Image de couverture de livre

Controllable and explainable personality sliders for LLMs at inference time

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hoppe, Florian, Khachaturov, David, Mullins, Robert, Meng, Mark Huasong
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Complexity Matters: Effective Dimensionality as a Measure for Adversarial Robustness
par: Khachaturov, David, et autres
Publié: (2024)

Verbalizing LLMs' assumptions to explain and control sycophancy
par: Cheng, Myra, et autres
Publié: (2026)

Feedback Forensics: A Toolkit to Measure AI Personality
par: Findeis, Arduin, et autres
Publié: (2025)

GlitchProber: Advancing Effective Detection and Mitigation of Glitch Tokens in Large Language Models
par: Zhang, Zhibo, et autres
Publié: (2024)

Inverse Constitutional AI: Compressing Preferences into Principles
par: Findeis, Arduin, et autres
Publié: (2024)

Watermarking Needs Input Repetition Masking
par: Khachaturov, David, et autres
Publié: (2025)

Large language models struggle with ethnographic text annotation
par: Goodall, Leonardo S., et autres
Publié: (2026)

Enhancing reasoning accuracy in large language models during inference time
par: Sharma, Vinay, et autres
Publié: (2026)

Nondeterministic Polynomial-time Problem Challenge: An Ever-Scaling Reasoning Benchmark for LLMs
par: Yang, Chang, et autres
Publié: (2025)

Identifying Good and Bad Neurons for Task-Level Controllable LLMs
par: Li, Wenjie, et autres
Publié: (2026)

Learning and Enforcing Context-Sensitive Control for LLMs
par: Albinhassan, Mohammad, et autres
Publié: (2026)

Tailored Conversations beyond LLMs: A RL-Based Dialogue Manager
par: Galland, Lucie, et autres
Publié: (2025)

Adversarial Suffix Filtering: a Defense Pipeline for LLMs
par: Khachaturov, David, et autres
Publié: (2025)

Detecting and explaining postpartum depression in real-time with generative artificial intelligence
par: García-Méndez, Silvia, et autres
Publié: (2025)

Investigating the Robustness of Deductive Reasoning with Large Language Models
par: Hoppe, Fabian, et autres
Publié: (2025)

Two-dimensional early exit optimisation of LLM inference
par: Hůla, Jan, et autres
Publié: (2026)

Testing the Limits of Truth Directions in LLMs
par: Poulis, Angelos, et autres
Publié: (2026)

Fairness Evaluation and Inference Level Mitigation in LLMs
par: Nadeem, Afrozah, et autres
Publié: (2025)

An overview of model uncertainty and variability in LLM-based sentiment analysis. Challenges, mitigation strategies and the role of explainability
par: Herrera-Poyatos, David, et autres
Publié: (2025)

Multi-Personality Generation of LLMs at Decoding-time
par: Chen, Rongxin, et autres
Publié: (2025)

Steering Towards Fairness: Mitigating Political Bias in LLMs
par: Nadeem, Afrozah, et autres
Publié: (2025)

KV Cache Steering for Controlling Frozen LLMs
par: Belitsky, Max, et autres
Publié: (2025)

Towards Optimizing and Evaluating a Retrieval Augmented QA Chatbot using LLMs with Human in the Loop
par: Afzal, Anum, et autres
Publié: (2024)

Framing Political Bias in Multilingual LLMs Across Pakistani Languages
par: Nadeem, Afrozah, et autres
Publié: (2025)

Do LLMs "Feel"? Emotion Circuits Discovery and Control
par: Wang, Chenxi, et autres
Publié: (2025)

TokenSkip: Controllable Chain-of-Thought Compression in LLMs
par: Xia, Heming, et autres
Publié: (2025)

CCR-Bench: A Comprehensive Benchmark for Evaluating LLMs on Complex Constraints, Control Flows, and Real-World Cases
par: Xue, Xiaona, et autres
Publié: (2026)

Using LLMs to identify features of personal and professional skills in an open-response situational judgment test
par: Walsh, Cole, et autres
Publié: (2025)

PAD: Personalized Alignment of LLMs at Decoding-Time
par: Chen, Ruizhe, et autres
Publié: (2024)

Can We Edit LLMs for Long-Tail Biomedical Knowledge?
par: Yi, Xinhao, et autres
Publié: (2025)

Relative Bias: A Comparative Framework for Quantifying Bias in LLMs
par: Arbabi, Alireza, et autres
Publié: (2025)

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models
par: An, Bang, et autres
Publié: (2025)

Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time
par: Tan, Daniel, et autres
Publié: (2025)

Reasoning Primitives in Hybrid and Non-Hybrid LLMs: Do Architectural Differences Yield Advantages in State-Tracking and Recall?
par: Rawat, Shivam, et autres
Publié: (2026)

Exploiting the English Vocabulary Profile for L2 word-level vocabulary assessment with LLMs
par: Bannò, Stefano, et autres
Publié: (2025)

Attribute-Aware Controlled Product Generation with LLMs for E-commerce
par: Negri, Virginia, et autres
Publié: (2025)

Evaluating and explaining training strategies for zero-shot cross-lingual news sentiment analysis
par: Andrenšek, Luka, et autres
Publié: (2024)

An explainable transformer circuit for compositional generalization
par: Tang, Cheng, et autres
Publié: (2025)

The Political Preferences of LLMs
par: Rozado, David
Publié: (2024)

LLMs as Function Approximators: Terminology, Taxonomy, and Questions for Evaluation
par: Schlangen, David
Publié: (2024)