Buchumschlag

Under Pressure: Emotional Framing Induces Measurable Behavioral Shifts and Structured Internal Geometry in Small Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
1. Verfasser:	Usman, Rana Muhammad
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Computation and Language Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Shared Emotion Geometry Across Small Language Models: A Cross-Architecture Study of Representation, Behavior, and Methodological Confounds
von: Jeong, Jihoon
Veröffentlicht: (2026)

Framing Political Bias in Multilingual LLMs Across Pakistani Languages
von: Nadeem, Afrozah, et al.
Veröffentlicht: (2025)

Beyond Semantics: Measuring Fine-Grained Emotion Preservation in Small Language Model-Based Machine Translation
von: Wisniewski, Dawid, et al.
Veröffentlicht: (2026)

Measuring Representation Robustness in Large Language Models for Geometry
von: Jawandhia, Vedant, et al.
Veröffentlicht: (2026)

Extracting and Steering Emotion Representations in Small Language Models: A Methodological Comparison
von: Jeong, Jihoon
Veröffentlicht: (2026)

Context Structure Reshapes the Representational Geometry of Language Models
von: Hosseini, Eghbal A., et al.
Veröffentlicht: (2026)

Framing Effects in Independent-Agent Large Language Models: A Cross-Family Behavioral Analysis
von: Wang, Zice, et al.
Veröffentlicht: (2026)

Valence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control
von: Sun, Lihao, et al.
Veröffentlicht: (2026)

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults
von: Usman, Rana Muhammad
Veröffentlicht: (2026)

From Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty
von: Ivgi, Maor, et al.
Veröffentlicht: (2024)

DeFrame: Debiasing Large Language Models Against Framing Effects
von: Lim, Kahee, et al.
Veröffentlicht: (2026)

ChatGPT Reads Your Tone and Responds Accordingly -- Until It Does Not -- Emotional Framing Induces Bias in LLM Outputs
von: Bardol, Franck
Veröffentlicht: (2025)

Small Language Models: Survey, Measurements, and Insights
von: Lu, Zhenyan, et al.
Veröffentlicht: (2024)

Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors
von: Huang, Jing, et al.
Veröffentlicht: (2025)

Behavior Trees Enable Structured Programming of Language Model Agents
von: Kelley, Richard
Veröffentlicht: (2024)

Calibrating Reasoning in Language Models with Internal Consistency
von: Xie, Zhihui, et al.
Veröffentlicht: (2024)

Sadeed: Advancing Arabic Diacritization Through Small Language Model
von: Aldallal, Zeina, et al.
Veröffentlicht: (2025)

BiasLab: A Multilingual, Dual-Framing Framework for Robust Measurement of Output-Level Bias in Large Language Models
von: Guey, William, et al.
Veröffentlicht: (2026)

How Prompts Move Language Model Behavior: Frames, Salience, and Construal as Semantic Control
von: Kim, Dongseok, et al.
Veröffentlicht: (2025)

The Shape of Wisdom: Decision Trajectories in Language Models
von: Rana, Shailesh
Veröffentlicht: (2026)

SC-Phi2: A Fine-tuned Small Language Model for StarCraft II Macromanagement Tasks
von: Khan, Muhammad Junaid, et al.
Veröffentlicht: (2024)

Once Upon a Time: Interactive Learning for Storytelling with Small Language Models
von: Martins, Jonas Mayer, et al.
Veröffentlicht: (2025)

Large Language Model as a Catalyst: A Paradigm Shift in Base Station Siting Optimization
von: Wang, Yanhu, et al.
Veröffentlicht: (2024)

Large Language Models can Strategically Deceive their Users when Put Under Pressure
von: Scheurer, Jérémy, et al.
Veröffentlicht: (2023)

Mutarjim: Advancing Bidirectional Arabic-English Translation with a Small Language Model
von: Hennara, Khalil, et al.
Veröffentlicht: (2025)

Large Language Models for Cuffless Blood Pressure Measurement From Wearable Biosignals
von: Liu, Zengding, et al.
Veröffentlicht: (2024)

Measuring Stability Beyond Accuracy in Small Open-Source Medical Large Language Models for Pediatric Endocrinology
von: D'Amario, Vanessa, et al.
Veröffentlicht: (2025)

InfiR : Crafting Effective Small Language Models and Multimodal Small Language Models in Reasoning
von: Xie, Congkai, et al.
Veröffentlicht: (2025)

Mechanistic Interpretability of Socio-Political Frames in Language Models
von: Asghari, Hadi, et al.
Veröffentlicht: (2025)

Enhancing Emotional Generation Capability of Large Language Models via Emotional Chain-of-Thought
von: Li, Zaijing, et al.
Veröffentlicht: (2024)

Translating Under Pressure: Domain-Aware LLMs for Crisis Communication
von: Castaldo, Antonio, et al.
Veröffentlicht: (2026)

Small Language Model as Data Prospector for Large Language Model
von: Ni, Shiwen, et al.
Veröffentlicht: (2024)

TInR: Exploring Tool-Internalized Reasoning in Large Language Models
von: Xu, Qiancheng, et al.
Veröffentlicht: (2026)

Learning Uncertainty from Sequential Internal Dispersion in Large Language Models
von: Srey, Ponhvoan, et al.
Veröffentlicht: (2026)

Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals
von: Torrielli, Federico, et al.
Veröffentlicht: (2026)

From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning
von: Wu, Xuansheng, et al.
Veröffentlicht: (2023)

Self-Prompting Small Language Models for Privacy-Sensitive Clinical Information Extraction
von: Chuang, Yao-Shun, et al.
Veröffentlicht: (2026)

Hallucination Detection with Small Language Models
von: Cheung, Ming
Veröffentlicht: (2025)

Multilingual Hate Speech Detection in Social Media Using Translation-Based Approaches with Large Language Models
von: Usman, Muhammad, et al.
Veröffentlicht: (2025)

The Dog the Cat Chased Stumped the Model: Measuring When Language Models Abandon Structure for Shortcuts
von: Madhusudan, Sangmitra, et al.
Veröffentlicht: (2025)