Copertina

Elucidating Mechanisms of Demographic Bias in LLMs for Healthcare

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ahsan, Hiba, Sharma, Arnab Sen, Amir, Silvio, Bau, David, Wallace, Byron C.
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

Can SAEs reveal and mitigate racial biases of LLMs in healthcare?
di: Ahsan, Hiba, et al.
Pubblicazione: (2025)

Retrieving Evidence from EHRs with LLMs: Possibilities and Challenges
di: Ahsan, Hiba, et al.
Pubblicazione: (2023)

Locating and Editing Factual Associations in Mamba
di: Sharma, Arnab Sen, et al.
Pubblicazione: (2024)

Function Vectors in Large Language Models
di: Todd, Eric, et al.
Pubblicazione: (2023)

Vector Arithmetic in Concept and Token Subspaces
di: Feucht, Sheridan, et al.
Pubblicazione: (2025)

Circuit Distillation
di: Wadhwa, Somin, et al.
Pubblicazione: (2025)

Revisiting Relation Extraction in the era of Large Language Models
di: Wadhwa, Somin, et al.
Pubblicazione: (2023)

Investigating Mysteries of CoT-Augmented Distillation
di: Wadhwa, Somin, et al.
Pubblicazione: (2024)

Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs
di: Feucht, Sheridan, et al.
Pubblicazione: (2024)

On-the-fly Definition Augmentation of LLMs for Biomedical NER
di: Munnangi, Monica, et al.
Pubblicazione: (2024)

Who Taught You That? Tracing Teachers in Model Distillation
di: Wadhwa, Somin, et al.
Pubblicazione: (2025)

The Dual-Route Model of Induction
di: Feucht, Sheridan, et al.
Pubblicazione: (2025)

Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
di: Pal, Koyena, et al.
Pubblicazione: (2023)

Open (Clinical) LLMs are Sensitive to Instruction Phrasings
di: Arroyo, Alberto Mario Ceballos, et al.
Pubblicazione: (2024)

Evaluating the Bias in LLMs for Surveying Opinion and Decision Making in Healthcare
di: Khaokaew, Yonchanok, et al.
Pubblicazione: (2025)

Linearity of Relation Decoding in Transformer Language Models
di: Hernandez, Evan, et al.
Pubblicazione: (2023)

Assessing the Reliability of LLMs Annotations in the Context of Demographic Bias and Model Explanation
di: Mohammadi, Hadi, et al.
Pubblicazione: (2025)

Language Models use Lookbacks to Track Beliefs
di: Prakash, Nikhil, et al.
Pubblicazione: (2025)

Robustness and Confounders in the Demographic Alignment of LLMs with Human Perceptions of Offensiveness
di: Alipour, Shayan, et al.
Pubblicazione: (2024)

Do Automatic Factuality Metrics Measure Factuality? A Critical Evaluation
di: Ramprasad, Sanjana, et al.
Pubblicazione: (2024)

LLMs Do Not See Age: Assessing Demographic Bias in Automated Systematic Review Synthesis
di: Aghaebe, Favour Yahdii, et al.
Pubblicazione: (2025)

Evaluating LLMs for Demographic-Targeted Social Bias Detection: A Comprehensive Benchmark Study
di: Majumdar, Ayan, et al.
Pubblicazione: (2025)

LLMs Encode Harmfulness and Refusal Separately
di: Zhao, Jiachen, et al.
Pubblicazione: (2025)

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective
di: Chandna, Bhavik, et al.
Pubblicazione: (2025)

Sometimes the Model doth Preach: Quantifying Religious Bias in Open LLMs through Demographic Analysis in Asian Nations
di: Shankar, Hari, et al.
Pubblicazione: (2025)

Leveraging ChatGPT in Pharmacovigilance Event Extraction: An Empirical Study
di: Sun, Zhaoyue, et al.
Pubblicazione: (2024)

oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning
di: Xu, Ruiling, et al.
Pubblicazione: (2025)

CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMs
di: Nikeghbal, Nafiseh, et al.
Pubblicazione: (2025)

LLMs for Explainable AI: A Comprehensive Survey
di: Bilal, Ahsan, et al.
Pubblicazione: (2025)

The Confidence Trap: Gender Bias and Predictive Certainty in LLMs
di: Sabir, Ahmed, et al.
Pubblicazione: (2026)

Are LLMs Rational Investors? A Study on Detecting and Reducing the Financial Bias in LLMs
di: Zhou, Yuhang, et al.
Pubblicazione: (2024)

LLMs Process Lists With General Filter Heads
di: Sharma, Arnab Sen, et al.
Pubblicazione: (2025)

Measuring Mechanistic Independence: Can Bias Be Removed Without Erasing Demographics?
di: Shan, Zhengyang, et al.
Pubblicazione: (2025)

Measuring AI "Slop" in Text
di: Shaib, Chantal, et al.
Pubblicazione: (2025)

Detection and Measurement of Syntactic Templates in Generated Text
di: Shaib, Chantal, et al.
Pubblicazione: (2024)

Mechanics of Bias and Reasoning: Interpreting the Impact of Chain-of-Thought Prompting on Gender Bias in LLMs
di: Pearman, Edie, et al.
Pubblicazione: (2026)

Automatically Extracting Numerical Results from Randomized Controlled Trials with Large Language Models
di: Yun, Hye Sun, et al.
Pubblicazione: (2024)

Caught in the Web of Words: Do LLMs Fall for Spin in Medical Literature?
di: Yun, Hye Sun, et al.
Pubblicazione: (2025)

Which Demographics do LLMs Default to During Annotation?
di: Schäfer, Johannes, et al.
Pubblicazione: (2024)

Different Demographic Cues Yield Inconsistent Conclusions About LLM Personalization and Bias
di: Tonneau, Manuel, et al.
Pubblicazione: (2026)