Image de couverture de livre

Inference-Time Selective Debiasing to Enhance Fairness in Text Classification Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kuzmin, Gleb, Yadav, Neemesh, Smirnov, Ivan, Baldwin, Timothy, Shelmanov, Artem
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Exploring Large Language Models for Detecting Mental Disorders
par: Kuzmin, Gleb, et autres
Publié: (2024)

Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification
par: Fadeeva, Ekaterina, et autres
Publié: (2024)

Uncertainty Quantification for Large Language Diffusion Models
par: Vazhentsev, Artem, et autres
Publié: (2026)

ReProbe: Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models
par: Ni, Jingwei, et autres
Publié: (2025)

A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs
par: Shelmanov, Artem, et autres
Publié: (2025)

Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models
par: Vazhentsev, Artem, et autres
Publié: (2024)

Vikhr: The Family of Open-Source Instruction-Tuned Large Language Models for Russian
par: Nikolich, Aleksandr, et autres
Publié: (2024)

Effects of Theory of Mind and Prosocial Beliefs on Steering Human-Aligned Behaviors of LLMs in Ultimatum Games
par: Yadav, Neemesh, et autres
Publié: (2025)

Debiasing Reward Models via Causally Motivated Inference-Time Intervention
par: Shinoda, Kazutoshi, et autres
Publié: (2026)

MHSafeEval: Role-Aware Interaction-Level Evaluation of Mental Health Safety in Large Language Models
par: Lee, Suhyun, et autres
Publié: (2026)

LLM-Assisted Content Conditional Debiasing for Fair Text Embedding
par: Deng, Wenlong, et autres
Publié: (2024)

Debiasing Text Safety Classifiers through a Fairness-Aware Ensemble
par: Sturman, Olivia, et autres
Publié: (2024)

Social Debiasing for Fair Multi-modal LLMs
par: Cheng, Harry, et autres
Publié: (2024)

ATGen: A Framework for Active Text Generation
par: Tsvigun, Akim, et autres
Publié: (2025)

Uncertainty-Aware Attention Heads: Efficient Unsupervised Uncertainty Quantification for LLMs
par: Vazhentsev, Artem, et autres
Publié: (2025)

Dual Debiasing: Remove Stereotypes and Keep Factual Gender for Fair Language Modeling and Translation
par: Limisiewicz, Tomasz, et autres
Publié: (2025)

Exploring the Hidden Capacity of LLMs for One-Step Text Generation
par: Mezentsev, Gleb, et autres
Publié: (2025)

Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models
par: Vazhentsev, Artem, et autres
Publié: (2025)

Psychometric Predictive Power of Large Language Models
par: Kuribayashi, Tatsuki, et autres
Publié: (2023)

Uncertainty-aware abstention in medical diagnosis based on medical texts
par: Vazhentsev, Artem, et autres
Publié: (2025)

CatRAG: Functor-Guided Structural Debiasing with Retrieval Augmentation for Fair LLMs
par: Ranjan, Ravi, et autres
Publié: (2026)

Target-oriented Multimodal Sentiment Classification with Counterfactual-enhanced Debiasing
par: Liu, Zhiyue, et autres
Publié: (2025)

Enhancing the QA Model through a Multi-domain Debiasing Framework
par: Wang, Yuefeng, et autres
Publié: (2026)

AXOLOTL: Fairness through Assisted Self-Debiasing of Large Language Model Outputs
par: Ebrahimi, Sana, et autres
Publié: (2024)

General Phrase Debiaser: Debiasing Masked Language Models at a Multi-Token Level
par: Shi, Bingkang, et autres
Publié: (2023)

DINER: Debiasing Aspect-based Sentiment Analysis with Multi-variable Causal Inference
par: Wu, Jialong, et autres
Publié: (2024)

Amplifying, Not Learning: Fine-Tuned AI Text Detectors Amplify a Pretrained Direction
par: Smirnov, Alexander
Publié: (2026)

L2D-Clinical: Learning to Defer for Adaptive Model Selection in Clinical Text Classification
par: Kondadadi, Rishik, et autres
Publié: (2026)

Potential and Challenges of Model Editing for Social Debiasing
par: Yan, Jianhao, et autres
Publié: (2024)

Evaluating Evidence Attribution in Generated Fact Checking Explanations
par: Xing, Rui, et autres
Publié: (2024)

Selecting Between BERT and GPT for Text Classification in Political Science Research
par: Wang, Yu, et autres
Publié: (2024)

SparseGrad: A Selective Method for Efficient Fine-tuning of MLP Layers
par: Chekalina, Viktoriia, et autres
Publié: (2024)

BayesPrompt: Prompting Large-Scale Pre-Trained Language Models on Few-shot Inference via Debiased Domain Abstraction
par: Li, Jiangmeng, et autres
Publié: (2024)

A Simple Ensemble Strategy for LLM Inference: Towards More Stable Text Classification
par: Niimi, Junichiro
Publié: (2025)

With Greater Text Comes Greater Necessity: Inference-Time Training Helps Long Text Generation
par: Wang, Y., et autres
Publié: (2024)

Enhancing LLM-Based Text Classification in Political Science: Automatic Prompt Optimization and Dynamic Exemplar Selection for Few-Shot Learning
par: Liu, Menglin, et autres
Publié: (2024)

Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time
par: Yang, Wang, et autres
Publié: (2025)

Label Distribution Learning-Enhanced Dual-KNN for Text Classification
par: Yuan, Bo, et autres
Publié: (2025)

Interdisciplinary Fairness in Imbalanced Research Proposal Topic Inference: A Hierarchical Transformer-based Method with Selective Interpolation
par: Xiao, Meng, et autres
Publié: (2023)

Selective Attention Federated Learning: Improving Privacy and Efficiency for Clinical Text Classification
par: Li, Yue, et autres
Publié: (2025)