The paper introduces a calibrated instrument for rigorously measuring how inference optimizations—such as quantization, early‑exit, and speculative decoding—affect the output quality of large language models. It uses a formally calibrated LLM judge that verifies no systematic bias between statistically equivalent outputs and includes a null condition to ensure measured differences are zero. Applying this method, the authors find that a 4‑bit model is indistinguishable from its 16‑bit counterpart, while 3‑bit quantization and early‑exit techniques incur measurable quality losses that vary by language and task, and that token‑certainty‑based acceptance rules cannot reliably identify impactful errors.
By Jerry Kaplan
The paper argues that traditional global calibration metrics, such as Expected Calibration Error and Brier Score, are confounded by differences in model accuracy when comparing large language models. It introduces ACE, an accuracy‑controlled evaluation framework that offers Instance‑Aligned, Distribution‑Aligned, and Candidate‑Aligned views to provide fairer cross‑model comparisons. Experiments across various benchmarks reveal that many reported calibration advantages disappear after accuracy control and that model rankings often reverse, indicating that raw global metrics are unreliable for cross‑model calibration assessment.
By Zhichao Yang, Caiqi Zhang, Ruihan Yang, Chengzu Li, Nigel Collier, Deqing Yang
arXiv:2608. 15046v1 Announce Type: new Abstract: A fraction of a point of benchmark accuracy is the usual evidence that a compressed model is equivalent to its original.
By Amogh Singh
arXiv:2608. 14509v1 Announce Type: new Abstract: Systems that ask a language model to reach a conclusion from many sources usually concatenate them into one prompt.
By Zhelun Wu
arXiv:2509. 17314v4 Announce Type: replace-cross Abstract: Software increasingly relies on the emergent capabilities of Large Language Models (LLMs), from natural language understanding to program analysis and generation.
By Juyeon Yoon, Somin Kim, Robert Feldt, Shin Yoo
The paper investigates how test‑time computation can enhance language models and at what cost, introducing the SELF‑POT benchmark to evaluate this across competition mathematics, competitive programming, and agentic workflows. SELF‑POT separates candidate coverage from final accuracy, tracks correctness transitions under revision, and measures protocol completion alongside task success. Using a unified budget rule, the study compares direct inference, parallel sampling, and self‑revision across five low‑cost reasoning models, revealing that selection rules and failure handling significantly influence gains and cost savings.
By Bangji Yang, Jingyuan Li, Jiajun Fan, Yi Evie Zhang, Ruihan Guo, Hongba Ma, Neil He, Chumeng Liang, Qinglong Zheng, Zhanghan Ni, Ge Liu
When a tool-using agent is given the same task in a different language, does it still take the same steps? Multilingual evaluation rarely asks: it compares final answers and discards the actions.
The paper argues that relying solely on overall accuracy or F1 scores to validate automatic scorers in LLM evaluation can conceal prompt‑specific errors that distort comparative results. By auditing six models on 180 invented‑entity questions across six prompts, the authors show that a scorer’s overall F1 of .916 masks substantial variation—up to 33.3%—in error rates depending on the prompt. In a second audit, differences in measured prompt effects dropped dramatically when multiple raters were used, highlighting the need to validate the exact comparison rather than the scorer alone.
By Ancil Crayton
The study analyzes 373,019 judgments from LLM‑scored benchmarks, decomposing variance into system, item, judge, and interaction components via generalizability theory. It finds that with a single judge, generalizability converges to a ceiling determined by the system‑by‑judge variance, which is substantially lower in pairwise preference settings, allowing one judge to suffice. The research also reveals significant biases in presentation order and highlights that many published win‑rate claims fall below the measured floor of the benchmarks.
By Atul Anand
arXiv:2608. 06564v2 Announce Type: replace Abstract: Quantization is how large language models are actually deployed, and below four bits it hurts.
By Zekun Wu, Swati Dhiman, Adriano Koshiyama
arXiv:2608. 11694v1 Announce Type: cross Abstract: A benchmark score comes from a single phrasing of each problem.
By Shailja Thakur, Sungeun An, Chad DeLuca, Hima Patel
Almost every large language model that reaches a broad audience is quantized: trained in full precision, then compressed for efficiency. This step is assumed harmless and its safety is rarely re-checked.