arXiv AI July 3, 2026 By Amin Banayeeanzade, Ala N. Tak, Fatemeh Bahrani, Anahita Bolourani, Leonardo Blas, Emilio Ferrara, Jonathan Gratch, Sai Praneeth Karimireddy

Psychological Steering in LLMs: An Evaluation of Effectiveness and Trustworthiness

Read the original on arXiv AI →

arXiv:2510. 04484v2 Announce Type: replace-cross Abstract: The ability to control LLMs' emulated emotional states and personality traits is an essential step in enabling rich, human-centered interactions in socially interactive settings.

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 arXiv AI.

arXiv AI

Jun 29

Low-Agreeableness Persona Conditioning for Safe LLM Fine-Tuning

arXiv:2606. 27709v1 Announce Type: cross Abstract: Recent work has shown that fine-tuning large language models (LLMs) for social warmth degrades factual reliability and increases sycophancy.

By Austin MY Cheung, Yi Yang

llms diffusion fine-tuning safety

arXiv AI

Aug 13

SteeringSafety: Benchmarking Representation Steering in LLMs Across Safety Perspectives

arXiv:2509. 13450v3 Announce Type: replace Abstract: We introduce SteeringSafety, a benchmark for evaluating representation steering methods across nine safety perspectives spanning 18 datasets.

By Vincent Siu, Nicholas Crispino, David Park, Nathan W. Henry, Zhun Wang, Yang Liu, Dawn Song, Chenguang Wang

llms benchmarks safety

arXiv Computation and Language

Aug 31

The Company You Keep: How LLMs Respond to Dark Triad Traits

arXiv:2603.04299v5 Announce Type: replace Abstract: LLMs often exhibit highly agreeable conversational styles, also known as AI sycophancy. This pattern may become problematic when interacting with u...

By Angelica Henestrosa, Zeyi Lu, Pavel Chizhov, Ivan P. Yamshchikov

llms

arXiv AI

Jun 9

The Governance of Human-LLM Interaction: Safety Gating, Civility Steering, and Affective Default Lock-In

arXiv:2606. 08172v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly mediate high-stakes interactions in finance, medicine, and mental-health support, yet users have limited control over how these systems communicate.

By Manuele Reani, Hongjian Zhang, Hongyu Tian

llms agents safety

arXiv AI

Jun 18

Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts

arXiv:2606. 18258v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit a wide range of human-like behaviors, from expressing thoughts and emotions, to engaging in relationship-building with users, to refusing requests and maintaining boundaries.

By Sunnie S. Y. Kim, Margit Bowler, Leon A Gatys

llms

arXiv Computation and Language

Sep 1

Do LLMs Change Their Minds Like Humans? Diagnosing Human--LLM Divergence in Single-Turn Persuasion Judgments

arXiv:2608.29803v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as proxies for human participants in social simulations, yet whether they update their beliefs...

By Lin Chen, Yitong Chen, Yong Li

llms

One email a morning, machine-written

Related stories

Low-Agreeableness Persona Conditioning for Safe LLM Fine-Tuning

SteeringSafety: Benchmarking Representation Steering in LLMs Across Safety Perspectives

The Company You Keep: How LLMs Respond to Dark Triad Traits

The Governance of Human-LLM Interaction: Safety Gating, Civility Steering, and Affective Default Lock-In

Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts

Do LLMs Change Their Minds Like Humans? Diagnosing Human--LLM Divergence in Single-Turn Persuasion Judgments