English
Related papers

Related papers: The Well-Tempered Classifier: Some Elementary Prop…

200 papers

The great performances of deep learning are undeniable, with impressive results over a wide range of tasks. However, the output confidence of these models is usually not well-calibrated, which can be an issue for applications where…

Computer Vision and Pattern Recognition · Computer Science 2019-06-11 Azadeh Sadat Mozafari , Hugo Siqueira Gomes , Wilson Leão , Christian Gagné

Pre-trained protein language models have demonstrated significant applicability in different protein engineering task. A general usage of these pre-trained transformer models latent representation is to use a mean pool across residue…

While Bayesian neural networks (BNNs) provide a sound and principled alternative to standard neural networks, an artificial sharpening of the posterior usually needs to be applied to reach comparable performance. This is in stark contrast…

Machine Learning · Computer Science 2023-07-19 Gregor Bachmann , Lorenzo Noci , Thomas Hofmann

Modern large language model (LLM) inference engines optimize throughput and latency under fixed decoding rules, treating generation as a linear progression in token time. We propose a fundamentally different paradigm: entropic\-time…

Computation and Language · Computer Science 2026-03-05 Andrew Kiruluta

As large language models (LLMs) are increasingly used for factual question-answering, it becomes more important for LLMs to have the capability to communicate the likelihood that their answer is correct. For these verbalized expressions of…

Computation and Language · Computer Science 2025-12-15 Sophia Hager , David Mueller , Kevin Duh , Nicholas Andrews

The thermal and acoustic properties displayed by a wide variety of glasses at low temperatures are well described by the model of tunneling two level systems (TLS). We review the standard TLS model as well as developments that have occurred…

Disordered Systems and Neural Networks · Physics 2021-01-11 Clare C. Yu , Hervé M. Carruzzo

Reinforcement Learning has demonstrated substantial improvements in the reasoning abilities of Large Language Models (LLMs), exhibiting significant applicability across various domains. Recent research has identified that tokens within LLMs…

Computation and Language · Computer Science 2025-10-13 Haomin Zhuang , Yujun Zhou , Taicheng Guo , Yue Huang , Fangxu Liu , Kai Song , Xiangliang Zhang

Large language models (LLMs) have demonstrated remarkable capabilities but often struggle to align with human preferences, leading to harmful or undesirable outputs. Preference learning, which trains models to distinguish between preferred…

Machine Learning · Computer Science 2025-10-16 Shawn Im , Sharon Li

Even when decoding with temperature $T=0$, large language models (LLMs) can produce divergent outputs for identical inputs. Recent work by Thinking Machines Lab highlights implementation-level sources of nondeterminism, including batch-size…

Artificial Intelligence · Computer Science 2026-04-27 Alberto Messina , Stefano Scotta

Deep Learning methods are known to suffer from calibration issues: they typically produce over-confident estimates. These problems are exacerbated in the low data regime. Although the calibration of probabilistic models is well studied,…

Machine Learning · Statistics 2021-11-30 Rahul Rahaman , Alexandre H. Thiery

The temperature parameter plays a profound role during training and/or inference with large foundation models (LFMs) such as large language models (LLMs) and CLIP models. Particularly, it adjusts the logits in the softmax function in LLMs,…

Machine Learning · Computer Science 2024-06-18 Zi-Hao Qiu , Siqi Guo , Mao Xu , Tuo Zhao , Lijun Zhang , Tianbao Yang

Variational inference (VI) combined with data subsampling enables approximate posterior inference over large data sets, but suffers from poor local optima. We first formulate a deterministic annealing approach for the generic class of…

Machine Learning · Statistics 2016-05-31 Stephan Mandt , James McInerney , Farhan Abrol , Rajesh Ranganath , David Blei

For semantic segmentation, label probabilities are often uncalibrated as they are typically only the by-product of a segmentation task. Intersection over Union (IoU) and Dice score are often used as criteria for segmentation success, while…

Computer Vision and Pattern Recognition · Computer Science 2021-07-28 Zhipeng Ding , Xu Han , Peirong Liu , Marc Niethammer

We examined how model size, temperature, and prompt style affect Large Language Models' (LLMs) alignment within itself, between models, and with human in assessing clinical reasoning skills. Model size emerged as a key factor in LLM-human…

Computation and Language · Computer Science 2025-09-25 Julie Jung , Max Lu , Sina Chole Benker , Dogus Darici

With electric power systems becoming more compact and increasingly powerful, the relevance of thermal stress especially during overload operation is expected to increase ceaselessly. Whenever critical temperatures cannot be measured…

Machine Learning · Computer Science 2022-11-03 Wilhelm Kirchgässner , Oliver Wallscheid , Joachim Böcker

Label smoothing is widely used in deep neural networks for multi-class classification. While it enhances model generalization and reduces overconfidence by aiming to lower the probability for the predicted class, it distorts the predicted…

Machine Learning · Computer Science 2021-10-12 Mohamed Maher , Meelis Kull

We study the feasibility of identifying epistemic uncertainty (reflecting a lack of knowledge), as opposed to aleatoric uncertainty (reflecting entropy in the underlying distribution), in the outputs of large language models (LLMs) over…

Machine Learning · Computer Science 2024-02-28 Gustaf Ahdritz , Tian Qin , Nikhil Vyas , Boaz Barak , Benjamin L. Edelman

Self-consistency improves reasoning by aggregating diverse stochastic samples, yet the dynamics behind its efficacy remain underexplored. We reframe self-consistency as a dynamic distributional alignment problem, revealing that decoding…

Computation and Language · Computer Science 2025-06-12 Yiwei Li , Ji Zhang , Shaoxiong Feng , Peiwen Yuan , Xinglin Wang , Jiayi Shi , Yueqi Zhang , Chuyi Tan , Boyuan Pan , Yao Hu , Kan Li

Large language models are increasingly used as automated evaluators in research and enterprise settings, a practice known as LLM-as-a-judge. While prior work has examined accuracy, bias, and alignment with human preferences, far less…

Computation and Language · Computer Science 2026-03-06 Fiona Lau

Autoregressive language models typically use temperature parameter at inference to shape the probability distribution and control the randomness of the text generated. After the text was generated, this parameter can be estimated using…

Computation and Language · Computer Science 2026-03-17 Nikolay Mikhaylovskiy