arXiv:2607. 23915v1 Announce Type: cross Abstract: We examine how prompt tone affects both accuracy of the LLM answers and inference cost as reflected in output-token consumption.
By Akhil Kumar, Om Dobariya
arXiv:2606. 24083v1 Announce Type: cross Abstract: "Talk short.
By Morayo Danielle Adeyemi, Ryan A. Rossi, Franck Dernoncourt
The paper investigates how prompt design influences energy consumption in on-device large language models (LLMs). It examines two prompt properties—cognitive load and phrasing pattern—across various datasets, models, and devices, using phase-level profiling to separate prefill and decode energy. Findings show that cognitive load mainly affects energy per token, while phrasing pattern influences energy mainly through token usage, and that prompt design reshapes the energy-quality trade‑off differently for each model.
By Wei Hu, Xiaolong Tu, Dawei Chen, Yitao Chen, Kyungtae Han, Haoxin Wang
arXiv:2608. 12150v1 Announce Type: new Abstract: Standard evaluation of large language models assumes stable model rankings across inference conditions.
By Rodrigo Guedes de Souza, Alison R. Panisson
As the chain-of-thought reasoning capabilities of large language models improve, evaluating and calibrating their reasoning confidence is becoming increasingly important for quantifying the uncertaint...
The paper introduces Variance‑Calibrated Modulation (VCM), a training‑free pre‑decoding technique that reshapes language model probability distributions before truncation. VCM uses two dynamic mechanisms: a Contextual Searchlight via PMI to suppress stopwords and highlight context‑relevant tokens, and an Adaptive Self‑Debiasing that applies scale‑invariant penalization based on real‑time logit standard deviation. Experiments on open‑ended generation, factual QA, and mathematical reasoning show that VCM consistently reduces the likelihood trap, improving diversity, coherence, and reasoning accuracy with minimal computational cost.
By Yuanhao Ding, Meimingwei Li, Esteban Garces Arias, Matthias A{\ss}enmacher, Christian Heumann, Chongsheng Zhang