Beyond prompt brittleness: Evaluating the reliability and consistency of political worldviews in LLMs
Fuente:
arXiv
Guardado en:
| Autores principales: | Ceron, Tanise, Falk, Neele, Barić, Ana, Nikolaev, Dmitry, Padó, Sebastian |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
Do Political Opinions Transfer Between Western Languages? An Analysis of Unaligned and Aligned Multilingual LLMs
por: Weeber, Franziska, et al.
Publicado: (2025)
por: Weeber, Franziska, et al.
Publicado: (2025)
What Is The Political Content in LLMs' Pre- and Post-Training Data?
por: Ceron, Tanise, et al.
Publicado: (2025)
por: Ceron, Tanise, et al.
Publicado: (2025)
Actor Identification in Discourse: A Challenge for LLMs?
por: Barić, Ana, et al.
Publicado: (2024)
por: Barić, Ana, et al.
Publicado: (2024)
Toeing the Party Line: Election Manifestos as a Key to Understand Political Discourse on Twitter
por: Maurer, Maximilian, et al.
Publicado: (2024)
por: Maurer, Maximilian, et al.
Publicado: (2024)
Generalizability of Media Frames: Corpus creation and analysis across countries
por: Daffara, Agnese, et al.
Publicado: (2025)
por: Daffara, Agnese, et al.
Publicado: (2025)
Approximate Attributions for Off-the-Shelf Siamese Transformers
por: Möller, Lucas, et al.
Publicado: (2024)
por: Möller, Lucas, et al.
Publicado: (2024)
Beyond Marginal Distributions: A Framework to Evaluate the Representativeness of Demographic-Aligned LLMs
por: Williams, Tristan, et al.
Publicado: (2026)
por: Williams, Tristan, et al.
Publicado: (2026)
Multi-Dimensional Machine Translation Evaluation: Model Evaluation and Resource for Korean
por: Park, Dojun, et al.
Publicado: (2024)
por: Park, Dojun, et al.
Publicado: (2024)
Using LLMs as prompt modifier to avoid biases in AI image generators
por: Peinl, René
Publicado: (2025)
por: Peinl, René
Publicado: (2025)
Strategies for political-statement segmentation and labelling in unstructured text
por: Nikolaev, Dmitry, et al.
Publicado: (2025)
por: Nikolaev, Dmitry, et al.
Publicado: (2025)
Do Language Models Encode Knowledge of Linguistic Constraint Violations?
por: Hardy, et al.
Publicado: (2026)
por: Hardy, et al.
Publicado: (2026)
Overview of PerpectiveArg2024: The First Shared Task on Perspective Argument Retrieval
por: Falk, Neele, et al.
Publicado: (2024)
por: Falk, Neele, et al.
Publicado: (2024)
Investigating Subjective Factors of Argument Strength: Storytelling, Emotions, and Hedging
por: Quensel, Carlotta, et al.
Publicado: (2025)
por: Quensel, Carlotta, et al.
Publicado: (2025)
Finding Sense in Nonsense with Generated Contexts: Perspectives from Humans and Language Models
por: Olsen, Katrina, et al.
Publicado: (2026)
por: Olsen, Katrina, et al.
Publicado: (2026)
Beyond Accuracy: Diagnosing Algebraic Reasoning Failures in LLMs Across Nine Complexity Dimensions
por: Patil, Parth, et al.
Publicado: (2026)
por: Patil, Parth, et al.
Publicado: (2026)
An evaluation of LLMs for political bias in Western media: Israel-Hamas and Ukraine-Russia wars
por: Chandra, Rohitash, et al.
Publicado: (2026)
por: Chandra, Rohitash, et al.
Publicado: (2026)
Identifying attributions of causality in political text
por: Garcia-Corral, Paulina
Publicado: (2025)
por: Garcia-Corral, Paulina
Publicado: (2025)
Artwork Interpretation with Vision Language Models: A Case Study on Emotions and Emotion Symbols
por: Padó, Sebastian, et al.
Publicado: (2025)
por: Padó, Sebastian, et al.
Publicado: (2025)
LLMs are Biased Teachers: Evaluating LLM Bias in Personalized Education
por: Weissburg, Iain, et al.
Publicado: (2024)
por: Weissburg, Iain, et al.
Publicado: (2024)
Evaluating the Simulation of Human Personality-Driven Susceptibility to Misinformation with LLMs
por: Pratelli, Manuel, et al.
Publicado: (2025)
por: Pratelli, Manuel, et al.
Publicado: (2025)
LLMs left, right, and center: Assessing GPT's capabilities to label political bias from web domains
por: Hernandes, Raphael, et al.
Publicado: (2024)
por: Hernandes, Raphael, et al.
Publicado: (2024)
What About the Scene with the Hitler Reference? HAUNT: A Framework to Probe LLMs' Self-consistency Via Adversarial Nudge
por: Dutta, Arka, et al.
Publicado: (2025)
por: Dutta, Arka, et al.
Publicado: (2025)
Between Help and Harm: An Evaluation of Mental Health Crisis Handling by LLMs
por: Arnaiz-Rodriguez, Adrian, et al.
Publicado: (2025)
por: Arnaiz-Rodriguez, Adrian, et al.
Publicado: (2025)
Surfacing Subtle Stereotypes: A Multilingual, Debate-Oriented Evaluation of Modern LLMs
por: Saeed, Muhammed, et al.
Publicado: (2025)
por: Saeed, Muhammed, et al.
Publicado: (2025)
Towards Understanding the Relationship between In-context Learning and Compositional Generalization
por: Han, Sungjun, et al.
Publicado: (2024)
por: Han, Sungjun, et al.
Publicado: (2024)
Exploring Safety Alignment Evaluation of LLMs in Chinese Mental Health Dialogues via LLM-as-Judge
por: Cai, Yunna, et al.
Publicado: (2025)
por: Cai, Yunna, et al.
Publicado: (2025)
Politicians vs ChatGPT. A study of presuppositions in French and Italian political communication
por: Garassino, Davide, et al.
Publicado: (2024)
por: Garassino, Davide, et al.
Publicado: (2024)
The Statistical Signature of LLMs
por: Hadad, Ortal, et al.
Publicado: (2026)
por: Hadad, Ortal, et al.
Publicado: (2026)
How Far Are LLMs from Believable AI? A Benchmark for Evaluating the Believability of Human Behavior Simulation
por: Xiao, Yang, et al.
Publicado: (2023)
por: Xiao, Yang, et al.
Publicado: (2023)
On the Credibility of Evaluating LLMs using Survey Questions
por: Libovický, Jindřich
Publicado: (2026)
por: Libovický, Jindřich
Publicado: (2026)
Evaluating the Promise and Pitfalls of LLMs in Hiring Decisions
por: Anzenberg, Eitan, et al.
Publicado: (2025)
por: Anzenberg, Eitan, et al.
Publicado: (2025)
MEDEQUALQA: Evaluating Biases in LLMs with Counterfactual Reasoning
por: Ghosh, Rajarshi, et al.
Publicado: (2025)
por: Ghosh, Rajarshi, et al.
Publicado: (2025)
Truth Knows No Language: Evaluating Truthfulness Beyond English
por: Figueras, Blanca Calvo, et al.
Publicado: (2025)
por: Figueras, Blanca Calvo, et al.
Publicado: (2025)
Efficient Language Modeling for Low-Resource Settings with Hybrid RNN-Transformer Architectures
por: Lindenmaier, Gabriel, et al.
Publicado: (2025)
por: Lindenmaier, Gabriel, et al.
Publicado: (2025)
Diverging Transformer Predictions for Human Sentence Processing: A Comprehensive Analysis of Agreement Attraction Effects
por: von der Malsburg, Titus, et al.
Publicado: (2026)
por: von der Malsburg, Titus, et al.
Publicado: (2026)
Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts
por: Aldahoul, Nouar, et al.
Publicado: (2025)
por: Aldahoul, Nouar, et al.
Publicado: (2025)
Evaluating the Capabilities of LLMs for Supporting Anticipatory Impact Assessment
por: Allaham, Mowafak, et al.
Publicado: (2024)
por: Allaham, Mowafak, et al.
Publicado: (2024)
Evaluating Cultural Awareness of LLMs for Yoruba, Malayalam, and English
por: Dawson, Fiifi, et al.
Publicado: (2024)
por: Dawson, Fiifi, et al.
Publicado: (2024)
Your Students Don't Use LLMs Like You Wish They Did
por: Kobler, Sebastian, et al.
Publicado: (2026)
por: Kobler, Sebastian, et al.
Publicado: (2026)
RTP-LX: Can LLMs Evaluate Toxicity in Multilingual Scenarios?
por: de Wynter, Adrian, et al.
Publicado: (2024)
por: de Wynter, Adrian, et al.
Publicado: (2024)
Ejemplares similares
-
Do Political Opinions Transfer Between Western Languages? An Analysis of Unaligned and Aligned Multilingual LLMs
por: Weeber, Franziska, et al.
Publicado: (2025) -
What Is The Political Content in LLMs' Pre- and Post-Training Data?
por: Ceron, Tanise, et al.
Publicado: (2025) -
Actor Identification in Discourse: A Challenge for LLMs?
por: Barić, Ana, et al.
Publicado: (2024) -
Toeing the Party Line: Election Manifestos as a Key to Understand Political Discourse on Twitter
por: Maurer, Maximilian, et al.
Publicado: (2024) -
Generalizability of Media Frames: Corpus creation and analysis across countries
por: Daffara, Agnese, et al.
Publicado: (2025)