Contrastive adversarial gender debiasing
Natural Language Processing JournalThis research contributes a comprehensive analysis of gender bias within contemporary AI language models, specifically examining iterations of the GPT series, alongside Gemini and Llama. The study offers a systematic investigation, encompassing multiple experiments spanning sentence completions, generative narratives, bilingual analysis, and visual ...
openaire +3 more sources
General Phrase Debiaser: Debiasing Masked Language Models at a Multi-Token Level
ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)Accepted by ICASSP 2024 as mian conference ...
Bingkang Shi +6 more
openaire +3 more sources
Correcting common errors in probabilistic evaluations: efficacy of debiasing
, 2006 SPE paper number 102188‘Debiasing” refers to techniques taught during risk and uncertainty training that enable trainees to avoid or reduce errors arising from cognitive biases.
Begg, S. +5 more
core +1 more source
AILarge Language Models (LLMs) inherit societal biases from their training data, potentially leading to harmful outputs. While various techniques aim to mitigate these biases, their effects are typically evaluated only along the targeted dimension, leaving
Shireen Chand +2 more
doaj +1 more source
Teacher-Student Training for Debiasing: General Permutation Debiasing for Large Language Models
Findings of the Association for Computational Linguistics ACL 2024Large Language Models (LLMs) have demonstrated impressive zero-shot capabilities and versatility in NLP tasks, however they sometimes fail to maintain crucial invariances for specific tasks. One example is permutation sensitivity, where LLMs' outputs may significantly vary depending on the order of the input options.
Adian Liusie +2 more
openaire +2 more sources
Debiasing Polynomial and Fourier Regression
We study the problem of approximating an unknown function $f:\mathbb{R}\to\mathbb{R}$ by a degree-$d$ polynomial using as few function evaluations as possible, where error is measured with respect to a probability distribution $μ$. Existing randomized algorithms achieve near-optimal sample complexities to recover a $ (1+\varepsilon) $-optimal ...
Chris Camaño +2 more
openaire +2 more sources
Additional Material for Debiasing Architectural Decision-Making: Teaching Software Practitioners
<p>Additional material for the paper subsmission "Debiasing Architectural Decision-Making: Teaching Software Practitioners".<br><br>Coding_info.xlsx - Code description as well as code measurements for all coded values.<br> ...
Anonymous
core +1 more source
Restoring the Right Stream: Training-Free OOD Robustness for Vision-Language-Action Policies. [PDF]
Entropy (Basel)Yan Z, Shen G.
europepmc +1 more source
Adversarial debiasing for age-equitable diabetes prediction: performance-fairness trade-offs and partition dependency in machine learning. [PDF]
Front Digit HealthYata VK +4 more
europepmc +1 more source
TASRIC: A Type-Aware Semantic Retrieval Augmentation Framework With Iterative Correction for Bias Mitigation. [PDF]
Ann N Y Acad SciLi C, Li C, Zhang M.
europepmc +1 more source