paper-with-me

홈 › Papers

Fine-tune your Classifier: Finding Correlations With Temperature

2022-10-18 · Benjamin Chamand, Olivier Risser-Maroix, Camille Kurtz, Philippe Joly, Nicolas Loménie

Temperature is a widely used hyperparameter in various tasks involving neural networks, such as classification or metric learning, whose choice can have a direct impact on the model performance. Most of existing works select its value using hyperparameter optimization methods requiring several runs to find the optimal value. We propose to analyze the impact of temperature on classification tasks by describing a dataset as a set of statistics computed on representations on which we can build a heuristic giving us a default value of temperature. We study the correlation between these extracted statistics and the observed optimal temperatures. This preliminary study on more than a hundred combinations of different datasets and features extractors highlights promising results towards the construction of a general heuristic for temperature.

📄 PDF Abstract BibTeX arXiv:2210.09715

Code (0)

등록된 구현이 없습니다.

Tasks

Hyperparameter OptimizationMetric Learning

Similar Papers 제목 키워드 기반

Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis

2023-05-23 · Oscar Chew, Hsuan-Tien Lin, Kai-Wei Chang, Kuan-Hao Huang

Recent research has revealed that machine learning models have a tendency to leverage spurious correlations that exist in the training set but may not hold true in general circumstances. For instance, a sentiment classif…

Classificationtext-classificationText Classification

Your Large Language Models Are Leaving Fingerprints

2024-05-22 · Hope McGovern, Rickard Stureborg, Yoshi Suhara, Dimitris Alikaniotis

It has been shown that finetuned transformers and other supervised detectors effectively distinguish between human and machine-generated text in some situations arXiv:2305.13242, but we find that even simple classifiers …

RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models

2024-11-06 · Maya Varma, Jean-Benoit Delbrouck, Zhihong Chen, Akshay Chaudhari 외

Fine-tuned vision-language models (VLMs) often capture spurious correlations between image features and textual attributes, resulting in degraded zero-shot performance at test time. Existing approaches for addressing spu…

image-classificationImage Classificationzero-shot-classificationZero-Shot Learning

Feeding LLM Annotations to BERT Classifiers at Your Own Risk

2025-04-21 · Yucheng Lu, Kazimier Smith

Using LLM-generated labels to fine-tune smaller encoder-only models for text classification has gained popularity in various settings. While this approach may be justified in simple and low-stakes applications, we conduc…

text-classificationText Classification

multiMentalRoBERTa: A Fine-tuned Multiclass Classifier for Mental Health Disorder

2025-11-01 · K M Sajjadul Islam, John Fields, Praveen Madiraju arxiv

The early detection of mental health disorders from social media text is critical for enabling timely support, risk assessment, and referral to appropriate resources. This work introduces multiMentalRoBERTa, a fine-tuned…