Copertina

Ensemble Debiasing Across Class and Sample Levels for Fairer Prompting Accuracy

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lin, Ruixi, Wang, Ziqiao, You, Yang
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Optimizing Class-Level Probability Reweighting Coefficients for Equitable Prompting Accuracy
di: Lin, Ruixi, et al.
Pubblicazione: (2024)

Let the Fuzzy Rule Speak: Enhancing In-context Learning Debiasing with Interpretability
di: Lin, Ruixi, et al.
Pubblicazione: (2024)

Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey
di: Parraga, Otávio, et al.
Pubblicazione: (2022)

Rethinking Prompt-based Debiasing in Large Language Models
di: Yang, Xinyi, et al.
Pubblicazione: (2025)

LH-Mix: Local Hierarchy Correlation Guided Mixup over Hierarchical Prompt Tuning
di: Kong, Fanshuang, et al.
Pubblicazione: (2024)

On SkipGram Word Embedding Models with Negative Sampling: Unified Framework and Impact of Noise Distributions
di: Liu, Dezhi, et al.
Pubblicazione: (2020)

Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustment
di: Zhang, Congzhi, et al.
Pubblicazione: (2024)

General Phrase Debiaser: Debiasing Masked Language Models at a Multi-Token Level
di: Shi, Bingkang, et al.
Pubblicazione: (2023)

Learning Optimal Prompt Ensemble for Multi-source Visual Prompt Transfer
di: Zhang, Enming, et al.
Pubblicazione: (2025)

Thinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Models
di: Furniturewala, Shaz, et al.
Pubblicazione: (2024)

Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Prompts
di: Lin, Yujie, et al.
Pubblicazione: (2026)

Logical Negation Augmenting and Debiasing for Prompt-based Methods
di: Li, Yitian, et al.
Pubblicazione: (2024)

HateDebias: On the Diversity and Variability of Hate Speech Debiasing
di: Wu, Hongyan, et al.
Pubblicazione: (2024)

Can a large language model be a gaslighter?
di: Li, Wei, et al.
Pubblicazione: (2024)

ConsPrompt: Exploiting Contrastive Samples for Fewshot Prompt Learning
di: Weng, Jinta, et al.
Pubblicazione: (2022)

Debiasing Text Safety Classifiers through a Fairness-Aware Ensemble
di: Sturman, Olivia, et al.
Pubblicazione: (2024)

FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs
di: Dehdashtian, Sepehr, et al.
Pubblicazione: (2024)

Unlabeled Debiasing in Downstream Tasks via Class-wise Low Variance Regularization
di: Masoudian, Shahed, et al.
Pubblicazione: (2024)

Discovering the Hidden Role of Gini Index In Prompt-based Classification
di: Lin, Ruixi
Pubblicazione: (2026)

Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments
di: Zhou, Han, et al.
Pubblicazione: (2024)

Reducing Biases towards Minoritized Populations in Medical Curricular Content via Artificial Intelligence for Fairer Health Outcomes
di: Salavati, Chiman, et al.
Pubblicazione: (2024)

When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling
di: Yun, Heecheol, et al.
Pubblicazione: (2025)

Debiasing Large Language Models via Adaptive Causal Prompting with Sketch-of-Thought
di: Li, Bowen, et al.
Pubblicazione: (2026)

Activated Parameter Locating via Causal Intervention for Model Merging
di: Kong, Fanshuang, et al.
Pubblicazione: (2024)

MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling
di: Limisiewicz, Tomasz, et al.
Pubblicazione: (2024)

Can We Afford The Perfect Prompt? Balancing Cost and Accuracy with the Economical Prompting Index
di: McDonald, Tyler, et al.
Pubblicazione: (2024)

Teacher-Student Training for Debiasing: General Permutation Debiasing for Large Language Models
di: Liusie, Adian, et al.
Pubblicazione: (2024)

More Samples or More Prompts? Exploring Effective In-Context Sampling for LLM Few-Shot Prompt Engineering
di: Yao, Bingsheng, et al.
Pubblicazione: (2023)

BayesPrompt: Prompting Large-Scale Pre-Trained Language Models on Few-shot Inference via Debiased Domain Abstraction
di: Li, Jiangmeng, et al.
Pubblicazione: (2024)

Accuracy and Consistency of LLMs in the Registered Dietitian Exam: The Impact of Prompt Engineering and Knowledge Retrieval
di: Azimi, Iman, et al.
Pubblicazione: (2024)

Beyond Self-Consistency: Ensemble Reasoning Boosts Consistency and Accuracy of LLMs in Cancer Staging
di: Chang, Chia-Hsuan, et al.
Pubblicazione: (2024)

M-Ped: Multi-Prompt Ensemble Decoding for Large Language Models
di: Guo, Jiaxin, et al.
Pubblicazione: (2024)

AURORA:Automated Training Framework of Universal Process Reward Models via Ensemble Prompting and Reverse Verification
di: Tan, Xiaoyu, et al.
Pubblicazione: (2025)

Traditional Chinese Medicine Case Analysis System for High-Level Semantic Abstraction: Optimized with Prompt and RAG
di: Xu, Peng, et al.
Pubblicazione: (2024)

Towards Multimodal Sentiment Analysis Debiasing via Bias Purification
di: Yang, Dingkang, et al.
Pubblicazione: (2024)

Babysit A Language Model From Scratch: Interactive Language Learning by Trials and Demonstrations
di: Ma, Ziqiao, et al.
Pubblicazione: (2024)

Robust Persona-Aware Toxicity Detection with Prompt Optimization and Learned Ensembling
di: Atil, Berk, et al.
Pubblicazione: (2026)

FairJudge: An Adaptive, Debiased, and Consistent LLM-as-a-Judge
di: Yang, Bo, et al.
Pubblicazione: (2026)

DeCAP: Context-Adaptive Prompt Generation for Debiasing Zero-shot Question Answering in Large Language Models
di: Bae, Suyoung, et al.
Pubblicazione: (2025)

Beyond Accuracy: Diagnosing Algebraic Reasoning Failures in LLMs Across Nine Complexity Dimensions
di: Patil, Parth, et al.
Pubblicazione: (2026)