benchmarks read each item at a single canonical surface form.
arXiv:2606. 12117v1 Announce Type: cross Abstract: Benchmark scores often misrepresent a large language model's (LLM's) knowledge, because they rely, e.
The paper investigates the reliability of ranking tables produced by small-sample evaluations of large language models (LLMs). Using LLM‑inferred prompt structure across eight model variants, the authors find that prompt‑structure recovery is highly unstable, with only the bottom of the ranking consistently reproducible. They demonstrate that standard evaluation practices can misrepresent model performance and propose reporting practices to improve transparency.
The paper argues that verbalized confidence—once viewed as overconfident and coarse—has become the preferred soft‑scoring method for LLM‑as‑a‑Judge on top‑tier proprietary models released after 2025. Experiments on SummEval, AggreFact, and HelpSteer2 across up to 18 LLMs show that log‑probabilities are no longer the best signal, and that adding an overconfidence advisory and self‑debate further improves calibration and robustness. The authors note that these enhancements incur little accuracy loss on post‑2025 models but do affect pre‑2025 ones, highlighting a compatibility shift in how confidence should be measured.
arXiv:2605. 27752v2 Announce Type: replace Abstract: LLM confidence calibration is often evaluated by comparing two signals: token-probability scores and verbalized confidence.