Same Question, Different Answer? Measuring and Mitigating Prompt Privilege for Equitable AI Access
Lier Jin, Lan Hu, Binqi Shen, Hanyu Cai, Yuting Xin
cs.CL
Submitted: 2026-08-09
Updated: 2026-08-11
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Adhera: A Human-Centered Health Informatics Solution for Reducing Informal Caregiver Burden through Improved Medication Adherence
- Interpretable Factor Decomposition for Decision Intelligence in Large-Scale Financial Markets: Evidence from China's A-Share Market
- Beyond Chat: a Framework for LLMs as Human-Centered Support Systems
- Risk-based test framework for LLM features in regulated software
- PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts
- A Volume-Price-Adjusted MACD Trading Strategy with Sensitivity Calibration for U.S. Equity Indices
- When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems
- Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict
- Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAG
- Non-Intrusive Graph-Based Bot Detection for E-Commerce Using Inductive Graph Neural Networks
- PACED: Distillation and On-Policy Self-Distillation at the Frontier of Student Competence
- Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training
- DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models
- SCRIBE: Structured Mid-Level Supervision for Tool-Using Language Models
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering