Cover Image

Neural steering vectors reveal dose and exposure-dependent impacts of human-AI relationships

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kirk, Hannah Rose, Davidson, Henry, Saunders, Ed, Luettgau, Lennart, Vidgen, Bertie, Hale, Scott A., Summerfield, Christopher
Format:	Preprint
Published:	2025
Subjects:	Human-Computer Interaction
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Why human-AI relationships need socioaffective alignment
by: Kirk, Hannah Rose, et al.
Published: (2025)

PRISM-X: Experiments on Personalised Fine-Tuning with Human and Simulated Users
by: Kirk, Hannah Rose, et al.
Published: (2026)

Conversational AI increases political knowledge as effectively as self-directed internet search
by: Luettgau, Lennart, et al.
Published: (2025)

SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models
by: Vidgen, Bertie, et al.
Published: (2023)

When Do LLM Preferences Predict Downstream Behavior?
by: Slama, Katarina, et al.
Published: (2026)

Ask don't tell: Reducing sycophancy in large language models
by: Dubois, Magda, et al.
Published: (2026)

XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
by: Röttger, Paul, et al.
Published: (2023)

People readily follow personal advice from AI but it does not improve their well-being
by: Luettgau, Lennart, et al.
Published: (2025)

HiBayES: A Hierarchical Bayesian Modeling Framework for AI Evaluation Statistics
by: Luettgau, Lennart, et al.
Published: (2025)

Multilingual != Multicultural: Evaluating Gaps Between Multilingual Capabilities and Cultural Alignment in LLMs
by: Rystrøm, Jonathan, et al.
Published: (2025)

Measuring and Mitigating Persona Distortions from AI Writing Assistance
by: Röttger, Paul, et al.
Published: (2026)

The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models
by: Kirk, Hannah Rose, et al.
Published: (2024)

Lessons from a Chimp: AI "Scheming" and the Quest for Ape Language
by: Summerfield, Christopher, et al.
Published: (2025)

Vulnerability-Amplifying Interaction Loops: a systematic failure mode in AI chatbot mental-health interactions
by: Weilnhammer, Veith, et al.
Published: (2026)

SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety
by: Röttger, Paul, et al.
Published: (2024)

Classification is a RAG problem: A case study on hate speech detection
by: Willats, Richard, et al.
Published: (2025)

Disclosure By Design: Identity Transparency as a Behavioural Property of Conversational AI Models
by: Gausen, Anna, et al.
Published: (2026)

One-shot emergency psychiatric triage across 15 frontier AI chatbots
by: Weilnhammer, Veith, et al.
Published: (2026)

Reward Model Interpretability via Optimal and Pessimal Tokens
by: Christian, Brian, et al.
Published: (2025)

Oregon County Library Service, 1965.
by: Davidson, Rose, Ed.
Published: (1966)

Indian-BhED: A Dataset for Measuring India-Centric Biases in Large Language Models
by: Khandelwal, Khyati, et al.
Published: (2023)

Technological folie à deux: Feedback Loops Between AI Chatbots and Mental Illness
by: Dohnány, Sebastian, et al.
Published: (2025)

WorkBench: a Benchmark Dataset for Agents in a Realistic Workplace Setting
by: Styles, Olly, et al.
Published: (2024)

Reward Models Inherit Value Biases from Pretraining
by: Christian, Brian, et al.
Published: (2026)

Robust estimation of causal dose-response relationship using exposure data with dose as an instrumental variable
by: Wang, Jixian, et al.
Published: (2025)

The AI Consumer Index (ACE)
by: Benchek, Julien, et al.
Published: (2025)

Early learning of the optimal constant solution in neural networks and humans
by: Rubruck, Jirko, et al.
Published: (2024)

The benefit of dose-exposure-response modeling in the estimation of dose-response relationship and dose optimization: some theoretical and simulation evidence
by: Wang, Jixian, et al.
Published: (2025)

Skewed Score: A statistical framework to assess autograders
by: Dubois, Magda, et al.
Published: (2025)

The AI Community Building the Future? A Quantitative Analysis of Development Activity on Hugging Face Hub
by: Osborne, Cailean, et al.
Published: (2024)

LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low-Resource and Extinct Languages
by: Bean, Andrew M., et al.
Published: (2024)

The paradoxical cycle of neutral genesis
by: Summerfield, Joel
Published: (2025)

Effects of the Changing Employment Situation on Urban Chinese Woman
by: Summerfield, Gale
Published: (1994)

Lie Algebra Decomposition Classes for Reductive Algebraic Groups in Arbitrary Characteristic
by: Summerfield, Joel
Published: (2025)

Topics in English for the Secondary School.
by: Summerfield, Geoffrey
Published: (1965)

Can sparse autoencoders be used to decompose and interpret steering vectors?
by: Mayne, Harry, et al.
Published: (2024)

LMUnit: Fine-grained Evaluation with Natural Language Unit Tests
by: Saad-Falcon, Jon, et al.
Published: (2024)

‘Cheering on from the side‐lines’: The perceived impact of romantic partner's commentary and behaviour on maintaining women's appearance anxiety
by: Gemma Stephanie Lumsdale, et al.
Published: (2024)

Analysis of human steering behavior differences in human-in-control and autonomy-in-control driving
by: Mai, Rene, et al.
Published: (2024)

Real‐world evidence for computerized insulin dose‐adjustment algorithms in the effective use of continuous glucose monitoring by primary care clinicians
by: Mayer B. Davidson, et al.
Published: (2024)