Hugging Face Trending Papers August 12, 2026

Locating and Controlling Implicit Personalization in Large Language Models

Read the original on Hugging Face Trending Papers →

Large language models (LLMs) often shift their outputs in response to implicit demographic cues even when users never state a demographic identity. Previous work has documented this behavior, but the connection between these behavioral changes and the model's internal activations remains unclear.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

arXiv AI

Aug 13

Locating and Controlling Implicit Personalization in Large Language Models

arXiv:2608. 11735v1 Announce Type: cross Abstract: Large language models (LLMs) often shift their outputs in response to implicit demographic cues even when users never state a demographic identity.

By Yueru Yan, Siqi Wu, Thai Le

llms benchmarks

arXiv Computation and Language

Sep 1

Different Demographic Cues Yield Inconsistent Conclusions About LLM Personalization and Bias

The paper examines how large language models (LLMs) respond to different demographic cues—such as names—when users seek advice, focusing on race and gender in a U.S. context. It finds that using different cues for the same group leads to only partially overlapping changes in model responses, producing inconsistent conclusions about personalization and unstable bias metrics. The authors argue that LLMs react to linguistic signals tied to cues rather than to stable demographic categories, and they call for evaluations that use multiple cues and consider underlying mechanisms.

By Manuel Tonneau, Neil K. R. Sehgal, Niyati Malhotra, Sharif Kazemi, Victor Orozco-Olvera, Ana Mar\'ia Mu\~noz Boudet, Lakshmi Subramanian, Samuel P. Fraiberger, Sharath Chandra Guntuku, Valentin Hofmann

llms safety

arXiv AI

Sep 1

Evaluating the Hidden Costs of Personalization in Large Language Models

arXiv:2608.28833v1 Announce Type: new Abstract: While Large language models (LLMs) incorporate user personalization signals to improve usability and helpfulness, they increasingly shift from providin...

By Yumeng Wang, Yuchen Wu, Cheng Qian, Zhiyuan Fan, Hyeonjeong Ha, Shujin Wu, Jiayu Liu, Heng Ji, Ge Wang

llms safety

arXiv AI

Jul 24

ImplicitBBQ: Benchmarking Implicit Bias in Large Language Models through Characteristic Based Cues

arXiv:2604. 01925v2 Announce Type: replace-cross Abstract: Large Language Models increasingly suppress biased outputs when demographic identity is stated explicitly, yet may still exhibit implicit biases when identity is conveyed indirectly.

By Bhaskara Hanuma Vedula, Darshan Anghan, Ishita Goyal, Ponnurangam Kumaraguru, Abhijnan Chakraborty

llms benchmarks safety

arXiv AI

Sep 16

The Role of Implicit and Explicit Demographic Signals in Large Language Model-based Student Assessment

arXiv:2609.16993v1 Announce Type: cross Abstract: Large Language Models are now common in student assessment, but we know little about how student demographics affect their use. Sometimes, considerin...

By Donya Rooein, Luca Benedetto, Dirk Hovy

llms nlp benchmarks

arXiv Computation and Language

Sep 22

Privacy Personalization Trade offs in LLMs: The Impact of Stylometric Signal Reduction on User-Specific Text Generation

arXiv:2609.22112v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated the ability to generate user-specific text with high stylistic fidelity. However, the personal data that...

By Muhammed Nazmul Arefin, Omar Jamal Hammad

llms benchmarks safety

One email a morning, machine-written

Related stories

Locating and Controlling Implicit Personalization in Large Language Models

Different Demographic Cues Yield Inconsistent Conclusions About LLM Personalization and Bias

Evaluating the Hidden Costs of Personalization in Large Language Models

ImplicitBBQ: Benchmarking Implicit Bias in Large Language Models through Characteristic Based Cues

The Role of Implicit and Explicit Demographic Signals in Large Language Model-based Student Assessment

Privacy Personalization Trade offs in LLMs: The Impact of Stylometric Signal Reduction on User-Specific Text Generation